Publications

@misc{kwon_evaluating_2025,

title = {Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans},

author = {Deuksin Kwon and Kaleen Shrestha and Bin Han and Elena Hayoung Lee and Gale Lucas},

url = {http://arxiv.org/abs/2509.16394},

doi = {10.48550/arXiv.2509.16394},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-25},

publisher = {arXiv},

abstract = {Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses the behavioral alignment of personality-prompted LLMs in adversarial dispute resolution by simulating multi-turn conflict dialogues that incorporate negotiation. Each LLM is guided by a matched Five-Factor personality profile to control for individual variation and enhance realism. We evaluate alignment across three dimensions: linguistic style, emotional expression (e.g., anger dynamics), and strategic behavior. GPT-4.1 achieves the closest alignment with humans in linguistic style and emotional dynamics, while Claude-3.7-Sonnet best reflects strategic behavior. Nonetheless, substantial alignment gaps persist. Our findings establish a benchmark for alignment between LLMs and humans in socially complex interactions, underscoring both the promise and the limitations of personality conditioning in dialogue modeling.},

note = {arXiv:2509.16394 [cs]},

keywords = {AI, DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{wang_implicit_2025,

title = {Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations},

author = {Yunzhe Wang and Gale M. Lucas and Burcin Becerik-Gerber and Volkan Ustun},

url = {http://arxiv.org/abs/2509.16457},

doi = {10.48550/arXiv.2509.16457},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-25},

publisher = {arXiv},

abstract = {Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often deviate from expert expectations and real-world data–a phenomenon we term the Behavior-Realism Gap. To address this, we introduce a theoretical framework called Persona-Environment Behavioral Alignment (PEBA), formulated as a distribution matching problem grounded in Lewin's behavior equation stating that behavior is a function of the person and their environment. Leveraging PEBA, we propose PersonaEvolve (PEvo), an LLM-based optimization algorithm that iteratively refines agent personas, implicitly aligning their collective behaviors with realistic expert benchmarks within a specified environmental context. We validate PEvo in an active shooter incident simulation we developed, achieving an 84% average reduction in distributional divergence compared to no steering and a 34% improvement over explicit instruction baselines. Results also show PEvo-refined personas generalize to novel, related simulation scenarios. Our method greatly enhances behavioral realism and reliability in high-stakes social simulations. More broadly, the PEBA-PEvo framework provides a principled approach to developing trustworthy LLM-driven social simulations.},

note = {arXiv:2509.16457 [cs]},

keywords = {AI, DTIC, Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@misc{wang_data-driven_2025,

title = {A data-driven discretized CS:GO simulation environment to facilitate strategic multi-agent planning research},

author = {Yunzhe Wang and Volkan Ustun and Chris McGroarty},

url = {http://arxiv.org/abs/2509.06355},

doi = {10.48550/arXiv.2509.06355},

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {Modern simulation environments for complex multi-agent interactions must balance high-fidelity detail with computational efficiency. We present DECOY, a novel multi-agent simulator that abstracts strategic, long-horizon planning in 3D terrains into high-level discretized simulation while preserving low-level environmental fidelity. Using Counter-Strike: Global Offensive (CS:GO) as a testbed, our framework accurately simulates gameplay using only movement decisions as tactical positioning – without explicitly modeling low-level mechanics such as aiming and shooting. Central to our approach is a waypoint system that simplifies and discretizes continuous states and actions, paired with neural predictive and generative models trained on real CS:GO tournament data to reconstruct event outcomes. Extensive evaluations show that replays generated from human data in DECOY closely match those observed in the original game. Our publicly available simulation environment provides a valuable tool for advancing research in strategic multi-agent planning and behavior generation.},

note = {arXiv:2509.06355 [cs]},

keywords = {DTIC, Simulation},

pubstate = {published},

tppubtype = {misc}

}

@misc{rakshit_emotionally-aware_2025,

title = {Emotionally-Aware Agents for Dispute Resolution},

author = {Sushrita Rakshit and James Hale and Kushal Chawla and Jeanne M. Brett and Jonathan Gratch},

url = {http://arxiv.org/abs/2509.04465},

doi = {10.48550/arXiv.2509.04465},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {In conflict, people use emotional expressions to shape their counterparts' thoughts, feelings, and actions. This paper explores whether automatic text emotion recognition offers insight into this influence in the context of dispute resolution. Prior work has shown the promise of such methods in negotiations; however, disputes evoke stronger emotions and different social processes. We use a large corpus of buyer-seller dispute dialogues to investigate how emotional expressions shape subjective and objective outcomes. We further demonstrate that large-language models yield considerably greater explanatory power than previous methods for emotion intensity annotation and better match the decisions of human annotators. Findings support existing theoretical models for how emotional expressions contribute to conflict escalation and resolution and suggest that agent-based systems could be useful in managing disputes by recognizing and potentially mitigating emotional escalation.},

note = {arXiv:2509.04465 [cs]},

keywords = {AI, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{beltz_guarding_2025,

title = {Guarding Against Malicious Biased Threats (GAMBiT) Experiments: Revealing Cognitive Bias in Human-Subjects Red-Team Cyber Range Operations},

author = {Brandon Beltz and Jim Doty and Yvonne Fonken and Nikolos Gurney and Brett Israelsen and Nathan Lau and Stacy Marsella and Rachelle Thomas and Stoney Trent and Peggy Wu and Ya-Ting Yang and Quanyan Zhu},

url = {http://arxiv.org/abs/2508.20963},

doi = {10.48550/arXiv.2508.20963},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {We present three large-scale human-subjects red-team cyber range datasets from the Guarding Against Malicious Biased Threats (GAMBiT) project. Across Experiments 1-3 (July 2024-March 2025), 19-20 skilled attackers per experiment conducted two 8-hour days of self-paced operations in a simulated enterprise network (SimSpace Cyber Force Platform) while we captured multi-modal data: self-reports (background, demographics, psychometrics), operational notes, terminal histories, keylogs, network packet captures (PCAP), and NIDS alerts (Suricata). Each participant began from a standardized Kali Linux VM and pursued realistic objectives (e.g., target discovery and data exfiltration) under controlled constraints. Derivative curated logs and labels are included. The combined release supports research on attacker behavior modeling, bias-aware analytics, and method benchmarking. Data are available via IEEE Dataport entries for Experiments 1-3.},

note = {arXiv:2508.20963 [cs]},

keywords = {DTIC, Security},

pubstate = {published},

tppubtype = {misc}

}

@misc{han_can_2025,

title = {Can LLMs Generate Behaviors for Embodied Virtual Agents Based on Personality Traits?},

author = {Bin Han and Deuksin Kwon and Spencer Lin and Kaleen Shrestha and Jonathan Gratch},

url = {http://arxiv.org/abs/2508.21087},

doi = {10.48550/arXiv.2508.21087},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {This study proposes a framework that employs personality prompting with Large Language Models to generate verbal and nonverbal behaviors for virtual agents based on personality traits. Focusing on extraversion, we evaluated the system in two scenarios: negotiation and ice breaking, using both introverted and extroverted agents. In Experiment 1, we conducted agent to agent simulations and performed linguistic analysis and personality classification to assess whether the LLM generated language reflected the intended traits and whether the corresponding nonverbal behaviors varied by personality. In Experiment 2, we carried out a user study to evaluate whether these personality aligned behaviors were consistent with their intended traits and perceptible to human observers. Our results show that LLMs can generate verbal and nonverbal behaviors that align with personality traits, and that users are able to recognize these traits through the agents' behaviors. This work underscores the potential of LLMs in shaping personality aligned virtual agents.},

note = {arXiv:2508.21087 [cs]},

keywords = {DTIC?, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{chen_idu_2025,

title = {IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data},

author = {Meida Chen and Luis Leal and Yue Hu and Rong Liu and Butian Xiong and Andrew Feng and Jiuyi Xu and Yangming Shi},

url = {http://arxiv.org/abs/2508.17579},

doi = {10.48550/arXiv.2508.17579},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {For simulation and training purposes, military organizations have made substantial investments in developing high-resolution 3D virtual environments through extensive imaging and 3D scanning. However, the dynamic nature of battlefield conditions-where objects may appear or vanish over time-makes frequent full-scale updates both time-consuming and costly. In response, we introduce the Incremental Dynamic Update (IDU) pipeline, which efficiently updates existing 3D reconstructions, such as 3D Gaussian Splatting (3DGS), with only a small set of newly acquired images. Our approach starts with camera pose estimation to align new images with the existing 3D model, followed by change detection to pinpoint modifications in the scene. A 3D generative AI model is then used to create high-quality 3D assets of the new elements, which are seamlessly integrated into the existing 3D model. The IDU pipeline incorporates human guidance to ensure high accuracy in object identification and placement, with each update focusing on a single new object at a time. Experimental results confirm that our proposed IDU pipeline significantly reduces update time and labor, offering a cost-effective and targeted solution for maintaining up-to-date 3D models in rapidly evolving military scenarios.},

note = {arXiv:2508.17579 [cs]},

keywords = {DTIC, VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{hans_quantifying_2025,

title = {Quantifying Loss Aversion in Cyber Adversaries via LLM Analysis},

author = {Soham Hans and Nikolos Gurney and Stacy Marsella and Sofia Hirschmann},

url = {http://arxiv.org/abs/2508.13240},

doi = {10.48550/arXiv.2508.13240},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {Understanding and quantifying human cognitive biases from empirical data has long posed a formidable challenge, particularly in cybersecurity, where defending against unknown adversaries is paramount. Traditional cyber defense strategies have largely focused on fortification, while some approaches attempt to anticipate attacker strategies by mapping them to cognitive vulnerabilities, yet they fall short in dynamically interpreting attacks in progress. In recognition of this gap, IARPA's ReSCIND program seeks to infer, defend against, and even exploit attacker cognitive traits. In this paper, we present a novel methodology that leverages large language models (LLMs) to extract quantifiable insights into the cognitive bias of loss aversion from hacker behavior. Our data are collected from an experiment in which hackers were recruited to attack a controlled demonstration network. We process the hacker generated notes using LLMs using it to segment the various actions and correlate the actions to predefined persistence mechanisms used by hackers. By correlating the implementation of these mechanisms with various operational triggers, our analysis provides new insights into how loss aversion manifests in hacker decision-making. The results demonstrate that LLMs can effectively dissect and interpret nuanced behavioral patterns, thereby offering a transformative approach to enhancing cyber defense strategies through real-time, behavior-based analysis.},

note = {arXiv:2508.13240 [cs]},

keywords = {DTIC, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{xiong_splat_2025,

title = {Splat Feature Solver},

author = {Butian Xiong and Rong Liu and Kenneth Xu and Meida Chen and Andrew Feng},

url = {http://arxiv.org/abs/2508.12216},

doi = {10.48550/arXiv.2508.12216},

year  = {2025},

date = {2025-08-01},

urldate = {2025-09-18},

publisher = {arXiv},

abstract = {Feature lifting has emerged as a crucial component in 3D scene understanding, enabling the attachment of rich image feature descriptors (e.g., DINO, CLIP) onto splat-based 3D representations. The core challenge lies in optimally assigning rich general attributes to 3D primitives while addressing the inconsistency issues from multi-view images. We present a unified, kernel- and feature-agnostic formulation of the feature lifting problem as a sparse linear inverse problem, which can be solved efficiently in closed form. Our approach admits a provable upper bound on the global optimal error under convex losses for delivering high quality lifted features. To address inconsistencies and noise in multi-view observations, we introduce two complementary regularization strategies to stabilize the solution and enhance semantic fidelity. Tikhonov Guidance enforces numerical stability through soft diagonal dominance, while Post-Lifting Aggregation filters noisy inputs via feature clustering. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on open-vocabulary 3D segmentation benchmarks, outperforming training-based, grouping-based, and heuristic-forward baselines while producing the lifted features in minutes. Code is available at textbackslashhrefhttps://github.com/saliteta/splat-distiller.gittextbackslashtextbfgithub. We also have a textbackslashhrefhttps://splat-distiller.pages.dev/},

note = {arXiv:2508.12216 [cs]},

keywords = {DTIC?, VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{king_detecting_2025,

title = {Detecting AI Assistance in Abstract Complex Tasks},

author = {Tyler King and Nikolos Gurney and John H. Miller and Volkan Ustun},

url = {http://arxiv.org/abs/2507.10761},

doi = {10.48550/arXiv.2507.10761},

year  = {2025},

date = {2025-07-01},

urldate = {2025-08-19},

publisher = {arXiv},

abstract = {Detecting assistance from artificial intelligence is increasingly important as they become ubiquitous across complex tasks such as text generation, medical diagnosis, and autonomous driving. Aid detection is challenging for humans, especially when looking at abstract task data. Artificial neural networks excel at classification thanks to their ability to quickly learn from and process large amounts of data – assuming appropriate preprocessing. We posit detecting help from AI as a classification task for such models. Much of the research in this space examines the classification of complex but concrete data classes, such as images. Many AI assistance detection scenarios, however, result in data that is not machine learning-friendly. We demonstrate that common models can effectively classify such data when it is appropriately preprocessed. To do so, we construct four distinct neural network-friendly image formulations along with an additional time-series formulation that explicitly encodes the exploration/exploitation of users, which allows for generalizability to other abstract tasks. We benchmark the quality of each image formulation across three classical deep learning architectures, along with a parallel CNN-RNN architecture that leverages the additional time series to maximize testing performance, showcasing the importance of encoding temporal and spatial quantities for detecting AI aid in abstract tasks.},

note = {arXiv:2507.10761 [cs]},

keywords = {AI, DTIC?},

pubstate = {published},

tppubtype = {misc}

}

@misc{chen_rdd_2025,

title = {RDD: Robust Feature Detector and Descriptor using Deformable Transformer},

author = {Gonglin Chen and Tianwen Fu and Haiwei Chen and Wenbin Teng and Hanyuan Xiao and Yajie Zhao},

url = {http://arxiv.org/abs/2505.08013},

doi = {10.48550/arXiv.2505.08013},

year  = {2025},

date = {2025-06-01},

urldate = {2025-07-17},

publisher = {arXiv},

abstract = {As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despite their ubiquity. While recent works have identified the importance of local features in modeling geometric transformations, these methods fail to learn the visual cues present in long-range relationships. We present Robust Deformable Detector (RDD), a novel and robust keypoint detector/descriptor leveraging the deformable transformer, which captures global context and geometric invariance through deformable self-attention mechanisms. Specifically, we observed that deformable attention focuses on key locations, effectively reducing the search space complexity and modeling the geometric invariance. Furthermore, we collected an Air-to-Ground dataset for training in addition to the standard MegaDepth dataset. Our proposed method outperforms all state-of-the-art keypoint detection/description methods in sparse matching tasks and is also capable of semi-dense matching. To ensure comprehensive evaluation, we introduce two challenging benchmarks: one emphasizing large viewpoint and scale variations, and the other being an Air-to-Ground benchmark – an evaluation setting that has recently gaining popularity for 3D reconstruction across different altitudes.},

note = {arXiv:2505.08013 [cs]},

keywords = {VGL},

pubstate = {published},

tppubtype = {misc}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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 = {DTIC, Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@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}

}

@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}

}

@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}

}