jasonjiang
mikinyaa
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 9 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
upvoted
a
paper
about 11 hours ago
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
Organizations
None yet
-
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
Paper • 2502.09411 • Published • 22 -
GAIR/lima
Viewer • Updated • 1.33k • 627 • 453 -
HuggingFaceM4/FineVision
Viewer • Updated • 24.2M • 108k • 465
-
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
Paper • 2502.09411 • Published • 22 -
GAIR/lima
Viewer • Updated • 1.33k • 627 • 453 -
HuggingFaceM4/FineVision
Viewer • Updated • 24.2M • 108k • 465
models
0
None public yet
datasets
0
None public yet