Zhuoran Jin

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos

Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling

Pixels Lie, Code Doesn't: Thinking with Visual Programming for ''Seemingly Impossible'' Multimodal Agentic Reasoning Tasks

WebPlanner: Task Planning with Autonomous Experience Exploration and Utilization for Real World Multimodal Web Agents

RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models