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 19 hours ago
MORSE-500: A Programmatically Controllable Video Benchmark to
Stress-Test Multimodal Reasoning
authored
a paper
5 days ago
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
authored
a paper
5 days ago
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in
Videos
Organizations
None yet
Collections
1
spaces
1
datasets
44
jinzhuoran/OmniRewardData
Viewer
•
Updated
•
778k
•
155
•
1
jinzhuoran/AOKVQA-200
Viewer
•
Updated
•
200
•
26
jinzhuoran/MMMU_Pro-200
Viewer
•
Updated
•
200
•
23
jinzhuoran/MathVista-200
Viewer
•
Updated
•
200
•
12
jinzhuoran/MathVerse-400
Viewer
•
Updated
•
400
•
27
jinzhuoran/VisualSimpleQA-200
Viewer
•
Updated
•
200
•
28
jinzhuoran/MMMU-500
Viewer
•
Updated
•
500
•
28
jinzhuoran/MathVision-200
Viewer
•
Updated
•
200
•
30
jinzhuoran/MathVerse-200
Viewer
•
Updated
•
200
•
32
jinzhuoran/AlgoPuzzleVQA-200
Viewer
•
Updated
•
200
•
31