1 citations · 2 across the 10 of their papers we have counts for
11 papers
Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering
Rohit Kundu, Arindam Dutta, Sarosij Bose +2
Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning th…
Driving Video Retrieval for Complex Queries with Structured Grounding
Manyi Yao, Sparsh Garg, Christian Shelton +2
Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins a…
SAGA: Source Attribution of Generative AI Videos
Rohit Kundu, Vishal Mohanty, Hao Xiong +3
The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce SAGA (Source Attri…
VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions
Yash Garg, Saketh Bachu, Arindam Dutta +5
Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these met…
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
Trishna Chakraborty, Udita Ghosh, Xiaopan Zhang +5
Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user ins…
FORGE: Forensic Reasoning with Grounded Evidence
Rohit Kundu, Shan Jia, Vishal Mohanty +2
Forensic deepfake analysis demands more than binary classification: investigators need region-grounded natural language explanations they can verify against the image. Multimodal l…
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
Arindam Dutta, Meng Zheng, Zhongpai Gao +5
Reconstructing clothed humans from a single image is a fundamental task in computer vision with wide-ranging applications. Although existing monocular clothed human reconstruction…
Unsupervised Domain Adaptation for Occlusion Resilient Human Pose Estimation
Arindam Dutta, Sarosij Bose, Saketh Bachu +3
Occlusions are a significant challenge to human pose estimation algorithms, often resulting in inaccurate and anatomically implausible poses. Although current occlusion-robust huma…
Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content
Rohit Kundu, Hao Xiong, Vishal Mohanty +2
Existing DeepFake detection techniques primarily focus on facial manipulations, such as face-swapping or lip-syncing. However, advancements in text-to-video (T2V) and image-to-vide…
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
Saketh Bachu, Erfan Shayegani, Rohit Lal +6
Vision-language models (VLMs) have improved significantly in their capabilities, but their complex architecture makes their safety alignment challenging. In this paper, we reveal a…
Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior
Calvin-Khang Ta, Arindam Dutta, Rohit Kundu +4
The Skinned Multi-Person Linear (SMPL) model plays a crucial role in 3D human pose estimation, providing a streamlined yet effective representation of the human body. However, ensu…