collaborators

7 papers

cs.CV2026

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…

cs.CV2026

Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation

Sarosij Bose, Ravi K. Rajendran, Biplob Debnath +3

Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical profess…

cs.CV2025

Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes

Sarosij Bose, Arindam Dutta, Sayak Nag +4

Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered…

cs.CV2025

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…

cs.CV2025

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Sayak Nag, Udita Ghosh, Calvin-Khang Ta +3

Scene Graph Generation (SGG) aims to represent visual scenes by identifying objects and their pairwise relationships, providing a structured understanding of image content. However…

cs.CV2025

Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation

Sarosij Bose, Hannah Dela Cruz, Arindam Dutta +3

Human pose estimation is a critical tool across a variety of healthcare applications. Despite significant progress in pose estimation algorithms targeting adults, such developments…