Reincarnated Mix-policy Proximal Policy Gradient (ReMix), a general approach to enable on-policy RFT methods like PPO and GRPO to leverage off-policy.
Jing Liang
AnitaLeung
AI & ML interests
None yet
Recent Activity
updated a model about 2 months ago
AnitaLeung/opus-round2-qwen3_5-27b-step56-4shards published a model about 2 months ago
AnitaLeung/opus-round2-qwen3_5-27b-step56-4shards updated a model about 2 months ago
AnitaLeung/opus-round2-qwen3_5-9b-step42Organizations
None yet
models 7
AnitaLeung/opus-round2-qwen3_5-27b-step56-4shards
27B • Updated • 6
AnitaLeung/opus-round2-qwen3_5-9b-step42
9B • Updated • 4
AnitaLeung/qwen35-27b-0710-epoch2
27B • Updated • 10
AnitaLeung/qwen35-27b-0710-epoch1
Updated • 13
AnitaLeung/qwen35-4b-0629-sft
2B • Updated • 5
AnitaLeung/Remix-R1-Distilled-Qwen-1.5B
2B • Updated • 12 • 1
AnitaLeung/Remix-R1-Distilled-Qwen-7B
8B • Updated • 10 • 2
datasets 0
None public yet