RL checkpoints of Octopus-8B and baselines of paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation
Yi Ding
Tuwhy
AI & ML interests
None yet
Recent Activity
updated a model 10 days ago
Tuwhy/Qwen3-32B-OPST published a model 10 days ago
Tuwhy/Qwen3-32B-OPST upvoted a paper about 2 months ago
Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control