Project Page: https://mmecot.github.io/
Dongzhi Jiang
CaraJ
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 10 hours ago
Does Reinforcement Learning Really Incentivize Reasoning Capacity in
LLMs Beyond the Base Model?
upvoted
a
paper
10 days ago
VCR-Bench: A Comprehensive Evaluation Framework for Video
Chain-of-Thought Reasoning
liked
a dataset
11 days ago
CaraJ/MME-CoT_VLMEvalKit
Organizations
Collections
3
models
1
datasets
8
CaraJ/MME-CoT
Viewer
•
Updated
•
1.13k
•
462
•
18
CaraJ/MME-CoT_VLMEvalKit
Viewer
•
Updated
•
1.13k
•
39
•
1
CaraJ/MAVIS-Function
Viewer
•
Updated
•
60
•
141
•
7
CaraJ/MAVIS-Geometry
Viewer
•
Updated
•
40
•
197
•
11
CaraJ/MMSearch
Viewer
•
Updated
•
900
•
176
•
20
CaraJ/baihe-private
Viewer
•
Updated
•
200
•
24
CaraJ/Mathverse_VLMEvalKit
Viewer
•
Updated
•
8.67k
•
54
•
1
CaraJ/MathVerse-lmmseval
Viewer
•
Updated
•
8.67k
•
1.37k
•
2