On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Paper
•
2508.11408
•
Published
•
6
•
5
garyzhang
xiaoniqiu
·
AI & ML interests
LLM, Agents
Recent Activity
commented on
a paper
about 11 hours ago
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised
Fine-Tuning and Reinforcement Learning via Dynamic Weighting
commented on
a paper
1 day ago
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised
Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Organizations
None yet
commented
a
paper
about 11 hours ago
commented
a
paper
1 day ago
Add json mode inference for Llama3-8B-Chinese-Chat
#26 opened over 1 year ago
by
xiaoniqiu