Publications
Search
West, Taylor N.; Prinzing, Michael M.; Garton, Catherine; Berman, Catherine J.; Zhou, Jieni; Hale, James; Gratch, Jonathan; Fredrickson, Barbara L.
Improving social connection with weak ties and strangers: effects of a new micro-intervention on interaction quality and social behavior Journal Article
In: The Journal of Positive Psychology, vol. 20, no. 4, pp. 652–662, 2025, ISSN: 1743-9760, 1743-9779.
@article{west_improving_2025,
title = {Improving social connection with weak ties and strangers: effects of a new micro-intervention on interaction quality and social behavior},
author = {Taylor N. West and Michael M. Prinzing and Catherine Garton and Catherine J. Berman and Jieni Zhou and James Hale and Jonathan Gratch and Barbara L. Fredrickson},
url = {https://www.tandfonline.com/doi/full/10.1080/17439760.2024.2394451},
doi = {10.1080/17439760.2024.2394451},
issn = {1743-9760, 1743-9779},
year = {2025},
date = {2025-07-01},
urldate = {2025-06-25},
journal = {The Journal of Positive Psychology},
volume = {20},
number = {4},
pages = {652–662},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gurney, Nikolos; Miller, John H.; Pynadath, David V.
Exploring the choice landscape: Anchoring and framing effects on search behavior in complex choices Journal Article
In: Journal of Choice Modelling, vol. 55, pp. 100549, 2025, ISSN: 17555345.
@article{gurney_exploring_2025,
title = {Exploring the choice landscape: Anchoring and framing effects on search behavior in complex choices},
author = {Nikolos Gurney and John H. Miller and David V. Pynadath},
url = {https://linkinghub.elsevier.com/retrieve/pii/S1755534525000120},
doi = {10.1016/j.jocm.2025.100549},
issn = {17555345},
year = {2025},
date = {2025-06-01},
urldate = {2025-04-15},
journal = {Journal of Choice Modelling},
volume = {55},
pages = {100549},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Klumpe, Stella; Mitchell, Kelsey C.; Cox, Emma; Katz, Jeffrey S.; Lazarowski, Lucia; Deshpande, Gopikrishna; Gratch, Jonathan; Visser, Ewart J. De; Ayaz, Hasan; Li, Xingnan; Franke, Adrian A.; Krueger, Frank
Social bonding between humans, animals, and robots: Dogs outperform AIBOs, their robotic replicas, as social companions Journal Article
In: PLoS One, vol. 20, no. 6, pp. e0324312, 2025, ISSN: 1932-6203.
@article{klumpe_social_2025,
title = {Social bonding between humans, animals, and robots: Dogs outperform AIBOs, their robotic replicas, as social companions},
author = {Stella Klumpe and Kelsey C. Mitchell and Emma Cox and Jeffrey S. Katz and Lucia Lazarowski and Gopikrishna Deshpande and Jonathan Gratch and Ewart J. De Visser and Hasan Ayaz and Xingnan Li and Adrian A. Franke and Frank Krueger},
editor = {Casey R. Lynch},
url = {https://dx.plos.org/10.1371/journal.pone.0324312},
doi = {10.1371/journal.pone.0324312},
issn = {1932-6203},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-12},
journal = {PLoS One},
volume = {20},
number = {6},
pages = {e0324312},
abstract = {In the evolving landscape of technology, robots have emerged as social companions, prompting an investigation into social bonding between humans and robots. While human-animal interactions are well-studied, human-robot interactions (HRI) remain comparatively underexplored. Ethorobotics, a field of social robotic engineering based on ecology and ethology, suggests designing companion robots modeled on animal companions, which are simpler to emulate than humans. However, it is unclear whether these robots can match the social companionship provided by their original models. This study examined social bonding between humans and AIBOs, dog-inspired companion robots, compared to real dogs. Nineteen female participants engaged in 12 affiliative interactions with dogs and AIBOs across two counter-balanced, one-month bonding phases. Social bonding was assessed through urinary oxytocin (OXT) level change over an interaction, self-reported attachment using an adapted version of the Lexington Attachment to Pets Scale, and social companionship evaluations administering the Robot-Dog Questionnaire. To examine OXT level changes and self-reported attachment by comparing the two social companions, we conducted mixed-effects model analyses and planned follow-up comparisons. Frequency comparison, binary logistic regression, and thematic analysis were performed to analyze social companionship evaluations. Results revealed significant differences between dogs and AIBOs in fostering social bonds. OXT level change increased during interactions with dogs but decreased with AIBOs. Participants reported stronger attachment to dogs and rated them as better social companions. These findings highlight the current limitations of AIBOs in fostering social bonding immediately compared to dogs. Our study contributes to the growing HRI research by demonstrating an existing gap between AIBOs and dogs as social companions. It highlights the need for further investigation to understand the complexities of social bonding with companion robots, which is essential to implement successful applications for social robots in diverse domains such as the elderly and health care, education, and entertainment.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Chang, Di; Cao, Mingdeng; Shi, Yichun; Liu, Bo; Cai, Shengqu; Zhou, Shijie; Huang, Weilin; Wetzstein, Gordon; Soleymani, Mohammad; Wang, Peng
ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions Miscellaneous
2025, (arXiv:2506.03107 [cs]).
@misc{chang_bytemorph_2025,
title = {ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions},
author = {Di Chang and Mingdeng Cao and Yichun Shi and Bo Liu and Shengqu Cai and Shijie Zhou and Weilin Huang and Gordon Wetzstein and Mohammad Soleymani and Peng Wang},
url = {http://arxiv.org/abs/2506.03107},
doi = {10.48550/arXiv.2506.03107},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-17},
publisher = {arXiv},
abstract = {Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing approaches and datasets predominantly focus on static scenes or rigid transformations, limiting their capacity to handle expressive edits involving dynamic motion. To address this gap, we introduce ByteMorph, a comprehensive framework for instruction-based image editing with an emphasis on non-rigid motions. ByteMorph comprises a large-scale dataset, ByteMorph-6M, and a strong baseline model built upon the Diffusion Transformer (DiT), named ByteMorpher. ByteMorph-6M includes over 6 million high-resolution image editing pairs for training, along with a carefully curated evaluation benchmark ByteMorph-Bench. Both capture a wide variety of non-rigid motion types across diverse environments, human figures, and object categories. The dataset is constructed using motion-guided data generation, layered compositing techniques, and automated captioning to ensure diversity, realism, and semantic coherence. We further conduct a comprehensive evaluation of recent instruction-based image editing methods from both academic and commercial domains.},
note = {arXiv:2506.03107 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Hale, James; Kim, Peter H.; Gratch, Jonathan
“Provably fair” algorithms may perpetuate racial and gender bias: a study of salary dispute resolution Journal Article
In: Auton Agent Multi-Agent Syst, vol. 39, no. 1, pp. 20, 2025, ISSN: 1387-2532, 1573-7454.
@article{hale_provably_2025,
title = {“Provably fair” algorithms may perpetuate racial and gender bias: a study of salary dispute resolution},
author = {James Hale and Peter H. Kim and Jonathan Gratch},
url = {https://link.springer.com/10.1007/s10458-025-09703-x},
doi = {10.1007/s10458-025-09703-x},
issn = {1387-2532, 1573-7454},
year = {2025},
date = {2025-06-01},
urldate = {2025-03-18},
journal = {Auton Agent Multi-Agent Syst},
volume = {39},
number = {1},
pages = {20},
abstract = {Abstract
Prior work suggests automated dispute resolution tools using “provably fair” algorithms can address disparities between demographic groups. These methods use multi-criteria elicited preferences from all disputants and satisfy constraints to generate “fair” solutions. However, we analyze the potential for inequity to permeate proposals through the preference elicitation stage. This possibility arises if differences in dispositional attitudes differ between demographics, and those dispositions affect elicited preferences. Specifically, risk aversion plays a prominent role in predicting preferences. Risk aversion predicts a weaker relative preference for
salary
and a softer within-issue utility for each issue; this leads to worse compensation packages for risk-averse groups. These results raise important questions in AI-value alignment about whether an AI mediator should take explicit preferences at face value.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Prior work suggests automated dispute resolution tools using “provably fair” algorithms can address disparities between demographic groups. These methods use multi-criteria elicited preferences from all disputants and satisfy constraints to generate “fair” solutions. However, we analyze the potential for inequity to permeate proposals through the preference elicitation stage. This possibility arises if differences in dispositional attitudes differ between demographics, and those dispositions affect elicited preferences. Specifically, risk aversion plays a prominent role in predicting preferences. Risk aversion predicts a weaker relative preference for
salary
and a softer within-issue utility for each issue; this leads to worse compensation packages for risk-averse groups. These results raise important questions in AI-value alignment about whether an AI mediator should take explicit preferences at face value.
Traum, David; Brixey, Jacqueline
Does a code-switching dialogue system help users learn conversational fluency in Choctaw? Journal Article
In: Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), pp. 8-17, 2025, ISBN: 979-8-89176-236-7.
@article{brixey-traum-2025-code,
title = {Does a code-switching dialogue system help users learn conversational fluency in Choctaw?},
author = {David Traum and Jacqueline Brixey},
url = {https://aclanthology.org/2025.americasnlp-1.2/},
doi = {10.18653/v1/2025.americasnlp-1.2},
isbn = {979-8-89176-236-7},
year = {2025},
date = {2025-05-05},
urldate = {2025-05-05},
journal = {Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)},
pages = {8-17},
publisher = {Association for Computational Linguistics},
address = {Albuquerque, New Mexico},
abstract = {We investigate the learning outcomes and user response to a chatbot for practicing conversational Choctaw, an endangered American Indigenous language. Conversational fluency is a goal for many language learners, however, for learners of endangered languages in North America, access to fluent speakers may be limited. Chatbots are potentially ideal dialogue partners as this kind of dialogue system fulfills a non-authoritative role by focusing on carrying on a conversation as an equal conversational partner. The goal of the chatbot investigated in this work is to serve as a conversational partner in the absence of a fluent Choctaw-speaking human interlocutor. We investigate the impact of code-switching in the interaction, comparing a bilingual chatbot against a monolingual Choctaw version. We evaluate the systems for user engagement and enjoyment, as well as gains in conversational fluency from interacting with the system.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Okado, Yuko; Nye, Benjamin D.; Aguirre, Angelica; Swartout, William
In: Int J Artif Intell Educ, 2025, ISSN: 1560-4292, 1560-4306.
@article{okado_how_2025,
title = {How Can Virtual Agents Scale Up Mentoring?: Insights from College Students’ Experiences Using the CareerFair.ai Platform at an American Hispanic-Serving Institution},
author = {Yuko Okado and Benjamin D. Nye and Angelica Aguirre and William Swartout},
url = {https://link.springer.com/10.1007/s40593-025-00482-w},
doi = {10.1007/s40593-025-00482-w},
issn = {1560-4292, 1560-4306},
year = {2025},
date = {2025-05-01},
urldate = {2025-06-24},
journal = {Int J Artif Intell Educ},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Core, Mark; Nye, Benjamin; Carr, Kayla; Li, Shirley; Shiel, Aaron; Auerbach, Daniel; Leeds, Andrew; Swartout, William
Usability and Preferences for a Personalized Adaptive Learning System for AI Upskilling Journal Article
In: FLAIRS, vol. 38, 2025, ISSN: 2334-0762, 2334-0754.
@article{core_usability_2025,
title = {Usability and Preferences for a Personalized Adaptive Learning System for AI Upskilling},
author = {Mark Core and Benjamin Nye and Kayla Carr and Shirley Li and Aaron Shiel and Daniel Auerbach and Andrew Leeds and William Swartout},
url = {https://journals.flvc.org/FLAIRS/article/view/138996},
doi = {10.32473/flairs.38.1.138996},
issn = {2334-0762, 2334-0754},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-20},
journal = {FLAIRS},
volume = {38},
abstract = {As AI tools become common across jobs and industries, it is critical to broaden education about AI beyond teaching computer scientists how to build AI systems. To expand AI education, we are researching AI for AI learning: a personalized and adaptive learning system that integrates dialog-based tutoring and gamified programming activities. To study this problem, we adapted and expanded an existing smartphone adaptive coach to develop the Game-if-AI system. Using a design-based research approach, Game-if-AI was iteratively tested and improved across four semesters of optional use in a course designed for technician-level understanding of AI: mastering programming skills to apply AI libraries and established models. In this study, we measured the interests and needs of these technical learners, based on both survey data and on how they engaged with topics in the system. Based on this data, new topics were added and the system was refined. In this paper, we report students' usability ratings for system components and student preferences based on completion rates of AI topics available each semester. Students rated the adaptive system positively overall (93% rated as a "good idea"), but more complex learning activities (tutoring dialogs, programming) were rated lower than traditional ones (e.g., multiple choice, reading). Students were most likely to master topics highly aligned to the course materials, as well as self-directed learning toward easier high-interest topics (e.g., LLM Prompting).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wang, Ning; Fu, Boxi; Dincer, Betul; Masur, Omkar; Faizi, David; Ravindran, Harshul; Wang, Julia; Lai, Devashish; Merchant, Chirag
Becoming Fei: An Educational Game for AI and Data Science Education for Novice Learners Book Section
In: Smith, Brian K.; Borge, Marcela (Ed.): Learning and Collaboration Technologies, vol. 15808, pp. 69–79, Springer Nature Switzerland, Cham, 2025, ISBN: 978-3-031-93745-3 978-3-031-93746-0, (Series Title: Lecture Notes in Computer Science).
@incollection{smith_becoming_2025,
title = {Becoming Fei: An Educational Game for AI and Data Science Education for Novice Learners},
author = {Ning Wang and Boxi Fu and Betul Dincer and Omkar Masur and David Faizi and Harshul Ravindran and Julia Wang and Devashish Lai and Chirag Merchant},
editor = {Brian K. Smith and Marcela Borge},
url = {https://link.springer.com/10.1007/978-3-031-93746-0_6},
doi = {10.1007/978-3-031-93746-0_6},
isbn = {978-3-031-93745-3 978-3-031-93746-0},
year = {2025},
date = {2025-05-01},
urldate = {2025-06-12},
booktitle = {Learning and Collaboration Technologies},
volume = {15808},
pages = {69–79},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Awada, Mohamad; Gerber, Burcin Becerik; Lucas, Gale M.; Roll, Shawn C.
The Impact of Color Correlated Temperature and Illuminance Levels of Office Lighting on Stress and Cognitive Restoration Journal Article
In: Journal of Environmental Psychology, pp. 102628, 2025, ISSN: 02724944.
@article{awada_impact_2025,
title = {The Impact of Color Correlated Temperature and Illuminance Levels of Office Lighting on Stress and Cognitive Restoration},
author = {Mohamad Awada and Burcin Becerik Gerber and Gale M. Lucas and Shawn C. Roll},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0272494425001112},
doi = {10.1016/j.jenvp.2025.102628},
issn = {02724944},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-20},
journal = {Journal of Environmental Psychology},
pages = {102628},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gordon, Andrew
Logical Abduction as a Computational Model of Narrative Proceedings Article
In: Geneva, Switzerland, 2025.
@inproceedings{gordon_andrew_logical_2025,
title = {Logical Abduction as a Computational Model of Narrative},
author = {Andrew Gordon},
url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://asgordon.github.io/publications/CMN2025.PDF},
year = {2025},
date = {2025-05-01},
address = {Geneva, Switzerland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chaubey, Ashutosh; Guan, Xulang; Soleymani, Mohammad
Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning Miscellaneous
2025, (Version Number: 1).
@misc{chaubey_face-llava_2025,
title = {Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning},
author = {Ashutosh Chaubey and Xulang Guan and Mohammad Soleymani},
url = {https://arxiv.org/abs/2504.07198},
doi = {10.48550/ARXIV.2504.07198},
year = {2025},
date = {2025-04-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {The human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications. We propose Face-LLaVA, a multimodal large language model for face-centered, in-context learning, including facial expression and attribute recognition. Additionally, Face-LLaVA is able to generate natural language descriptions that can be used for reasoning. Leveraging existing visual databases, we first developed FaceInstruct-1M, a face-centered database for instruction tuning MLLMs for face processing. We then developed a novel face-specific visual encoder powered by Face-Region Guided Cross-Attention that integrates face geometry with local visual features. We evaluated the proposed method across nine different datasets and five different face processing tasks, including facial expression recognition, action unit detection, facial attribute detection, age estimation and deepfake detection. Face-LLaVA achieves superior results compared to existing open-source MLLMs and competitive performance compared to commercial solutions. Our model output also receives a higher reasoning rating by GPT under a zero-shot setting across all the tasks. Both our dataset and model wil be released at https://face-llava.github.io to support future advancements in social AI and foundational vision-language research.},
note = {Version Number: 1},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Hale, James; Rakshit, Sushrita; Chawla, Kushal; Brett, Jeanne M.; Gratch, Jonathan
KODIS: A Multicultural Dispute Resolution Dialogue Corpus Miscellaneous
2025, (arXiv:2504.12723 [cs]).
@misc{hale_kodis_2025,
title = {KODIS: A Multicultural Dispute Resolution Dialogue Corpus},
author = {James Hale and Sushrita Rakshit and Kushal Chawla and Jeanne M. Brett and Jonathan Gratch},
url = {http://arxiv.org/abs/2504.12723},
doi = {10.48550/arXiv.2504.12723},
year = {2025},
date = {2025-04-01},
urldate = {2025-05-20},
publisher = {arXiv},
abstract = {We present KODIS, a dyadic dispute resolution corpus containing thousands of dialogues from over 75 countries. Motivated by a theoretical model of culture and conflict, participants engage in a typical customer service dispute designed by experts to evoke strong emotions and conflict. The corpus contains a rich set of dispositional, process, and outcome measures. The initial analysis supports theories of how anger expressions lead to escalatory spirals and highlights cultural differences in emotional expression. We make this corpus and data collection framework available to the community.},
note = {arXiv:2504.12723 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Lin, Spencer; Jun, Miru; Rizk, Basem; Shieh, Karen; Fisher, Scott; Mozgai, Sharon
Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework Proceedings Article
In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–9, 2025, (arXiv:2504.14427 [cs]).
@inproceedings{lin_optimizing_2025,
title = {Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework},
author = {Spencer Lin and Miru Jun and Basem Rizk and Karen Shieh and Scott Fisher and Sharon Mozgai},
url = {http://arxiv.org/abs/2504.14427},
doi = {10.1145/3706599.3707399},
year = {2025},
date = {2025-04-01},
urldate = {2025-05-20},
booktitle = {Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
pages = {1–9},
abstract = {This case study presents our user-centered design model for Socially Intelligent Agent (SIA) development frameworks through our experience developing Estuary, an open source multimodal framework for building low-latency real-time socially interactive agents. We leverage the Rapid Assessment Process (RAP) to collect the thoughts of leading researchers in the field of SIAs regarding the current state of the art for SIA development as well as their evaluation of how well Estuary may potentially address current research gaps. We achieve this through a series of end-user interviews conducted by a fellow researcher in the community. We hope that the findings of our work will not only assist the continued development of Estuary but also guide the development of other future frameworks and technologies for SIAs.},
note = {arXiv:2504.14427 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Brun, Antonin; Lucas, Gale; Becerik-Gerber, Burçin
Under Pressure: Contextualizing Workplace Stress Towards User-Centered Interventions Proceedings Article
In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–9, ACM, Yokohama Japan, 2025, ISBN: 979-8-4007-1395-8.
@inproceedings{brun_under_2025,
title = {Under Pressure: Contextualizing Workplace Stress Towards User-Centered Interventions},
author = {Antonin Brun and Gale Lucas and Burçin Becerik-Gerber},
url = {https://dl.acm.org/doi/10.1145/3706599.3719987},
doi = {10.1145/3706599.3719987},
isbn = {979-8-4007-1395-8},
year = {2025},
date = {2025-04-01},
urldate = {2025-06-12},
booktitle = {Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
pages = {1–9},
publisher = {ACM},
address = {Yokohama Japan},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liu, Ziming; Xu, Jiuyi; Suen, Christine Wun Ki; Chen, Meida; Zou, Zhengbo; Shi, Yangming
Egocentric camera-based method for detecting static hazardous objects on construction sites Journal Article
In: Automation in Construction, vol. 172, pp. 106048, 2025, ISSN: 09265805.
@article{liu_egocentric_2025,
title = {Egocentric camera-based method for detecting static hazardous objects on construction sites},
author = {Ziming Liu and Jiuyi Xu and Christine Wun Ki Suen and Meida Chen and Zhengbo Zou and Yangming Shi},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0926580525000883},
doi = {10.1016/j.autcon.2025.106048},
issn = {09265805},
year = {2025},
date = {2025-04-01},
urldate = {2025-03-18},
journal = {Automation in Construction},
volume = {172},
pages = {106048},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Siniukov, Maksim; Chang, Di; Tran, Minh; Gong, Hongkun; Chaubey, Ashutosh; Soleymani, Mohammad
DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion Miscellaneous
2025, (Version Number: 1).
@misc{siniukov_ditailistener_2025,
title = {DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion},
author = {Maksim Siniukov and Di Chang and Minh Tran and Hongkun Gong and Ashutosh Chaubey and Mohammad Soleymani},
url = {https://arxiv.org/abs/2504.04010},
doi = {10.48550/ARXIV.2504.04010},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {Generating naturalistic and nuanced listener motions for extended interactions remains an open problem. Existing methods often rely on low-dimensional motion codes for facial behavior generation followed by photorealistic rendering, limiting both visual fidelity and expressive richness. To address these challenges, we introduce DiTaiListener, powered by a video diffusion model with multimodal conditions. Our approach first generates short segments of listener responses conditioned on the speaker's speech and facial motions with DiTaiListener-Gen. It then refines the transitional frames via DiTaiListener-Edit for a seamless transition. Specifically, DiTaiListener-Gen adapts a Diffusion Transformer (DiT) for the task of listener head portrait generation by introducing a Causal Temporal Multimodal Adapter (CTM-Adapter) to process speakers' auditory and visual cues. CTM-Adapter integrates speakers' input in a causal manner into the video generation process to ensure temporally coherent listener responses. For long-form video generation, we introduce DiTaiListener-Edit, a transition refinement video-to-video diffusion model. The model fuses video segments into smooth and continuous videos, ensuring temporal consistency in facial expressions and image quality when merging short video segments produced by DiTaiListener-Gen. Quantitatively, DiTaiListener achieves the state-of-the-art performance on benchmark datasets in both photorealism (+73.8% in FID on RealTalk) and motion representation (+6.1% in FD metric on VICO) spaces. User studies confirm the superior performance of DiTaiListener, with the model being the clear preference in terms of feedback, diversity, and smoothness, outperforming competitors by a significant margin.},
note = {Version Number: 1},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Gurney, Nikolos; Pynadath, David V.; Miller, John H.
Willingness to work as a predictor of human-agent team success Journal Article
In: Front. Comput. Sci., vol. 7, pp. 1405436, 2025, ISSN: 2624-9898.
@article{gurney_willingness_2025,
title = {Willingness to work as a predictor of human-agent team success},
author = {Nikolos Gurney and David V. Pynadath and John H. Miller},
url = {https://www.frontiersin.org/articles/10.3389/fcomp.2025.1405436/full},
doi = {10.3389/fcomp.2025.1405436},
issn = {2624-9898},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
journal = {Front. Comput. Sci.},
volume = {7},
pages = {1405436},
abstract = {Research shows that the effectiveness of human-agent teams depends heavily on human team members' prior experiences, whether from direct teaming activities or relevant domain knowledge. While researchers have proposed various mechanisms to explain this relationship, we present a simpler alternative explanation: experience serves primarily as an indicator of a person's fundamental willingness to engage in teaming tasks. We introduce a measure called “willingness to work” that quantifies this underlying disposition. Our empirical analysis demonstrates that this straightforward metric robustly predicts human-agent team performance. Beyond its practical value as a predictive tool, this reconceptualization of the experience-performance relationship necessitates a fresh examination of existing findings in the field. The results suggest that a team member's basic willingness to invest effort may be more fundamental to success than previously recognized mechanisms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ustun, Volkan; Hans, Soham; Kumar, Rajay; Wang, Yunzhe
Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning Miscellaneous
2025, (arXiv:2503.20078 [cs]).
@misc{ustun_abstracting_2025,
title = {Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning},
author = {Volkan Ustun and Soham Hans and Rajay Kumar and Yunzhe Wang},
url = {http://arxiv.org/abs/2503.20078},
doi = {10.48550/arXiv.2503.20078},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Frameworks such as Unity's ML-Agents help to make such reinforcement learning experiments more accessible to the simulation community. Military training simulations also benefit from advances in MARL, but they have immense computational requirements due to their complex, continuous, stochastic, partially observable, non-stationary, and doctrine-based nature. Furthermore, these simulations require geo-specific terrains, further exacerbating the computational resources problem. In our research, we leverage Unity's waypoints to automatically generate multi-layered representation abstractions of the geo-specific terrains to scale up reinforcement learning while still allowing the transfer of learned policies between different representations. Our early exploratory results on a novel MARL scenario, where each side has differing objectives, indicate that waypoint-based navigation enables faster and more efficient learning while producing trajectories similar to those taken by expert human players in CSGO gaming environments. This research points out the potential of waypoint-based navigation for reducing the computational costs of developing and training MARL models for military training simulations, where geo-specific terrains and differing objectives are crucial.},
note = {arXiv:2503.20078 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Liu, Ruying; Becerik-Gerber, Burcin; Pynadath, David V.; Marti, Deniz; Lucas, Gale M.
Elicitation and verification of learning via experts (EVOLVE) for creating a theoretical framework for active shooter incidents Journal Article
In: Developments in the Built Environment, vol. 21, pp. 100635, 2025, ISSN: 26661659.
@article{liu_elicitation_2025,
title = {Elicitation and verification of learning via experts (EVOLVE) for creating a theoretical framework for active shooter incidents},
author = {Ruying Liu and Burcin Becerik-Gerber and David V. Pynadath and Deniz Marti and Gale M. Lucas},
url = {https://linkinghub.elsevier.com/retrieve/pii/S2666165925000353},
doi = {10.1016/j.dibe.2025.100635},
issn = {26661659},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-18},
journal = {Developments in the Built Environment},
volume = {21},
pages = {100635},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Filter
2025
West, Taylor N.; Prinzing, Michael M.; Garton, Catherine; Berman, Catherine J.; Zhou, Jieni; Hale, James; Gratch, Jonathan; Fredrickson, Barbara L.
Improving social connection with weak ties and strangers: effects of a new micro-intervention on interaction quality and social behavior Journal Article
In: The Journal of Positive Psychology, vol. 20, no. 4, pp. 652–662, 2025, ISSN: 1743-9760, 1743-9779.
@article{west_improving_2025,
title = {Improving social connection with weak ties and strangers: effects of a new micro-intervention on interaction quality and social behavior},
author = {Taylor N. West and Michael M. Prinzing and Catherine Garton and Catherine J. Berman and Jieni Zhou and James Hale and Jonathan Gratch and Barbara L. Fredrickson},
url = {https://www.tandfonline.com/doi/full/10.1080/17439760.2024.2394451},
doi = {10.1080/17439760.2024.2394451},
issn = {1743-9760, 1743-9779},
year = {2025},
date = {2025-07-01},
urldate = {2025-06-25},
journal = {The Journal of Positive Psychology},
volume = {20},
number = {4},
pages = {652–662},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gurney, Nikolos; Miller, John H.; Pynadath, David V.
Exploring the choice landscape: Anchoring and framing effects on search behavior in complex choices Journal Article
In: Journal of Choice Modelling, vol. 55, pp. 100549, 2025, ISSN: 17555345.
@article{gurney_exploring_2025,
title = {Exploring the choice landscape: Anchoring and framing effects on search behavior in complex choices},
author = {Nikolos Gurney and John H. Miller and David V. Pynadath},
url = {https://linkinghub.elsevier.com/retrieve/pii/S1755534525000120},
doi = {10.1016/j.jocm.2025.100549},
issn = {17555345},
year = {2025},
date = {2025-06-01},
urldate = {2025-04-15},
journal = {Journal of Choice Modelling},
volume = {55},
pages = {100549},
keywords = {DTIC},
pubstate = {published},
tppubtype = {article}
}
Klumpe, Stella; Mitchell, Kelsey C.; Cox, Emma; Katz, Jeffrey S.; Lazarowski, Lucia; Deshpande, Gopikrishna; Gratch, Jonathan; Visser, Ewart J. De; Ayaz, Hasan; Li, Xingnan; Franke, Adrian A.; Krueger, Frank
Social bonding between humans, animals, and robots: Dogs outperform AIBOs, their robotic replicas, as social companions Journal Article
In: PLoS One, vol. 20, no. 6, pp. e0324312, 2025, ISSN: 1932-6203.
Abstract | Links | BibTeX | Tags: DTIC
@article{klumpe_social_2025,
title = {Social bonding between humans, animals, and robots: Dogs outperform AIBOs, their robotic replicas, as social companions},
author = {Stella Klumpe and Kelsey C. Mitchell and Emma Cox and Jeffrey S. Katz and Lucia Lazarowski and Gopikrishna Deshpande and Jonathan Gratch and Ewart J. De Visser and Hasan Ayaz and Xingnan Li and Adrian A. Franke and Frank Krueger},
editor = {Casey R. Lynch},
url = {https://dx.plos.org/10.1371/journal.pone.0324312},
doi = {10.1371/journal.pone.0324312},
issn = {1932-6203},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-12},
journal = {PLoS One},
volume = {20},
number = {6},
pages = {e0324312},
abstract = {In the evolving landscape of technology, robots have emerged as social companions, prompting an investigation into social bonding between humans and robots. While human-animal interactions are well-studied, human-robot interactions (HRI) remain comparatively underexplored. Ethorobotics, a field of social robotic engineering based on ecology and ethology, suggests designing companion robots modeled on animal companions, which are simpler to emulate than humans. However, it is unclear whether these robots can match the social companionship provided by their original models. This study examined social bonding between humans and AIBOs, dog-inspired companion robots, compared to real dogs. Nineteen female participants engaged in 12 affiliative interactions with dogs and AIBOs across two counter-balanced, one-month bonding phases. Social bonding was assessed through urinary oxytocin (OXT) level change over an interaction, self-reported attachment using an adapted version of the Lexington Attachment to Pets Scale, and social companionship evaluations administering the Robot-Dog Questionnaire. To examine OXT level changes and self-reported attachment by comparing the two social companions, we conducted mixed-effects model analyses and planned follow-up comparisons. Frequency comparison, binary logistic regression, and thematic analysis were performed to analyze social companionship evaluations. Results revealed significant differences between dogs and AIBOs in fostering social bonds. OXT level change increased during interactions with dogs but decreased with AIBOs. Participants reported stronger attachment to dogs and rated them as better social companions. These findings highlight the current limitations of AIBOs in fostering social bonding immediately compared to dogs. Our study contributes to the growing HRI research by demonstrating an existing gap between AIBOs and dogs as social companions. It highlights the need for further investigation to understand the complexities of social bonding with companion robots, which is essential to implement successful applications for social robots in diverse domains such as the elderly and health care, education, and entertainment.},
keywords = {DTIC},
pubstate = {published},
tppubtype = {article}
}
Chang, Di; Cao, Mingdeng; Shi, Yichun; Liu, Bo; Cai, Shengqu; Zhou, Shijie; Huang, Weilin; Wetzstein, Gordon; Soleymani, Mohammad; Wang, Peng
ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions Miscellaneous
2025, (arXiv:2506.03107 [cs]).
Abstract | Links | BibTeX | Tags: VGL
@misc{chang_bytemorph_2025,
title = {ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions},
author = {Di Chang and Mingdeng Cao and Yichun Shi and Bo Liu and Shengqu Cai and Shijie Zhou and Weilin Huang and Gordon Wetzstein and Mohammad Soleymani and Peng Wang},
url = {http://arxiv.org/abs/2506.03107},
doi = {10.48550/arXiv.2506.03107},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-17},
publisher = {arXiv},
abstract = {Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing approaches and datasets predominantly focus on static scenes or rigid transformations, limiting their capacity to handle expressive edits involving dynamic motion. To address this gap, we introduce ByteMorph, a comprehensive framework for instruction-based image editing with an emphasis on non-rigid motions. ByteMorph comprises a large-scale dataset, ByteMorph-6M, and a strong baseline model built upon the Diffusion Transformer (DiT), named ByteMorpher. ByteMorph-6M includes over 6 million high-resolution image editing pairs for training, along with a carefully curated evaluation benchmark ByteMorph-Bench. Both capture a wide variety of non-rigid motion types across diverse environments, human figures, and object categories. The dataset is constructed using motion-guided data generation, layered compositing techniques, and automated captioning to ensure diversity, realism, and semantic coherence. We further conduct a comprehensive evaluation of recent instruction-based image editing methods from both academic and commercial domains.},
note = {arXiv:2506.03107 [cs]},
keywords = {VGL},
pubstate = {published},
tppubtype = {misc}
}
Hale, James; Kim, Peter H.; Gratch, Jonathan
“Provably fair” algorithms may perpetuate racial and gender bias: a study of salary dispute resolution Journal Article
In: Auton Agent Multi-Agent Syst, vol. 39, no. 1, pp. 20, 2025, ISSN: 1387-2532, 1573-7454.
Abstract | Links | BibTeX | Tags:
@article{hale_provably_2025,
title = {“Provably fair” algorithms may perpetuate racial and gender bias: a study of salary dispute resolution},
author = {James Hale and Peter H. Kim and Jonathan Gratch},
url = {https://link.springer.com/10.1007/s10458-025-09703-x},
doi = {10.1007/s10458-025-09703-x},
issn = {1387-2532, 1573-7454},
year = {2025},
date = {2025-06-01},
urldate = {2025-03-18},
journal = {Auton Agent Multi-Agent Syst},
volume = {39},
number = {1},
pages = {20},
abstract = {Abstract
Prior work suggests automated dispute resolution tools using “provably fair” algorithms can address disparities between demographic groups. These methods use multi-criteria elicited preferences from all disputants and satisfy constraints to generate “fair” solutions. However, we analyze the potential for inequity to permeate proposals through the preference elicitation stage. This possibility arises if differences in dispositional attitudes differ between demographics, and those dispositions affect elicited preferences. Specifically, risk aversion plays a prominent role in predicting preferences. Risk aversion predicts a weaker relative preference for
salary
and a softer within-issue utility for each issue; this leads to worse compensation packages for risk-averse groups. These results raise important questions in AI-value alignment about whether an AI mediator should take explicit preferences at face value.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Prior work suggests automated dispute resolution tools using “provably fair” algorithms can address disparities between demographic groups. These methods use multi-criteria elicited preferences from all disputants and satisfy constraints to generate “fair” solutions. However, we analyze the potential for inequity to permeate proposals through the preference elicitation stage. This possibility arises if differences in dispositional attitudes differ between demographics, and those dispositions affect elicited preferences. Specifically, risk aversion plays a prominent role in predicting preferences. Risk aversion predicts a weaker relative preference for
salary
and a softer within-issue utility for each issue; this leads to worse compensation packages for risk-averse groups. These results raise important questions in AI-value alignment about whether an AI mediator should take explicit preferences at face value.
Traum, David; Brixey, Jacqueline
Does a code-switching dialogue system help users learn conversational fluency in Choctaw? Journal Article
In: Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), pp. 8-17, 2025, ISBN: 979-8-89176-236-7.
Abstract | Links | BibTeX | Tags: Learning Sciences, LLM
@article{brixey-traum-2025-code,
title = {Does a code-switching dialogue system help users learn conversational fluency in Choctaw?},
author = {David Traum and Jacqueline Brixey},
url = {https://aclanthology.org/2025.americasnlp-1.2/},
doi = {10.18653/v1/2025.americasnlp-1.2},
isbn = {979-8-89176-236-7},
year = {2025},
date = {2025-05-05},
urldate = {2025-05-05},
journal = {Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)},
pages = {8-17},
publisher = {Association for Computational Linguistics},
address = {Albuquerque, New Mexico},
abstract = {We investigate the learning outcomes and user response to a chatbot for practicing conversational Choctaw, an endangered American Indigenous language. Conversational fluency is a goal for many language learners, however, for learners of endangered languages in North America, access to fluent speakers may be limited. Chatbots are potentially ideal dialogue partners as this kind of dialogue system fulfills a non-authoritative role by focusing on carrying on a conversation as an equal conversational partner. The goal of the chatbot investigated in this work is to serve as a conversational partner in the absence of a fluent Choctaw-speaking human interlocutor. We investigate the impact of code-switching in the interaction, comparing a bilingual chatbot against a monolingual Choctaw version. We evaluate the systems for user engagement and enjoyment, as well as gains in conversational fluency from interacting with the system.},
keywords = {Learning Sciences, LLM},
pubstate = {published},
tppubtype = {article}
}
Okado, Yuko; Nye, Benjamin D.; Aguirre, Angelica; Swartout, William
In: Int J Artif Intell Educ, 2025, ISSN: 1560-4292, 1560-4306.
Links | BibTeX | Tags: DTIC, Learning Sciences
@article{okado_how_2025,
title = {How Can Virtual Agents Scale Up Mentoring?: Insights from College Students’ Experiences Using the CareerFair.ai Platform at an American Hispanic-Serving Institution},
author = {Yuko Okado and Benjamin D. Nye and Angelica Aguirre and William Swartout},
url = {https://link.springer.com/10.1007/s40593-025-00482-w},
doi = {10.1007/s40593-025-00482-w},
issn = {1560-4292, 1560-4306},
year = {2025},
date = {2025-05-01},
urldate = {2025-06-24},
journal = {Int J Artif Intell Educ},
keywords = {DTIC, Learning Sciences},
pubstate = {published},
tppubtype = {article}
}
Core, Mark; Nye, Benjamin; Carr, Kayla; Li, Shirley; Shiel, Aaron; Auerbach, Daniel; Leeds, Andrew; Swartout, William
Usability and Preferences for a Personalized Adaptive Learning System for AI Upskilling Journal Article
In: FLAIRS, vol. 38, 2025, ISSN: 2334-0762, 2334-0754.
Abstract | Links | BibTeX | Tags: AI, DTIC
@article{core_usability_2025,
title = {Usability and Preferences for a Personalized Adaptive Learning System for AI Upskilling},
author = {Mark Core and Benjamin Nye and Kayla Carr and Shirley Li and Aaron Shiel and Daniel Auerbach and Andrew Leeds and William Swartout},
url = {https://journals.flvc.org/FLAIRS/article/view/138996},
doi = {10.32473/flairs.38.1.138996},
issn = {2334-0762, 2334-0754},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-20},
journal = {FLAIRS},
volume = {38},
abstract = {As AI tools become common across jobs and industries, it is critical to broaden education about AI beyond teaching computer scientists how to build AI systems. To expand AI education, we are researching AI for AI learning: a personalized and adaptive learning system that integrates dialog-based tutoring and gamified programming activities. To study this problem, we adapted and expanded an existing smartphone adaptive coach to develop the Game-if-AI system. Using a design-based research approach, Game-if-AI was iteratively tested and improved across four semesters of optional use in a course designed for technician-level understanding of AI: mastering programming skills to apply AI libraries and established models. In this study, we measured the interests and needs of these technical learners, based on both survey data and on how they engaged with topics in the system. Based on this data, new topics were added and the system was refined. In this paper, we report students' usability ratings for system components and student preferences based on completion rates of AI topics available each semester. Students rated the adaptive system positively overall (93% rated as a "good idea"), but more complex learning activities (tutoring dialogs, programming) were rated lower than traditional ones (e.g., multiple choice, reading). Students were most likely to master topics highly aligned to the course materials, as well as self-directed learning toward easier high-interest topics (e.g., LLM Prompting).},
keywords = {AI, DTIC},
pubstate = {published},
tppubtype = {article}
}
Wang, Ning; Fu, Boxi; Dincer, Betul; Masur, Omkar; Faizi, David; Ravindran, Harshul; Wang, Julia; Lai, Devashish; Merchant, Chirag
Becoming Fei: An Educational Game for AI and Data Science Education for Novice Learners Book Section
In: Smith, Brian K.; Borge, Marcela (Ed.): Learning and Collaboration Technologies, vol. 15808, pp. 69–79, Springer Nature Switzerland, Cham, 2025, ISBN: 978-3-031-93745-3 978-3-031-93746-0, (Series Title: Lecture Notes in Computer Science).
@incollection{smith_becoming_2025,
title = {Becoming Fei: An Educational Game for AI and Data Science Education for Novice Learners},
author = {Ning Wang and Boxi Fu and Betul Dincer and Omkar Masur and David Faizi and Harshul Ravindran and Julia Wang and Devashish Lai and Chirag Merchant},
editor = {Brian K. Smith and Marcela Borge},
url = {https://link.springer.com/10.1007/978-3-031-93746-0_6},
doi = {10.1007/978-3-031-93746-0_6},
isbn = {978-3-031-93745-3 978-3-031-93746-0},
year = {2025},
date = {2025-05-01},
urldate = {2025-06-12},
booktitle = {Learning and Collaboration Technologies},
volume = {15808},
pages = {69–79},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {DTIC},
pubstate = {published},
tppubtype = {incollection}
}
Awada, Mohamad; Gerber, Burcin Becerik; Lucas, Gale M.; Roll, Shawn C.
The Impact of Color Correlated Temperature and Illuminance Levels of Office Lighting on Stress and Cognitive Restoration Journal Article
In: Journal of Environmental Psychology, pp. 102628, 2025, ISSN: 02724944.
@article{awada_impact_2025,
title = {The Impact of Color Correlated Temperature and Illuminance Levels of Office Lighting on Stress and Cognitive Restoration},
author = {Mohamad Awada and Burcin Becerik Gerber and Gale M. Lucas and Shawn C. Roll},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0272494425001112},
doi = {10.1016/j.jenvp.2025.102628},
issn = {02724944},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-20},
journal = {Journal of Environmental Psychology},
pages = {102628},
keywords = {DTIC},
pubstate = {published},
tppubtype = {article}
}
Gordon, Andrew
Logical Abduction as a Computational Model of Narrative Proceedings Article
In: Geneva, Switzerland, 2025.
@inproceedings{gordon_andrew_logical_2025,
title = {Logical Abduction as a Computational Model of Narrative},
author = {Andrew Gordon},
url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://asgordon.github.io/publications/CMN2025.PDF},
year = {2025},
date = {2025-05-01},
address = {Geneva, Switzerland},
keywords = {DTIC},
pubstate = {published},
tppubtype = {inproceedings}
}
Chaubey, Ashutosh; Guan, Xulang; Soleymani, Mohammad
Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning Miscellaneous
2025, (Version Number: 1).
Abstract | Links | BibTeX | Tags: DTIC, LLM
@misc{chaubey_face-llava_2025,
title = {Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning},
author = {Ashutosh Chaubey and Xulang Guan and Mohammad Soleymani},
url = {https://arxiv.org/abs/2504.07198},
doi = {10.48550/ARXIV.2504.07198},
year = {2025},
date = {2025-04-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {The human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications. We propose Face-LLaVA, a multimodal large language model for face-centered, in-context learning, including facial expression and attribute recognition. Additionally, Face-LLaVA is able to generate natural language descriptions that can be used for reasoning. Leveraging existing visual databases, we first developed FaceInstruct-1M, a face-centered database for instruction tuning MLLMs for face processing. We then developed a novel face-specific visual encoder powered by Face-Region Guided Cross-Attention that integrates face geometry with local visual features. We evaluated the proposed method across nine different datasets and five different face processing tasks, including facial expression recognition, action unit detection, facial attribute detection, age estimation and deepfake detection. Face-LLaVA achieves superior results compared to existing open-source MLLMs and competitive performance compared to commercial solutions. Our model output also receives a higher reasoning rating by GPT under a zero-shot setting across all the tasks. Both our dataset and model wil be released at https://face-llava.github.io to support future advancements in social AI and foundational vision-language research.},
note = {Version Number: 1},
keywords = {DTIC, LLM},
pubstate = {published},
tppubtype = {misc}
}
Hale, James; Rakshit, Sushrita; Chawla, Kushal; Brett, Jeanne M.; Gratch, Jonathan
KODIS: A Multicultural Dispute Resolution Dialogue Corpus Miscellaneous
2025, (arXiv:2504.12723 [cs]).
Abstract | Links | BibTeX | Tags: Dialogue, DTIC
@misc{hale_kodis_2025,
title = {KODIS: A Multicultural Dispute Resolution Dialogue Corpus},
author = {James Hale and Sushrita Rakshit and Kushal Chawla and Jeanne M. Brett and Jonathan Gratch},
url = {http://arxiv.org/abs/2504.12723},
doi = {10.48550/arXiv.2504.12723},
year = {2025},
date = {2025-04-01},
urldate = {2025-05-20},
publisher = {arXiv},
abstract = {We present KODIS, a dyadic dispute resolution corpus containing thousands of dialogues from over 75 countries. Motivated by a theoretical model of culture and conflict, participants engage in a typical customer service dispute designed by experts to evoke strong emotions and conflict. The corpus contains a rich set of dispositional, process, and outcome measures. The initial analysis supports theories of how anger expressions lead to escalatory spirals and highlights cultural differences in emotional expression. We make this corpus and data collection framework available to the community.},
note = {arXiv:2504.12723 [cs]},
keywords = {Dialogue, DTIC},
pubstate = {published},
tppubtype = {misc}
}
Lin, Spencer; Jun, Miru; Rizk, Basem; Shieh, Karen; Fisher, Scott; Mozgai, Sharon
Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework Proceedings Article
In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–9, 2025, (arXiv:2504.14427 [cs]).
Abstract | Links | BibTeX | Tags: AI, DTIC
@inproceedings{lin_optimizing_2025,
title = {Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework},
author = {Spencer Lin and Miru Jun and Basem Rizk and Karen Shieh and Scott Fisher and Sharon Mozgai},
url = {http://arxiv.org/abs/2504.14427},
doi = {10.1145/3706599.3707399},
year = {2025},
date = {2025-04-01},
urldate = {2025-05-20},
booktitle = {Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
pages = {1–9},
abstract = {This case study presents our user-centered design model for Socially Intelligent Agent (SIA) development frameworks through our experience developing Estuary, an open source multimodal framework for building low-latency real-time socially interactive agents. We leverage the Rapid Assessment Process (RAP) to collect the thoughts of leading researchers in the field of SIAs regarding the current state of the art for SIA development as well as their evaluation of how well Estuary may potentially address current research gaps. We achieve this through a series of end-user interviews conducted by a fellow researcher in the community. We hope that the findings of our work will not only assist the continued development of Estuary but also guide the development of other future frameworks and technologies for SIAs.},
note = {arXiv:2504.14427 [cs]},
keywords = {AI, DTIC},
pubstate = {published},
tppubtype = {inproceedings}
}
Brun, Antonin; Lucas, Gale; Becerik-Gerber, Burçin
Under Pressure: Contextualizing Workplace Stress Towards User-Centered Interventions Proceedings Article
In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–9, ACM, Yokohama Japan, 2025, ISBN: 979-8-4007-1395-8.
@inproceedings{brun_under_2025,
title = {Under Pressure: Contextualizing Workplace Stress Towards User-Centered Interventions},
author = {Antonin Brun and Gale Lucas and Burçin Becerik-Gerber},
url = {https://dl.acm.org/doi/10.1145/3706599.3719987},
doi = {10.1145/3706599.3719987},
isbn = {979-8-4007-1395-8},
year = {2025},
date = {2025-04-01},
urldate = {2025-06-12},
booktitle = {Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
pages = {1–9},
publisher = {ACM},
address = {Yokohama Japan},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Liu, Ziming; Xu, Jiuyi; Suen, Christine Wun Ki; Chen, Meida; Zou, Zhengbo; Shi, Yangming
Egocentric camera-based method for detecting static hazardous objects on construction sites Journal Article
In: Automation in Construction, vol. 172, pp. 106048, 2025, ISSN: 09265805.
@article{liu_egocentric_2025,
title = {Egocentric camera-based method for detecting static hazardous objects on construction sites},
author = {Ziming Liu and Jiuyi Xu and Christine Wun Ki Suen and Meida Chen and Zhengbo Zou and Yangming Shi},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0926580525000883},
doi = {10.1016/j.autcon.2025.106048},
issn = {09265805},
year = {2025},
date = {2025-04-01},
urldate = {2025-03-18},
journal = {Automation in Construction},
volume = {172},
pages = {106048},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Siniukov, Maksim; Chang, Di; Tran, Minh; Gong, Hongkun; Chaubey, Ashutosh; Soleymani, Mohammad
DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion Miscellaneous
2025, (Version Number: 1).
Abstract | Links | BibTeX | Tags: DTIC, VGL
@misc{siniukov_ditailistener_2025,
title = {DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion},
author = {Maksim Siniukov and Di Chang and Minh Tran and Hongkun Gong and Ashutosh Chaubey and Mohammad Soleymani},
url = {https://arxiv.org/abs/2504.04010},
doi = {10.48550/ARXIV.2504.04010},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {Generating naturalistic and nuanced listener motions for extended interactions remains an open problem. Existing methods often rely on low-dimensional motion codes for facial behavior generation followed by photorealistic rendering, limiting both visual fidelity and expressive richness. To address these challenges, we introduce DiTaiListener, powered by a video diffusion model with multimodal conditions. Our approach first generates short segments of listener responses conditioned on the speaker's speech and facial motions with DiTaiListener-Gen. It then refines the transitional frames via DiTaiListener-Edit for a seamless transition. Specifically, DiTaiListener-Gen adapts a Diffusion Transformer (DiT) for the task of listener head portrait generation by introducing a Causal Temporal Multimodal Adapter (CTM-Adapter) to process speakers' auditory and visual cues. CTM-Adapter integrates speakers' input in a causal manner into the video generation process to ensure temporally coherent listener responses. For long-form video generation, we introduce DiTaiListener-Edit, a transition refinement video-to-video diffusion model. The model fuses video segments into smooth and continuous videos, ensuring temporal consistency in facial expressions and image quality when merging short video segments produced by DiTaiListener-Gen. Quantitatively, DiTaiListener achieves the state-of-the-art performance on benchmark datasets in both photorealism (+73.8% in FID on RealTalk) and motion representation (+6.1% in FD metric on VICO) spaces. User studies confirm the superior performance of DiTaiListener, with the model being the clear preference in terms of feedback, diversity, and smoothness, outperforming competitors by a significant margin.},
note = {Version Number: 1},
keywords = {DTIC, VGL},
pubstate = {published},
tppubtype = {misc}
}
Gurney, Nikolos; Pynadath, David V.; Miller, John H.
Willingness to work as a predictor of human-agent team success Journal Article
In: Front. Comput. Sci., vol. 7, pp. 1405436, 2025, ISSN: 2624-9898.
Abstract | Links | BibTeX | Tags: DTIC, Virtual Agents
@article{gurney_willingness_2025,
title = {Willingness to work as a predictor of human-agent team success},
author = {Nikolos Gurney and David V. Pynadath and John H. Miller},
url = {https://www.frontiersin.org/articles/10.3389/fcomp.2025.1405436/full},
doi = {10.3389/fcomp.2025.1405436},
issn = {2624-9898},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
journal = {Front. Comput. Sci.},
volume = {7},
pages = {1405436},
abstract = {Research shows that the effectiveness of human-agent teams depends heavily on human team members' prior experiences, whether from direct teaming activities or relevant domain knowledge. While researchers have proposed various mechanisms to explain this relationship, we present a simpler alternative explanation: experience serves primarily as an indicator of a person's fundamental willingness to engage in teaming tasks. We introduce a measure called “willingness to work” that quantifies this underlying disposition. Our empirical analysis demonstrates that this straightforward metric robustly predicts human-agent team performance. Beyond its practical value as a predictive tool, this reconceptualization of the experience-performance relationship necessitates a fresh examination of existing findings in the field. The results suggest that a team member's basic willingness to invest effort may be more fundamental to success than previously recognized mechanisms.},
keywords = {DTIC, Virtual Agents},
pubstate = {published},
tppubtype = {article}
}
Ustun, Volkan; Hans, Soham; Kumar, Rajay; Wang, Yunzhe
Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning Miscellaneous
2025, (arXiv:2503.20078 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, Simulation
@misc{ustun_abstracting_2025,
title = {Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning},
author = {Volkan Ustun and Soham Hans and Rajay Kumar and Yunzhe Wang},
url = {http://arxiv.org/abs/2503.20078},
doi = {10.48550/arXiv.2503.20078},
year = {2025},
date = {2025-03-01},
urldate = {2025-04-15},
publisher = {arXiv},
abstract = {Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Frameworks such as Unity's ML-Agents help to make such reinforcement learning experiments more accessible to the simulation community. Military training simulations also benefit from advances in MARL, but they have immense computational requirements due to their complex, continuous, stochastic, partially observable, non-stationary, and doctrine-based nature. Furthermore, these simulations require geo-specific terrains, further exacerbating the computational resources problem. In our research, we leverage Unity's waypoints to automatically generate multi-layered representation abstractions of the geo-specific terrains to scale up reinforcement learning while still allowing the transfer of learned policies between different representations. Our early exploratory results on a novel MARL scenario, where each side has differing objectives, indicate that waypoint-based navigation enables faster and more efficient learning while producing trajectories similar to those taken by expert human players in CSGO gaming environments. This research points out the potential of waypoint-based navigation for reducing the computational costs of developing and training MARL models for military training simulations, where geo-specific terrains and differing objectives are crucial.},
note = {arXiv:2503.20078 [cs]},
keywords = {DTIC, Simulation},
pubstate = {published},
tppubtype = {misc}
}
Liu, Ruying; Becerik-Gerber, Burcin; Pynadath, David V.; Marti, Deniz; Lucas, Gale M.
Elicitation and verification of learning via experts (EVOLVE) for creating a theoretical framework for active shooter incidents Journal Article
In: Developments in the Built Environment, vol. 21, pp. 100635, 2025, ISSN: 26661659.
Links | BibTeX | Tags: DTIC, Social Simulation
@article{liu_elicitation_2025,
title = {Elicitation and verification of learning via experts (EVOLVE) for creating a theoretical framework for active shooter incidents},
author = {Ruying Liu and Burcin Becerik-Gerber and David V. Pynadath and Deniz Marti and Gale M. Lucas},
url = {https://linkinghub.elsevier.com/retrieve/pii/S2666165925000353},
doi = {10.1016/j.dibe.2025.100635},
issn = {26661659},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-18},
journal = {Developments in the Built Environment},
volume = {21},
pages = {100635},
keywords = {DTIC, Social Simulation},
pubstate = {published},
tppubtype = {article}
}
Jalal-Kamali, Ali; Gurney, Nikolos; Pynadath, David
Predicting Team Performance from Communications in Simulated Search-and-Rescue Miscellaneous
2025, (arXiv:2503.03791 [cs]).
Abstract | Links | BibTeX | Tags: AI, DTIC
@misc{jalal-kamali_predicting_2025,
title = {Predicting Team Performance from Communications in Simulated Search-and-Rescue},
author = {Ali Jalal-Kamali and Nikolos Gurney and David Pynadath},
url = {http://arxiv.org/abs/2503.03791},
doi = {10.48550/arXiv.2503.03791},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-18},
publisher = {arXiv},
abstract = {Understanding how individual traits influence team performance is valuable, but these traits are not always directly observable. Prior research has inferred traits like trust from behavioral data. We analyze conversational data to identify team traits and their correlation with teaming outcomes. Using transcripts from a Minecraft-based search-and-rescue experiment, we apply topic modeling and clustering to uncover key interaction patterns. Our findings show that variations in teaming outcomes can be explained through these inferences, with different levels of predictive power derived from individual traits and team dynamics.},
note = {arXiv:2503.03791 [cs]},
keywords = {AI, DTIC},
pubstate = {published},
tppubtype = {misc}
}
Kwon, Deuksin; Hae, Jiwon; Clift, Emma; Shamsoddini, Daniel; Gratch, Jonathan; Lucas, Gale M.
ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning through Action in Dynamic Offer Optimization Miscellaneous
2025, (arXiv:2503.07129 [cs]).
Abstract | Links | BibTeX | Tags: Virtual Agents
@misc{kwon_astra_2025,
title = {ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning through Action in Dynamic Offer Optimization},
author = {Deuksin Kwon and Jiwon Hae and Emma Clift and Daniel Shamsoddini and Jonathan Gratch and Gale M. Lucas},
url = {http://arxiv.org/abs/2503.07129},
doi = {10.48550/arXiv.2503.07129},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-18},
publisher = {arXiv},
abstract = {Negotiation requires dynamically balancing self-interest and cooperation to maximize one's own utility. Yet, existing agents struggle due to bounded rationality in human data, low adaptability to counterpart behavior, and limited strategic reasoning. To address this, we introduce principle-driven negotiation agents, powered by ASTRA, a novel framework for turn-level offer optimization grounded in two core principles: opponent modeling and Tit-for-Tat reciprocity. ASTRA operates in three stages: (1) interpreting counterpart behavior, (2) optimizing counteroffers via a linear programming (LP) solver, and (3) selecting offers based on negotiation tactics and the partner's acceptance probability. Through simulations and human evaluations, our agent effectively adapts to an opponent's shifting stance and achieves favorable outcomes through enhanced adaptability and strategic reasoning. Beyond improving negotiation performance, it also serves as a powerful coaching tool, offering interpretable strategic feedback and optimal offer recommendations.},
note = {arXiv:2503.07129 [cs]},
keywords = {Virtual Agents},
pubstate = {published},
tppubtype = {misc}
}
Fonseca, Henrique Correia Da; Melo, Celso M. De; Terada, Kazunori; Gratch, Jonathan; Paiva, Ana S.; Santos, Francisco C.
Evolution of indirect reciprocity under emotion expression Journal Article
In: Sci Rep, vol. 15, no. 1, pp. 9151, 2025, ISSN: 2045-2322.
Abstract | Links | BibTeX | Tags: DTIC
@article{correia_da_fonseca_evolution_2025,
title = {Evolution of indirect reciprocity under emotion expression},
author = {Henrique Correia Da Fonseca and Celso M. De Melo and Kazunori Terada and Jonathan Gratch and Ana S. Paiva and Francisco C. Santos},
url = {https://www.nature.com/articles/s41598-025-89588-8},
doi = {10.1038/s41598-025-89588-8},
issn = {2045-2322},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-20},
journal = {Sci Rep},
volume = {15},
number = {1},
pages = {9151},
abstract = {Abstract
Do emotion expressions impact the evolution of cooperation? Indirect Reciprocity offers a solution to the cooperation dilemma with prior work focusing on the role of social norms in propagating others’ reputations and contributing to evolutionarily stable cooperation. Recent experimental studies, however, show that emotion expressions shape pro-social behaviour, communicate one’s intentions to others, and serve an error-correcting function; yet, the role of emotion signals in the evolution of cooperation remains unexplored. We present the first model of IR based on evolutionary game theory that exposes how emotion expressions positively influence the evolution of cooperation, particularly in scenarios of frequent errors. Our findings provide evolutionary support for the existence of emotion-based social norms, which help foster cooperation among unrelated individuals.},
keywords = {DTIC},
pubstate = {published},
tppubtype = {article}
}
Do emotion expressions impact the evolution of cooperation? Indirect Reciprocity offers a solution to the cooperation dilemma with prior work focusing on the role of social norms in propagating others’ reputations and contributing to evolutionarily stable cooperation. Recent experimental studies, however, show that emotion expressions shape pro-social behaviour, communicate one’s intentions to others, and serve an error-correcting function; yet, the role of emotion signals in the evolution of cooperation remains unexplored. We present the first model of IR based on evolutionary game theory that exposes how emotion expressions positively influence the evolution of cooperation, particularly in scenarios of frequent errors. Our findings provide evolutionary support for the existence of emotion-based social norms, which help foster cooperation among unrelated individuals.
Jin, Zhangyu; Feng, Andrew; Chemburkar, Ankur; Melo, Celso M. De
PromptGAR: Flexible Promptive Group Activity Recognition Miscellaneous
2025, (arXiv:2503.08933 [cs]).
Abstract | Links | BibTeX | Tags:
@misc{jin_promptgar_2025,
title = {PromptGAR: Flexible Promptive Group Activity Recognition},
author = {Zhangyu Jin and Andrew Feng and Ankur Chemburkar and Celso M. De Melo},
url = {http://arxiv.org/abs/2503.08933},
doi = {10.48550/arXiv.2503.08933},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-20},
publisher = {arXiv},
abstract = {We present PromptGAR, a novel framework that addresses the limitations of current Group Activity Recognition (GAR) approaches by leveraging multi-modal prompts to achieve both input flexibility and high recognition accuracy. The existing approaches suffer from limited real-world applicability due to their reliance on full prompt annotations, the lack of long-term actor consistency, and under-exploration of multi-group scenarios. To bridge the gap, we proposed PromptGAR, which is the first GAR model to provide input flexibility across prompts, frames, and instances without the need for retraining. Specifically, we unify bounding boxes, skeletal keypoints, and areas as point prompts and employ a recognition decoder for cross-updating class and prompt tokens. To ensure long-term consistency for extended activity durations, we also introduce a relative instance attention mechanism that directly encodes instance IDs. Finally, PromptGAR explores the use of area prompts to enable the selective recognition of the particular group activity within videos that contain multiple concurrent groups. Comprehensive evaluations demonstrate that PromptGAR achieves competitive performances both on full prompts and diverse prompt inputs, establishing its effectiveness on input flexibility and generalization ability for real-world applications.},
note = {arXiv:2503.08933 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Liu, Ruying; Becerik-Gerber, Burçin; Lucas, Gale M.
Investigating Role of Personal Factors in Shaping Responses to Active Shooter Incident using Machine Learning Miscellaneous
2025, (arXiv:2503.05719 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, Social Simulation, VR
@misc{liu_investigating_2025,
title = {Investigating Role of Personal Factors in Shaping Responses to Active Shooter Incident using Machine Learning},
author = {Ruying Liu and Burçin Becerik-Gerber and Gale M. Lucas},
url = {http://arxiv.org/abs/2503.05719},
doi = {10.48550/arXiv.2503.05719},
year = {2025},
date = {2025-02-01},
urldate = {2025-03-18},
publisher = {arXiv},
abstract = {This study bridges the knowledge gap on how personal factors affect building occupants' responses in active shooter situations by applying interpretable machine learning methods to data from 107 participants. The personal factors studied are training methods, prior training experience, sense of direction, and gender. The response performance measurements consist of decisions (run, hide, multiple), vulnerability (corresponding to the time a participant is visible to a shooter), and pre-evacuation time. The results indicate that the propensity to run significantly determines overall response strategies, overshadowing vulnerability, and pre-evacuation time. The training method is a critical factor where VR-based training leads to better responses than video-based training. A better sense of direction and previous training experience are correlated with a greater propensity to run and less vulnerability. Gender slightly influences decisions and vulnerability but significantly impacts pre-evacuation time, with females evacuating slower, potentially due to higher risk perception. This study underscores the importance of personal factors in shaping responses to active shooter incidents.},
note = {arXiv:2503.05719 [cs]},
keywords = {DTIC, Social Simulation, VR},
pubstate = {published},
tppubtype = {misc}
}
Huang, Huajian; Chen, Yingshu; Li, Longwei; Cheng, Hui; Braud, Tristan; Zhao, Yajie; Yeung, Sai-Kit
SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting Miscellaneous
2025, (arXiv:2502.04734 [cs]).
Abstract | Links | BibTeX | Tags: VGL
@misc{huang_sc-omnigs_2025,
title = {SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting},
author = {Huajian Huang and Yingshu Chen and Longwei Li and Hui Cheng and Tristan Braud and Yajie Zhao and Sai-Kit Yeung},
url = {http://arxiv.org/abs/2502.04734},
doi = {10.48550/arXiv.2502.04734},
year = {2025},
date = {2025-02-01},
urldate = {2025-03-18},
publisher = {arXiv},
abstract = {360-degree cameras streamline data collection for radiance field 3D reconstruction by capturing comprehensive scene data. However, traditional radiance field methods do not address the specific challenges inherent to 360-degree images. We present SC-OmniGS, a novel self-calibrating omnidirectional Gaussian splatting system for fast and accurate omnidirectional radiance field reconstruction using 360-degree images. Rather than converting 360-degree images to cube maps and performing perspective image calibration, we treat 360-degree images as a whole sphere and derive a mathematical framework that enables direct omnidirectional camera pose calibration accompanied by 3D Gaussians optimization. Furthermore, we introduce a differentiable omnidirectional camera model in order to rectify the distortion of real-world data for performance enhancement. Overall, the omnidirectional camera intrinsic model, extrinsic poses, and 3D Gaussians are jointly optimized by minimizing weighted spherical photometric loss. Extensive experiments have demonstrated that our proposed SC-OmniGS is able to recover a high-quality radiance field from noisy camera poses or even no pose prior in challenging scenarios characterized by wide baselines and non-object-centric configurations. The noticeable performance gain in the real-world dataset captured by consumer-grade omnidirectional cameras verifies the effectiveness of our general omnidirectional camera model in reducing the distortion of 360-degree images.},
note = {arXiv:2502.04734 [cs]},
keywords = {VGL},
pubstate = {published},
tppubtype = {misc}
}
Roth, Holger R.; Xu, Ziyue; Chen, Chester; Xu, Daguang; Dogra, Prerna; Flores, Mona; Cheng, Yan; Feng, Andrew
Overview of real-world applications of federated learning with NVIDIA FLARE Journal Article
In: Journal of Biopharmaceutical Statistics, pp. 1–11, 2025, ISSN: 1054-3406, 1520-5711.
@article{roth_overview_2025,
title = {Overview of real-world applications of federated learning with NVIDIA FLARE},
author = {Holger R. Roth and Ziyue Xu and Chester Chen and Daguang Xu and Prerna Dogra and Mona Flores and Yan Cheng and Andrew Feng},
url = {https://www.tandfonline.com/doi/full/10.1080/10543406.2025.2456174},
doi = {10.1080/10543406.2025.2456174},
issn = {1054-3406, 1520-5711},
year = {2025},
date = {2025-02-01},
urldate = {2025-03-20},
journal = {Journal of Biopharmaceutical Statistics},
pages = {1–11},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Tak, Ala N.; Banayeeanzade, Amin; Bolourani, Anahita; Kian, Mina; Jia, Robin; Gratch, Jonathan
Mechanistic Interpretability of Emotion Inference in Large Language Models Miscellaneous
2025, (arXiv:2502.05489 [cs]).
Abstract | Links | BibTeX | Tags: LLM
@misc{tak_mechanistic_2025,
title = {Mechanistic Interpretability of Emotion Inference in Large Language Models},
author = {Ala N. Tak and Amin Banayeeanzade and Anahita Bolourani and Mina Kian and Robin Jia and Jonathan Gratch},
url = {http://arxiv.org/abs/2502.05489},
doi = {10.48550/arXiv.2502.05489},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-20},
publisher = {arXiv},
abstract = {Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model. Our evaluation includes diverse model families and sizes and is supported by robustness checks. We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory, a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli. By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations. This work highlights a novel way to causally intervene and precisely shape emotional text generation, potentially benefiting safety and alignment in sensitive affective domains.},
note = {arXiv:2502.05489 [cs]},
keywords = {LLM},
pubstate = {published},
tppubtype = {misc}
}
Liu, Ruying; Becerik-Gerber, Burcin; Lucas, Gale M.; Busta, Kelly
Impact of behavior-based virtual training on active shooter incident preparedness in healthcare facilities Journal Article
In: International Journal of Disaster Risk Reduction, vol. 118, pp. 105225, 2025, ISSN: 22124209.
Links | BibTeX | Tags: DTIC, Virtual Humans
@article{liu_impact_2025,
title = {Impact of behavior-based virtual training on active shooter incident preparedness in healthcare facilities},
author = {Ruying Liu and Burcin Becerik-Gerber and Gale M. Lucas and Kelly Busta},
url = {https://linkinghub.elsevier.com/retrieve/pii/S2212420925000494},
doi = {10.1016/j.ijdrr.2025.105225},
issn = {22124209},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-20},
journal = {International Journal of Disaster Risk Reduction},
volume = {118},
pages = {105225},
keywords = {DTIC, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Brun, Antonin; Liu, Ruying; Shukla, Aryan; Watson, Frances; Gratch, Jonathan
Exploring Emotion-Sensitive LLM-Based Conversational AI Miscellaneous
2025, (arXiv:2502.08920 [cs]).
Abstract | Links | BibTeX | Tags: AI, LLM
@misc{brun_exploring_2025,
title = {Exploring Emotion-Sensitive LLM-Based Conversational AI},
author = {Antonin Brun and Ruying Liu and Aryan Shukla and Frances Watson and Jonathan Gratch},
url = {http://arxiv.org/abs/2502.08920},
doi = {10.48550/arXiv.2502.08920},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-20},
publisher = {arXiv},
abstract = {Conversational AI chatbots have become increasingly common within the customer service industry. Despite improvements in their emotional development, they often lack the authenticity of real customer service interactions or the competence of service providers. By comparing emotion-sensitive and emotion-insensitive LLM-based chatbots across 30 participants, we aim to explore how emotional sensitivity in chatbots influences perceived competence and overall customer satisfaction in service interactions. Additionally, we employ sentiment analysis techniques to analyze and interpret the emotional content of user inputs. We highlight that perceptions of chatbot trustworthiness and competence were higher in the case of the emotion-sensitive chatbot, even if issue resolution rates were not affected. We discuss implications of improved user satisfaction from emotion-sensitive chatbots and potential applications in support services.},
note = {arXiv:2502.08920 [cs]},
keywords = {AI, LLM},
pubstate = {published},
tppubtype = {misc}
}
Cai, Yunxuan; Xiang, Sitao; Li, Zongjian; Chen, Haiwei; Zhao, Yajie
Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation Miscellaneous
2025, (Version Number: 1).
Abstract | Links | BibTeX | Tags: Artificial Intelligence (cs.AI), Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences
@misc{cai_bringing_2025,
title = {Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation},
author = {Yunxuan Cai and Sitao Xiang and Zongjian Li and Haiwei Chen and Yajie Zhao},
url = {https://arxiv.org/abs/2504.15259},
doi = {10.48550/ARXIV.2504.15259},
year = {2025},
date = {2025-01-01},
urldate = {2025-06-25},
publisher = {arXiv},
abstract = {Digital modeling and reconstruction of human faces serve various applications. However, its availability is often hindered by the requirements of data capturing devices, manual labor, and suitable actors. This situation restricts the diversity, expressiveness, and control over the resulting models. This work aims to demonstrate that a semantically controllable generative network can provide enhanced control over the digital face modeling process. To enhance diversity beyond the limited human faces scanned in a controlled setting, we introduce a novel data generation pipeline that creates a high-quality 3D face database using a pre-trained diffusion model. Our proposed normalization module converts synthesized data from the diffusion model into high-quality scanned data. Using the 44,000 face models we obtained, we further developed an efficient GAN-based generator. This generator accepts semantic attributes as input, and generates geometry and albedo. It also allows continuous post-editing of attributes in the latent space. Our asset refinement component subsequently creates physically-based facial assets. We introduce a comprehensive system designed for creating and editing high-quality face assets. Our proposed model has undergone extensive experiment, comparison and evaluation. We also integrate everything into a web-based interactive tool. We aim to make this tool publicly available with the release of the paper.},
note = {Version Number: 1},
keywords = {Artificial Intelligence (cs.AI), Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences},
pubstate = {published},
tppubtype = {misc}
}
Kang, Seoyoung; Yoon, Boram; Kim, Kangsoo; Gratch, Jonathan; Woo, Woontack
How Collaboration Context and Personality Traits Shape the Social Norms of Human-to-Avatar Identity Representation Journal Article
In: IEEE Trans. Visual. Comput. Graphics, pp. 1–10, 2025, ISSN: 1077-2626, 1941-0506, 2160-9306.
@article{kang_how_2025,
title = {How Collaboration Context and Personality Traits Shape the Social Norms of Human-to-Avatar Identity Representation},
author = {Seoyoung Kang and Boram Yoon and Kangsoo Kim and Jonathan Gratch and Woontack Woo},
url = {https://ieeexplore.ieee.org/document/10935702/},
doi = {10.1109/TVCG.2025.3549904},
issn = {1077-2626, 1941-0506, 2160-9306},
year = {2025},
date = {2025-01-01},
urldate = {2025-04-17},
journal = {IEEE Trans. Visual. Comput. Graphics},
pages = {1–10},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Tran, Minh; Yin, Yufeng; Soleymani, Mohammad
SetPeER: Set-Based Personalized Emotion Recognition With Weak Supervision Journal Article
In: IEEE Trans. Affective Comput., pp. 1–15, 2025, ISSN: 1949-3045, 2371-9850.
Links | BibTeX | Tags: DTIC, Emotion
@article{tran_setpeer_2025,
title = {SetPeER: Set-Based Personalized Emotion Recognition With Weak Supervision},
author = {Minh Tran and Yufeng Yin and Mohammad Soleymani},
url = {https://ieeexplore.ieee.org/document/10993348/},
doi = {10.1109/TAFFC.2025.3568024},
issn = {1949-3045, 2371-9850},
year = {2025},
date = {2025-01-01},
urldate = {2025-05-20},
journal = {IEEE Trans. Affective Comput.},
pages = {1–15},
keywords = {DTIC, Emotion},
pubstate = {published},
tppubtype = {article}
}
Wang, Ning; Hurt, Timothy; Krakowski, Ari; Greenwald, Eric; Hammerman, Jim; Santos, Sabrina De Los; Masur, Omkar; Fu, Boxi; Merchant, Chirag
Virtually Human: An Exhibit for Public AI Education Book Section
In: Stephanidis, Constantine; Antona, Margherita; Ntoa, Stavroula; Salvendy, Gavriel (Ed.): HCI International 2025 Posters, vol. 2529, pp. 436–443, Springer Nature Switzerland, Cham, 2025, ISBN: 978-3-031-94170-2 978-3-031-94171-9, (Series Title: Communications in Computer and Information Science).
@incollection{stephanidis_virtually_2025,
title = {Virtually Human: An Exhibit for Public AI Education},
author = {Ning Wang and Timothy Hurt and Ari Krakowski and Eric Greenwald and Jim Hammerman and Sabrina De Los Santos and Omkar Masur and Boxi Fu and Chirag Merchant},
editor = {Constantine Stephanidis and Margherita Antona and Stavroula Ntoa and Gavriel Salvendy},
url = {https://link.springer.com/10.1007/978-3-031-94171-9_42},
doi = {10.1007/978-3-031-94171-9_42},
isbn = {978-3-031-94170-2 978-3-031-94171-9},
year = {2025},
date = {2025-01-01},
urldate = {2025-06-17},
booktitle = {HCI International 2025 Posters},
volume = {2529},
pages = {436–443},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Communications in Computer and Information Science},
keywords = {DTIC},
pubstate = {published},
tppubtype = {incollection}
}
Hu, Yue; Liu, Rong; Chen, Meida; Beerel, Peter; Feng, Andrew
SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting Miscellaneous
2025, (arXiv:2501.07015 [cs]).
Abstract | Links | BibTeX | Tags: VGL
@misc{hu_splatmap_2025,
title = {SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting},
author = {Yue Hu and Rong Liu and Meida Chen and Peter Beerel and Andrew Feng},
url = {http://arxiv.org/abs/2501.07015},
doi = {10.48550/arXiv.2501.07015},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-16},
publisher = {arXiv},
abstract = {Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While differentiable rendering techniques such as Neural Radiance Fields (NeRF) address some of these challenges, their high computational costs make them unsuitable for real-time applications. Additionally, existing 3D Gaussian Splatting (3DGS) methods often focus on photometric consistency, neglecting geometric accuracy and failing to exploit SLAM's dynamic depth and pose updates for scene refinement. We propose a framework integrating dense SLAM with 3DGS for real-time, high-fidelity dense reconstruction. Our approach introduces SLAM-Informed Adaptive Densification, which dynamically updates and densifies the Gaussian model by leveraging dense point clouds from SLAM. Additionally, we incorporate Geometry-Guided Optimization, which combines edge-aware geometric constraints and photometric consistency to jointly optimize the appearance and geometry of the 3DGS scene representation, enabling detailed and accurate SLAM mapping reconstruction. Experiments on the Replica and TUM-RGBD datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results among monocular systems. Specifically, our method achieves a PSNR of 36.864, SSIM of 0.985, and LPIPS of 0.040 on Replica, representing improvements of 10.7%, 6.4%, and 49.4%, respectively, over the previous SOTA. On TUM-RGBD, our method outperforms the closest baseline by 10.2%, 6.6%, and 34.7% in the same metrics. These results highlight the potential of our framework in bridging the gap between photometric and geometric dense 3D scene representations, paving the way for practical and efficient monocular dense reconstruction.},
note = {arXiv:2501.07015 [cs]},
keywords = {VGL},
pubstate = {published},
tppubtype = {misc}
}
Rizzo, Albert “Skip”; Giosan, Cezar; Deac, George; Zaporozhets, Olya; Syvak, Oksana; Dragayeva, Svetlana; Bodner, Ehud; Mann, Shel; Stone, Jessica
The Virtual Ukraine Project: Trauma Therapy in Warzones with Virtual Reality Book Section
In: Stone, Jessica (Ed.): Mental Health Virtual Reality, pp. 159–180, Wiley, 2025, ISBN: 978-1-394-27845-9 978-1-394-27848-0.
@incollection{stone_virtual_2025,
title = {The Virtual Ukraine Project: Trauma Therapy in Warzones with Virtual Reality},
author = {Albert “Skip” Rizzo and Cezar Giosan and George Deac and Olya Zaporozhets and Oksana Syvak and Svetlana Dragayeva and Ehud Bodner and Shel Mann and Jessica Stone},
editor = {Jessica Stone},
url = {https://onlinelibrary.wiley.com/doi/10.1002/9781394278480.ch12},
doi = {10.1002/9781394278480.ch12},
isbn = {978-1-394-27845-9 978-1-394-27848-0},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-16},
booktitle = {Mental Health Virtual Reality},
pages = {159–180},
publisher = {Wiley},
edition = {1},
keywords = {MedVR},
pubstate = {published},
tppubtype = {incollection}
}
Liu, Rong; Sun, Dylan; Chen, Meida; Wang, Yue; Feng, Andrew
Deformable Beta Splatting Miscellaneous
2025, (arXiv:2501.18630 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, Narrative
@misc{liu_deformable_2025,
title = {Deformable Beta Splatting},
author = {Rong Liu and Dylan Sun and Meida Chen and Yue Wang and Andrew Feng},
url = {http://arxiv.org/abs/2501.18630},
doi = {10.48550/arXiv.2501.18630},
year = {2025},
date = {2025-01-01},
urldate = {2025-02-20},
publisher = {arXiv},
abstract = {3D Gaussian Splatting (3DGS) has advanced radiance field reconstruction by enabling real-time rendering. However, its reliance on Gaussian kernels for geometry and low-order Spherical Harmonics (SH) for color encoding limits its ability to capture complex geometries and diverse colors. We introduce Deformable Beta Splatting (DBS), a deformable and compact approach that enhances both geometry and color representation. DBS replaces Gaussian kernels with deformable Beta Kernels, which offer bounded support and adaptive frequency control to capture fine geometric details with higher fidelity while achieving better memory efficiency. In addition, we extended the Beta Kernel to color encoding, which facilitates improved representation of diffuse and specular components, yielding superior results compared to SH-based methods. Furthermore, Unlike prior densification techniques that depend on Gaussian properties, we mathematically prove that adjusting regularized opacity alone ensures distribution-preserved Markov chain Monte Carlo (MCMC), independent of the splatting kernel type. Experimental results demonstrate that DBS achieves state-of-the-art visual quality while utilizing only 45% of the parameters and rendering 1.5x faster than 3DGS-based methods. Notably, for the first time, splatting-based methods outperform state-of-the-art Neural Radiance Fields, highlighting the superior performance and efficiency of DBS for real-time radiance field rendering.},
note = {arXiv:2501.18630 [cs]},
keywords = {DTIC, Narrative},
pubstate = {published},
tppubtype = {misc}
}
Chang, Di; Xu, Hongyi; Xie, You; Gao, Yipeng; Kuang, Zhengfei; Cai, Shengqu; Zhang, Chenxu; Song, Guoxian; Wang, Chao; Shi, Yichun; Chen, Zeyuan; Zhou, Shijie; Luo, Linjie; Wetzstein, Gordon; Soleymani, Mohammad
X-Dyna: Expressive Dynamic Human Image Animation Miscellaneous
2025, (arXiv:2501.10021 [cs]).
Abstract | Links | BibTeX | Tags: VGL
@misc{chang_x-dyna_2025,
title = {X-Dyna: Expressive Dynamic Human Image Animation},
author = {Di Chang and Hongyi Xu and You Xie and Yipeng Gao and Zhengfei Kuang and Shengqu Cai and Chenxu Zhang and Guoxian Song and Chao Wang and Yichun Shi and Zeyuan Chen and Shijie Zhou and Linjie Luo and Gordon Wetzstein and Mohammad Soleymani},
url = {http://arxiv.org/abs/2501.10021},
doi = {10.48550/arXiv.2501.10021},
year = {2025},
date = {2025-01-01},
urldate = {2025-02-20},
publisher = {arXiv},
abstract = {We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment. Building on prior approaches centered on human pose control, X-Dyna addresses key shortcomings causing the loss of dynamic details, enhancing the lifelike qualities of human video animations. At the core of our approach is the Dynamics-Adapter, a lightweight module that effectively integrates reference appearance context into the spatial attentions of the diffusion backbone while preserving the capacity of motion modules in synthesizing fluid and intricate dynamic details. Beyond body pose control, we connect a local control module with our model to capture identity-disentangled facial expressions, facilitating accurate expression transfer for enhanced realism in animated scenes. Together, these components form a unified framework capable of learning physical human motion and natural scene dynamics from a diverse blend of human and scene videos. Comprehensive qualitative and quantitative evaluations demonstrate that X-Dyna outperforms state-of-the-art methods, creating highly lifelike and expressive animations. The code is available at https://github.com/bytedance/X-Dyna.},
note = {arXiv:2501.10021 [cs]},
keywords = {VGL},
pubstate = {published},
tppubtype = {misc}
}
Rodrigues, Patrick Borges; Becerik-Gerber, Burcin; Soibelman, Lucio; Lucas, Gale M.; Roll, Shawn C.
Impact of selective environmental sound attenuation on operator performance, stress, attention, and task engagement in teleoperated demolition Journal Article
In: Automation in Construction, vol. 169, pp. 105876, 2025, ISSN: 09265805.
@article{rodrigues_impact_2025,
title = {Impact of selective environmental sound attenuation on operator performance, stress, attention, and task engagement in teleoperated demolition},
author = {Patrick Borges Rodrigues and Burcin Becerik-Gerber and Lucio Soibelman and Gale M. Lucas and Shawn C. Roll},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0926580524006125},
doi = {10.1016/j.autcon.2024.105876},
issn = {09265805},
year = {2025},
date = {2025-01-01},
urldate = {2024-12-20},
journal = {Automation in Construction},
volume = {169},
pages = {105876},
keywords = {DTIC},
pubstate = {published},
tppubtype = {article}
}
Siniukov, Maksim; Xing, Ellie; Sanaz,; Isfahani, Attaripour; Soleymani, Mohammad
Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis Miscellaneous
2025, (Version Number: 1).
Abstract | Links | BibTeX | Tags: DTIC
@misc{siniukov_towards_2025,
title = {Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis},
author = {Maksim Siniukov and Ellie Xing and Sanaz and Attaripour Isfahani and Mohammad Soleymani},
url = {https://arxiv.org/abs/2501.03581},
doi = {10.48550/ARXIV.2501.03581},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-14},
publisher = {arXiv},
abstract = {Parkinson's Disease (PD) is a neurodegenerative disorder characterized by motor symptoms, including altered voice production in the early stages. Early diagnosis is crucial not only to improve PD patients' quality of life but also to enhance the efficacy of potential disease-modifying therapies during early neurodegeneration, a window often missed by current diagnostic tools. In this paper, we propose a more generalizable approach to PD recognition through domain adaptation and self-supervised learning. We demonstrate the generalization capabilities of the proposed approach across diverse datasets in different languages. Our approach leverages HuBERT, a large deep neural network originally trained for speech recognition and further trains it on unlabeled speech data from a population that is similar to the target group, i.e., the elderly, in a self-supervised manner. The model is then fine-tuned and adapted for use across different datasets in multiple languages, including English, Italian, and Spanish. Evaluations on four publicly available PD datasets demonstrate the model's efficacy, achieving an average specificity of 92.1% and an average sensitivity of 91.2%. This method offers objective and consistent evaluations across large populations, addressing the variability inherent in human assessments and providing a non-invasive, cost-effective and accessible diagnostic option.},
note = {Version Number: 1},
keywords = {DTIC},
pubstate = {published},
tppubtype = {misc}
}
2024
Addison, Parker; Nguyen, Minh-Tuan H.; Medan, Tomislav; Shah, Jinali; Manzari, Mohammad T.; McElrone, Brendan; Lalwani, Laksh; More, Aboli; Sharma, Smita; Roth, Holger R.; Yang, Isaac; Chen, Chester; Xu, Daguang; Cheng, Yan; Feng, Andrew; Xu, Ziyue
C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System Miscellaneous
2024, (arXiv:2412.13163 [cs]).
Abstract | Links | BibTeX | Tags: LLM
@misc{addison_c-fedrag_2024,
title = {C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System},
author = {Parker Addison and Minh-Tuan H. Nguyen and Tomislav Medan and Jinali Shah and Mohammad T. Manzari and Brendan McElrone and Laksh Lalwani and Aboli More and Smita Sharma and Holger R. Roth and Isaac Yang and Chester Chen and Daguang Xu and Yan Cheng and Andrew Feng and Ziyue Xu},
url = {http://arxiv.org/abs/2412.13163},
doi = {10.48550/arXiv.2412.13163},
year = {2024},
date = {2024-12-01},
urldate = {2025-03-20},
publisher = {arXiv},
abstract = {Organizations seeking to utilize Large Language Models (LLMs) for knowledge querying and analysis often encounter challenges in maintaining an LLM fine-tuned on targeted, up-to-date information that keeps answers relevant and grounded. Retrieval Augmented Generation (RAG) has quickly become a feasible solution for organizations looking to overcome the challenges of maintaining proprietary models and to help reduce LLM hallucinations in their query responses. However, RAG comes with its own issues regarding scaling data pipelines across tiered-access and disparate data sources. In many scenarios, it is necessary to query beyond a single data silo to provide richer and more relevant context for an LLM. Analyzing data sources within and across organizational trust boundaries is often limited by complex data-sharing policies that prohibit centralized data storage, therefore, inhibit the fast and effective setup and scaling of RAG solutions. In this paper, we introduce Confidential Computing (CC) techniques as a solution for secure Federated Retrieval Augmented Generation (FedRAG). Our proposed Confidential FedRAG system (C-FedRAG) enables secure connection and scaling of a RAG workflows across a decentralized network of data providers by ensuring context confidentiality. We also demonstrate how to implement a C-FedRAG system using the NVIDIA FLARE SDK and assess its performance using the MedRAG toolkit and MIRAGE benchmarking dataset.},
note = {arXiv:2412.13163 [cs]},
keywords = {LLM},
pubstate = {published},
tppubtype = {misc}
}
Murray, Benjamin; Brown, Richard; Ma, Pengcheng; Kerfoot, Eric; Xu, Daguang; Feng, Andrew; Cardoso, Jorge; Ourselin, Sebastien; Modat, Marc
Lazy Resampling: Fast and information preserving preprocessing for deep learning Journal Article
In: Computer Methods and Programs in Biomedicine, vol. 257, pp. 108422, 2024, ISSN: 01692607.
Links | BibTeX | Tags: Narrative
@article{murray_lazy_2024,
title = {Lazy Resampling: Fast and information preserving preprocessing for deep learning},
author = {Benjamin Murray and Richard Brown and Pengcheng Ma and Eric Kerfoot and Daguang Xu and Andrew Feng and Jorge Cardoso and Sebastien Ourselin and Marc Modat},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260724004152},
doi = {10.1016/j.cmpb.2024.108422},
issn = {01692607},
year = {2024},
date = {2024-12-01},
urldate = {2025-01-16},
journal = {Computer Methods and Programs in Biomedicine},
volume = {257},
pages = {108422},
keywords = {Narrative},
pubstate = {published},
tppubtype = {article}
}
Tran, Minh; Chang, Di; Siniukov, Maksim; Soleymani, Mohammad
DIM: Dyadic Interaction Modeling for Social Behavior Generation Book Section
In: Leonardis, Aleš; Ricci, Elisa; Roth, Stefan; Russakovsky, Olga; Sattler, Torsten; Varol, Gül (Ed.): Computer Vision – ECCV 2024, vol. 15095, pp. 484–503, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-72912-6 978-3-031-72913-3, (Series Title: Lecture Notes in Computer Science).
Links | BibTeX | Tags: DTIC, Social
@incollection{leonardis_dim_2024,
title = {DIM: Dyadic Interaction Modeling for Social Behavior Generation},
author = {Minh Tran and Di Chang and Maksim Siniukov and Mohammad Soleymani},
editor = {Aleš Leonardis and Elisa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and Gül Varol},
url = {https://link.springer.com/10.1007/978-3-031-72913-3_27},
doi = {10.1007/978-3-031-72913-3_27},
isbn = {978-3-031-72912-6 978-3-031-72913-3},
year = {2024},
date = {2024-12-01},
urldate = {2025-01-16},
booktitle = {Computer Vision – ECCV 2024},
volume = {15095},
pages = {484–503},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {DTIC, Social},
pubstate = {published},
tppubtype = {incollection}
}
Xu, Jiuyi; Chen, Meida; Feng, Andrew; Yu, Zifan; Shi, Yangming
Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework Journal Article
In: 2024, (Publisher: arXiv Version Number: 2).
Abstract | Links | BibTeX | Tags: DTIC, Narrative
@article{xu_open-vocabulary_2024,
title = {Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework},
author = {Jiuyi Xu and Meida Chen and Andrew Feng and Zifan Yu and Yangming Shi},
url = {https://arxiv.org/abs/2412.06268},
doi = {10.48550/ARXIV.2412.06268},
year = {2024},
date = {2024-12-01},
urldate = {2024-12-20},
abstract = {In the domain of the U.S. Army modeling and simulation, the availability of high quality annotated 3D data is pivotal to creating virtual environments for training and simulations. Traditional methodologies for 3D semantic and instance segmentation, such as KpConv, RandLA, Mask3D, etc., are designed to train on extensive labeled datasets to obtain satisfactory performance in practical tasks. This requirement presents a significant challenge, given the inherent scarcity of manually annotated 3D datasets, particularly for the military use cases. Recognizing this gap, our previous research leverages the One World Terrain data repository manually annotated databases, as showcased at IITSEC 2019 and 2021, to enrich the training dataset for deep learning models. However, collecting and annotating large scale 3D data for specific tasks remains costly and inefficient. To this end, the objective of this research is to design and develop a comprehensive and efficient framework for 3D segmentation tasks to assist in 3D data annotation. This framework integrates Grounding DINO and Segment anything Model, augmented by an enhancement in 2D image rendering via 3D mesh. Furthermore, the authors have also developed a user friendly interface that facilitates the 3D annotation process, offering intuitive visualization of rendered images and the 3D point cloud.},
note = {Publisher: arXiv
Version Number: 2},
keywords = {DTIC, Narrative},
pubstate = {published},
tppubtype = {article}
}
Roemmele, Melissa; Gordon, Andrew
From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items Proceedings Article
In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 5193–5203, Association for Computational Linguistics, Miami, Florida, USA, 2024.
Links | BibTeX | Tags: DTIC, Learning Sciences
@inproceedings{roemmele_test-taking_2024,
title = {From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items},
author = {Melissa Roemmele and Andrew Gordon},
url = {https://aclanthology.org/2024.findings-emnlp.299},
doi = {10.18653/v1/2024.findings-emnlp.299},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
pages = {5193–5203},
publisher = {Association for Computational Linguistics},
address = {Miami, Florida, USA},
keywords = {DTIC, Learning Sciences},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhu, Xin; Su, Zhenghui; Gratch, Jonathan; Culbertson, Heather
How Visualizing Touch Can Transform Perceptions of Intensity, Realism, and Emotion? Book Section
In: Kajimoto, Hiroyuki; Lopes, Pedro; Pacchierotti, Claudio; Basdogan, Cagatay; Gori, Monica; Lemaire-Semail, Betty; Marchal, Maud (Ed.): Haptics: Understanding Touch; Technology and Systems; Applications and Interaction, vol. 14768, pp. 194–207, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-70057-6 978-3-031-70058-3, (Series Title: Lecture Notes in Computer Science).
@incollection{kajimoto_how_2024,
title = {How Visualizing Touch Can Transform Perceptions of Intensity, Realism, and Emotion?},
author = {Xin Zhu and Zhenghui Su and Jonathan Gratch and Heather Culbertson},
editor = {Hiroyuki Kajimoto and Pedro Lopes and Claudio Pacchierotti and Cagatay Basdogan and Monica Gori and Betty Lemaire-Semail and Maud Marchal},
url = {https://link.springer.com/10.1007/978-3-031-70058-3_16},
doi = {10.1007/978-3-031-70058-3_16},
isbn = {978-3-031-70057-6 978-3-031-70058-3},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
booktitle = {Haptics: Understanding Touch; Technology and Systems; Applications and Interaction},
volume = {14768},
pages = {194–207},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {VR},
pubstate = {published},
tppubtype = {incollection}
}
Siniukov, Maksim; Yin, Yufeng; Fast, Eli; Qi, Yingshan; Monga, Aarav; Kim, Audrey; Soleymani, Mohammad
SEMPI: A Database for Understanding Social Engagement in Video-Mediated Multiparty Interaction Proceedings Article
In: International Conference on Multimodel Interaction, pp. 546–555, ACM, San Jose Costa Rica, 2024, ISBN: 979-8-4007-0462-8.
Links | BibTeX | Tags: Social Simulation
@inproceedings{siniukov_sempi_2024,
title = {SEMPI: A Database for Understanding Social Engagement in Video-Mediated Multiparty Interaction},
author = {Maksim Siniukov and Yufeng Yin and Eli Fast and Yingshan Qi and Aarav Monga and Audrey Kim and Mohammad Soleymani},
url = {https://dl.acm.org/doi/10.1145/3678957.3685752},
doi = {10.1145/3678957.3685752},
isbn = {979-8-4007-0462-8},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
booktitle = {International Conference on Multimodel Interaction},
pages = {546–555},
publisher = {ACM},
address = {San Jose Costa Rica},
keywords = {Social Simulation},
pubstate = {published},
tppubtype = {inproceedings}
}
Andalibi, Nazanin; Stark, Luke; McDuff, Daniel; Picard, Rosalind; Gratch, Jonathan; Howell, Noura
What should we do with Emotion AI? Towards an Agenda for the Next 30 Years Proceedings Article
In: Companion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing, pp. 98–101, ACM, San Jose Costa Rica, 2024, ISBN: 979-8-4007-1114-5.
Links | BibTeX | Tags: Emotion
@inproceedings{andalibi_what_2024,
title = {What should we do with Emotion AI? Towards an Agenda for the Next 30 Years},
author = {Nazanin Andalibi and Luke Stark and Daniel McDuff and Rosalind Picard and Jonathan Gratch and Noura Howell},
url = {https://dl.acm.org/doi/10.1145/3678884.3689135},
doi = {10.1145/3678884.3689135},
isbn = {979-8-4007-1114-5},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
booktitle = {Companion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing},
pages = {98–101},
publisher = {ACM},
address = {San Jose Costa Rica},
keywords = {Emotion},
pubstate = {published},
tppubtype = {inproceedings}
}
Loucks, Laura; Rizzo, Albert; Rothbaum, Barbara O.
Virtual Reality Exposure for Treating PTSD Due to Military Sexual Trauma Journal Article
In: J Clin Psychol, pp. jclp.23750, 2024, ISSN: 0021-9762, 1097-4679.
Abstract | Links | BibTeX | Tags: DTIC, MedVR
@article{loucks_virtual_2024,
title = {Virtual Reality Exposure for Treating PTSD Due to Military Sexual Trauma},
author = {Laura Loucks and Albert Rizzo and Barbara O. Rothbaum},
url = {https://onlinelibrary.wiley.com/doi/10.1002/jclp.23750},
doi = {10.1002/jclp.23750},
issn = {0021-9762, 1097-4679},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
journal = {J Clin Psychol},
pages = {jclp.23750},
abstract = {ABSTRACT
Virtual reality exposure therapy (VRE) has been used in the treatment of combat‐related PTSD since the late 1990s and was recently adapted to treat PTSD due to military sexual trauma (MST). With content specifically tailored to MST‐related contexts, we present the case study of a military veteran who participated in the open clinical trial examining the feasibility of VRE in the treatment of MST‐related PTSD (Loucks et al. 2019). We illustrate VRE's use in activating the trauma memory to facilitate therapeutic emotional processing across sessions and overall symptom reduction. The case study includes common challenges that may occur during VRE and relevant recommendations. The discussion will include lessons learned from the case study and the open clinical trial, recommendations for the flexible application of VRE, and the ongoing developments in the latest version of the VRE system, informed by feedback acquired from the clinicians and patients who experienced it in the initial clinical trial.},
keywords = {DTIC, MedVR},
pubstate = {published},
tppubtype = {article}
}
Virtual reality exposure therapy (VRE) has been used in the treatment of combat‐related PTSD since the late 1990s and was recently adapted to treat PTSD due to military sexual trauma (MST). With content specifically tailored to MST‐related contexts, we present the case study of a military veteran who participated in the open clinical trial examining the feasibility of VRE in the treatment of MST‐related PTSD (Loucks et al. 2019). We illustrate VRE's use in activating the trauma memory to facilitate therapeutic emotional processing across sessions and overall symptom reduction. The case study includes common challenges that may occur during VRE and relevant recommendations. The discussion will include lessons learned from the case study and the open clinical trial, recommendations for the flexible application of VRE, and the ongoing developments in the latest version of the VRE system, informed by feedback acquired from the clinicians and patients who experienced it in the initial clinical trial.
Hills, Mellanie; Korjian, Serge; Chi, Gerald; Natale, Andrea; Saxon, Leslie; Ferdinand, Keith; Kwaku, Kevin; Brancato, Scott; Baca-Motes, Katie; Steinhubl, Steve; Wessler, Jeff; Goldberg, Nieca; Asthana, Anisha; Shute, Kate; Applebaum, Jill; Doran, Kathleen; Nikolovski, Janeta; Kaul, Simrati; Wentworth, Dereck; Damaraju, Cv; DeFalco, Frank; Tavakoli, Cammie; Patel, Mithun; Curtis, Anne; Spertus, John; Gibson, Charles
Insights for Direct-to-Patient Clinical Trial Recruitment Strategies From the Heartline Study Journal Article
In: Circulation, vol. 150, no. Suppl_1, 2024, ISSN: 0009-7322, 1524-4539.
Abstract | Links | BibTeX | Tags: CBC
@article{hills_insights_2024,
title = {Insights for Direct-to-Patient Clinical Trial Recruitment Strategies From the Heartline Study},
author = {Mellanie Hills and Serge Korjian and Gerald Chi and Andrea Natale and Leslie Saxon and Keith Ferdinand and Kevin Kwaku and Scott Brancato and Katie Baca-Motes and Steve Steinhubl and Jeff Wessler and Nieca Goldberg and Anisha Asthana and Kate Shute and Jill Applebaum and Kathleen Doran and Janeta Nikolovski and Simrati Kaul and Dereck Wentworth and Cv Damaraju and Frank DeFalco and Cammie Tavakoli and Mithun Patel and Anne Curtis and John Spertus and Charles Gibson},
url = {https://www.ahajournals.org/doi/10.1161/circ.150.suppl_1.4143017},
doi = {10.1161/circ.150.suppl_1.4143017},
issn = {0009-7322, 1524-4539},
year = {2024},
date = {2024-11-01},
urldate = {2024-12-05},
journal = {Circulation},
volume = {150},
number = {Suppl_1},
abstract = {Background:
Decentralized clinical trials using direct-to-participant recruitment can potentially engage large, representative participant pools.
Research Question:
Can a decentralized clinical trial use a multichannel approach to recruit patients >65 years old across the United States?
Goals/Aims:
To share insights on multichannel strategies for participant recruitment in the decentralized, app-based Heartline study.
Methods:
Heartline is a randomized trial testing the impact of a mobile app-based heart health program with the electrocardiogram (ECG) and Irregular Rhythm Notification (IRN) features on Apple Watch for early diagnosis, treatment, and outcomes of atrial fibrillation. Eligible participants were US adults aged ≥65 years with an iPhone and Medicare coverage. Multiple pathways for broad outreach were explored, including digital (eg, email, social media) and traditional channels (eg, direct mail, community outreach). Recruitment efforts were assessed and refined to reach a large eligible population.
Results:
A multichannel approach led to textasciitilde300,000 Heartline study app installations. In total, 34,244 participants completed enrollment (Feb 2020-Dec 2022), of whom 28,155 completed baseline demographic assessments. Participants were widely distributed geographically, with notable representation of outlying and rural areas (
Figure 1
). Women accounted for 54% of the participants. Overall, most participants were White (93.0%), with Asian, Black, and Hispanic participants representing 2.8%, 2.7%, and 2.5%, respectively.
Conclusion:
The Heartline study demonstrated the ability to recruit large numbers of participants aged ≥65 years using a direct-to-participant approach. Broad outreach strategies ensured gender and geographic diversity, enrolling a higher percentage of women than typical cardiology trials, and participation from rural areas. However, underrepresentation across racial/ethnic groups persisted and strategies to increase enrollment are needed. For similar trials, a strategic multichannel approach, with strong data and analytics capabilities may be beneficial to effectively target and enroll eligible participants.},
keywords = {CBC},
pubstate = {published},
tppubtype = {article}
}
Decentralized clinical trials using direct-to-participant recruitment can potentially engage large, representative participant pools.
Research Question:
Can a decentralized clinical trial use a multichannel approach to recruit patients >65 years old across the United States?
Goals/Aims:
To share insights on multichannel strategies for participant recruitment in the decentralized, app-based Heartline study.
Methods:
Heartline is a randomized trial testing the impact of a mobile app-based heart health program with the electrocardiogram (ECG) and Irregular Rhythm Notification (IRN) features on Apple Watch for early diagnosis, treatment, and outcomes of atrial fibrillation. Eligible participants were US adults aged ≥65 years with an iPhone and Medicare coverage. Multiple pathways for broad outreach were explored, including digital (eg, email, social media) and traditional channels (eg, direct mail, community outreach). Recruitment efforts were assessed and refined to reach a large eligible population.
Results:
A multichannel approach led to textasciitilde300,000 Heartline study app installations. In total, 34,244 participants completed enrollment (Feb 2020-Dec 2022), of whom 28,155 completed baseline demographic assessments. Participants were widely distributed geographically, with notable representation of outlying and rural areas (
Figure 1
). Women accounted for 54% of the participants. Overall, most participants were White (93.0%), with Asian, Black, and Hispanic participants representing 2.8%, 2.7%, and 2.5%, respectively.
Conclusion:
The Heartline study demonstrated the ability to recruit large numbers of participants aged ≥65 years using a direct-to-participant approach. Broad outreach strategies ensured gender and geographic diversity, enrolling a higher percentage of women than typical cardiology trials, and participation from rural areas. However, underrepresentation across racial/ethnic groups persisted and strategies to increase enrollment are needed. For similar trials, a strategic multichannel approach, with strong data and analytics capabilities may be beneficial to effectively target and enroll eligible participants.