LARK Lab@HKUST (GZ)

non-profit

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

AI & ML interests

Large Language Models

Recent Activity

terr1ble authored a paper 1 day ago

SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

terr1ble authored a paper 1 day ago

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

sapphirex submitted a paper 2 days ago

Mosaic: Multi-Session Agentic Reinforcement Learning

View all activity

Papers

Mosaic: Multi-Session Agentic Reinforcement Learning

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

View all Papers

authored 2 papers 1 day ago

SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

Paper • 2608.00068 • Published Jul 29

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Paper • 2610.21463 • Published 3 days ago • 21

submitted a paper to Daily Papers 2 days ago

Mosaic: Multi-Session Agentic Reinforcement Learning

Paper • 2610.22174 • Published 3 days ago • 52

submitted a paper to Daily Papers 2 days ago

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Paper • 2610.21463 • Published 3 days ago • 21

authored a paper about 1 month ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published Sep 11 • 69

published 3 models 3 months ago

LARK-Lab/FormalRx-1.7B

2B • Updated Mar 22 • 4

LARK-Lab/FormalRx-4b

4B • Updated Mar 21 • 10

LARK-Lab/FormalRx-8b

8B • Updated Mar 21 • 56

updated a collection 4 months ago

Trainee2Trainer

This is the checkpoints and dataset for: From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning • 3 items • Updated Jun 18 • 1

updated a dataset 4 months ago

LARK-Lab/MAPF-FrozenLake-Benchmark

Viewer • Updated Jun 18 • 3.15k • 38 • 1

updated a model 4 months ago

LARK-Lab/Trainee2Trainer

Text Generation • 4B • Updated Jun 18 • 25 • 1

updated a collection 4 months ago

Trainee2Trainer

This is the checkpoints and dataset for: From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning • 3 items • Updated Jun 18 • 1

in LARK-Lab/MAPF-FrozenLake-Benchmark 4 months ago

Rename configs from wr* to benchmark_wr* to match codebase convention

#2 opened 4 months ago by

Initial upload: MAPF-FrozenLake eval benchmark

#1 opened 4 months ago by

published a dataset 4 months ago

LARK-Lab/MAPF-FrozenLake-Benchmark

Viewer • Updated Jun 18 • 3.15k • 38 • 1

updated a collection 4 months ago

Trainee2Trainer

This is the checkpoints and dataset for: From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning • 3 items • Updated Jun 18 • 1

submitted a paper to Daily Papers 4 months ago

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

Paper • 2606.17682 • Published Jun 16 • 26

published a model 4 months ago

LARK-Lab/Trainee2Trainer

Text Generation • 4B • Updated Jun 18 • 25 • 1

updated a dataset 4 months ago

LARK-Lab/EnvFactory-SFT-DeepSeekV4Flash-OpenAI

Viewer • Updated Jun 17 • 3.27k • 20

published a dataset 4 months ago

LARK-Lab/EnvFactory-SFT-DeepSeekV4Flash-OpenAI

Viewer • Updated Jun 17 • 3.27k • 20