Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Zhuoran Jin
jinzhuoran
AI & ML interests
NLP
Recent Activity
upvoted a paper 2 days ago
Critique of Agent Model submitted a paper 4 days ago
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix ItOrganizations
None yet