Publications

@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 = {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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}