VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Paper
•
2507.13348
•
Published
•
75
Xiangru Peng
pengxr
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 months ago
VisionThink: Smart and Efficient Vision Language Model via Reinforcement
Learning
authored
a paper
over 1 year ago
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of
LLMs
upvoted
a
paper
over 1 year ago
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of
LLMs
Organizations
None yet