Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Zhuoran Jin
jinzhuoran
AI & ML interests
NLP
Recent Activity
upvoted a paper about 24 hours ago
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks upvoted a paper 22 days ago
ASI-Bench: At the Dawn of Artificial Superintelligence upvoted a paper about 1 month ago
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent LearningOrganizations
None yet
datasets 45
jinzhuoran/MMR-VIP
Viewer • Updated • 1.68k • 25 • 3
jinzhuoran/OmniRewardData
Viewer • Updated • 778k • 705 • 2
jinzhuoran/AOKVQA-200
Viewer • Updated • 200 • 13
jinzhuoran/MMMU_Pro-200
Viewer • Updated • 200 • 39
jinzhuoran/MathVista-200
Viewer • Updated • 200 • 34
jinzhuoran/MathVerse-400
Viewer • Updated • 400 • 17
jinzhuoran/VisualSimpleQA-200
Viewer • Updated • 200 • 11
jinzhuoran/MMMU-500
Viewer • Updated • 500 • 15
jinzhuoran/MathVision-200
Viewer • Updated • 200 • 148
jinzhuoran/MathVerse-200
Viewer • Updated • 200 • 26