PRM and fine-tuned LLM used in our PURE github repo: https://github.com/CJReinforce/PURE
Jie Cheng
jinachris
AI & ML interests
Reinforcement learning, LLM
Recent Activity
upvoted
a
paper
30 days ago
TC-Light: Temporally Consistent Relighting for Dynamic Long Videos
liked
a dataset
about 1 month ago
a-m-team/AM-DeepSeek-R1-0528-Distilled
updated
a model
about 2 months ago
jinachris/PURE-PRM-7B
Organizations
None yet
