arxiv:2608.00220
Shaohang Wei
SylvainWei
AI & ML interests
NLP, LLM
Recent Activity
authored a paper 3 days ago
Verifier-Induced Support Reshaping in On-Policy Optimization authored a paper 3 days ago
Experience Augmented Policy Optimization for LLM Reasoning authored a paper 3 days ago
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMsOrganizations
models 12
SylvainWei/qwen3_8b_base-algo_dapo-data_iftrain-after_dapotrainset
Updated
SylvainWei/Qwen3-8B-Base_DAPO_trainset_n8_1node_h800
Updated
SylvainWei/limo-14B-ckpt-epoch-5
15B • Updated • 11
SylvainWei/limo-14B-ckpt-epoch-4
15B • Updated • 8
SylvainWei/limo-14B-ckpt-epoch-3
15B • Updated • 7
SylvainWei/limo-14B-ckpt-epoch-2
15B • Updated • 3
SylvainWei/limo-14B-ckpt-epoch-1
15B • Updated • 4
SylvainWei/s1.1-14B-ckpt-epoch-4
15B • Updated • 11
SylvainWei/s1.1-14B-ckpt-epoch-5
15B • Updated • 10
SylvainWei/s1.1-14B-ckpt-epoch-3
15B • Updated • 6