Agent Intelligence-Lab 🦞

non-profit

AI & ML interests

LLM, VLM, Agents, Robotics, Physical World

Recent Activity

wuxiyang submitted a paper 1 day ago

Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents

zli12321 updated a dataset 9 days ago

IntelligenceLab/Long-Horizon-Terminal-Bench

zli12321 updated a Space 9 days ago

IntelligenceLab/AI-for-Science

View all activity

Papers

Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents

View all Papers

submitted a paper to Daily Papers 1 day ago

Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents

Paper • 2610.18082 • Published 7 days ago • 4

updated a dataset 9 days ago

IntelligenceLab/Long-Horizon-Terminal-Bench

Benchmark • Updated 9 days ago • 154 • 32.6k • 141

updated a Space 9 days ago

AI for Science Collaboration

Join scientific AI collaboration as a graduate researcher

updated a dataset 11 days ago

IntelligenceLab/LHTB-leaderboard

Viewer • Updated 11 days ago • 1.22k • 5.78k • 4

published a Space 11 days ago

AI for Science Collaboration

Join scientific AI collaboration as a graduate researcher

updated a Space 11 days ago

Terminal Data Website

Access verified training tasks for AI agents

published a Space 13 days ago

Terminal Data Website

Access verified training tasks for AI agents

updated a Space 14 days ago

RSR-27B Sample Trajectories

Expert vs. rewritten agent trajectories behind RSR-27B

published a Space 14 days ago

RSR-27B Sample Trajectories

Expert vs. rewritten agent trajectories behind RSR-27B

updated a model 14 days ago

IntelligenceLab/RSR-27B

Image-Text-to-Text • 28B • Updated 13 days ago • 129 • 2

authored a paper 14 days ago

Self-Supervised Scaling of Terminal Environments for Scientific Domains

Paper • 2610.02710 • Published 18 days ago • 13

submitted a paper to Daily Papers 15 days ago

Self-Supervised Scaling of Terminal Environments for Scientific Domains

Paper • 2610.02710 • Published 18 days ago • 13

authored a paper 15 days ago

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 18 days ago • 106

published a model 19 days ago

IntelligenceLab/RSR-27B

Image-Text-to-Text • 28B • Updated 13 days ago • 129 • 2

authored a paper 22 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 25 days ago • 139

submitted a paper to Daily Papers 22 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 25 days ago • 139

authored 4 papers 26 days ago

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published Sep 18 • 35

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges

Paper • 2501.02189 • Published Jan 4, 2025 • 1

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

Paper • 2606.04291 • Published Jun 2 • 6

Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Paper • 2604.05333 • Published Apr 7 • 22