LARK-Lab/EnvFactory-SFT-DeepSeekV4Flash
Updated
AI & ML interests
Large Language Models
Recent Activity
View all activity
Papers
Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
LARK-Lab/SWITCH-Math-Train
Viewer • Updated • 45.8k
LARK-Lab/EnvFactory-RL
Viewer • Updated • 3.09k • 101
LARK-Lab/EnvFactory-SFT-FILTERED
Viewer • Updated • 26.5k • 135
LARK-Lab/EnvFactory-SFT-ALL
Viewer • Updated • 53.4k • 104
LARK-Lab/FormalRx-Test
Viewer • Updated • 7.03k • 991 • 2
LARK-Lab/CodeScalerPair-51K
Viewer • Updated • 51.1k • 36 • 1