LARK-Lab/SWITCH-Phase3-GRPO-LoRA-Qwen3-8B
Text Generation • 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/EnvFactory-8B
Text Generation • 8B • Updated • 8
LARK-Lab/EnvFactory-4B
Text Generation • 4B • Updated • 7
LARK-Lab/EnvFactory-1.7B
Text Generation • 2B • Updated • 79
LARK-Lab/CodeScaler-8B
Text Classification • 8B • Updated • 5
LARK-Lab/CodeScaler-4B
Text Classification • 4B • Updated • 7
LARK-Lab/CodeScaler-1.7B
Text Classification • 2B • Updated • 78