Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Paper
•
2506.04207
•
Published
•
45
•
4
Arthur EDMOND
Shumatsurontek
·
AI & ML interests
LLM & Computer Vision
Recent Activity
upvoted
a
paper
2 days ago
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain
Perspective
liked
a model
14 days ago
deepseek-ai/DeepSeek-R1-0528
commented on
a paper
20 days ago
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged
Reinforcement Learning
Organizations
commented
a
paper
20 days ago
OpenGVLab/InternVL3-78B
👍
13
3
#801 opened 2 months ago
by
galvani4987