Hritik Bansal

OpenThoughts: Data Recipes for Reasoning Models

VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

LaViDa: A Large Diffusion Model for Vision-Language Understanding

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

VideoPhy: Evaluating Physical Commonsense for Video Generation

Generative Verifiers: Reward Modeling as Next-Token Prediction