LARK Lab@HKUST (GZ)

AI & ML interests

Large Language Models

Recent Activity

xinyu04  submitted a paper 17 days ago

Efficient RLVR Training via Weighted Mutual Information Data Selection

xinyu04  authored a paper 17 days ago

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters

xinyu04  authored a paper 17 days ago

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models

View all activity

Papers

Efficient RLVR Training via Weighted Mutual Information Data Selection

View all Papers

Team members 13