garyzhang's picture

2 9 4

garyzhang

xiaoniqiu

·

garyzhang99

AI & ML interests

LLM, Agents

Recent Activity

upvoted a paper 24 days ago

Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering

updated a dataset 2 months ago

datajuicer/geometry_sft

published a dataset 2 months ago

datajuicer/geometry_sft

View all activity

Organizations

authored a paper 4 months ago

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

Paper • 2508.11408 • Published Aug 15, 2025 • 8