garyzhang's picture

2 6 5

garyzhang

xiaoniqiu

·

garyzhang99

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

authored a paper 2 days ago

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

View all activity

Organizations

None yet

upvoted a paper 3 days ago

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Paper • 2508.11408 • Published 7 days ago • 6

upvoted a paper 3 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 177

upvoted a paper 5 months ago

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute

Paper • 2503.23803 • Published Mar 31 • 8

upvoted a paper 11 months ago

Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

Paper • 2405.05904 • Published May 9, 2024 • 6

upvoted 2 papers about 1 year ago

Very Large-Scale Multi-Agent Simulation in AgentScope

Paper • 2407.17789 • Published Jul 25, 2024 • 34

OLMo: Accelerating the Science of Language Models

Paper • 2402.00838 • Published Feb 1, 2024 • 84