LARK Lab@HKUST (GZ)

non-profit

https://lark-lab-hkustgz.github.io/

AI & ML interests

Large Language Models

Recent Activity

RolandXMR authored a paper about 19 hours ago

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation

RolandXMR authored a paper about 19 hours ago

ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting

RolandXMR authored a paper about 19 hours ago

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

View all activity

Papers

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Efficient RLVR Training via Weighted Mutual Information Data Selection

View all Papers

LARK-Lab 's collections 2