On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Paper
•
2508.11408
•
Published
•
8
•
6
garyzhang
xiaoniqiu
·
AI & ML interests
LLM, Agents
Recent Activity
authored
a paper
5 days ago
The Synergy between Data and Multi-Modal Large Language Models: A Survey
from Co-Development Perspective
authored
a paper
5 days ago
Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement
Fine-Tuning of Large Language Models
authored
a paper
5 days ago
Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with
Foundation Models
Organizations
commented
2
papers
6 months ago
Add json mode inference for Llama3-8B-Chinese-Chat
#26 opened almost 2 years ago
by
xiaoniqiu