shufanshen/Qwen3-4B-GRPO-CodeEurus-150-steps
Reinforcement Learning • 4B • Updated • 19
Shufan Shen
shufanshen
AI & ML interests
Interpretable machine learning, parameter-efficient fine-tuning.
Recent Activity
authored a paper 1 day ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training authored a paper 1 day ago
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs liked a model 17 days ago
Edge0/Edge0-35B-A3B-previewOrganizations
shufanshen/Qwen3-8B-GRPO-DeepMath-50-steps
Reinforcement Learning • 8B • Updated • 15
shufanshen/Qwen3-8B-GRPO-DeepMath-150-steps
Reinforcement Learning • 8B • Updated • 17
shufanshen/Qwen3-8B-GRPO-DeepMath-100-steps
Reinforcement Learning • 8B • Updated • 12
shufanshen/Qwen3-4B-GRPO-DeepMath-50-steps
Reinforcement Learning • 4B • Updated • 15
shufanshen/Qwen3-4B-GRPO-DeepMath-150-steps
Reinforcement Learning • 4B • Updated • 18
shufanshen/Qwen3-4B-GRPO-DeepMath-100-steps
Reinforcement Learning • 4B • Updated • 13
shufanshen/Qwen3-4B-GRPO-CodeEurus-100-steps
Reinforcement Learning • 4B • Updated • 15
shufanshen/Qwen3-1.7B-GRPO-DeepMath-50-steps
Reinforcement Learning • 2B • Updated • 10
shufanshen/Qwen3-1.7B-GRPO-DeepMath-150-steps
Reinforcement Learning • 2B • Updated • 10
shufanshen/Qwen3-1.7B-GRPO-DeepMath-100-steps
Reinforcement Learning • 2B • Updated • 11
shufanshen/VL-SAE
Image-Text-to-Text • Updated • 2