Tsinghua Embodied AI Lab (TEA Lab)

university

TEA-Lab

AI & ML interests

The Tsinghua Embodied AI Lab (TEA Lab) is led by Prof. Huazhe Xu 🍯, where we build robot 🤖️ and then bring intelligence to them 🌍！

Recent Activity

cheryyunl submitted a paper 15 days ago

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning

cheryyunl authored a paper about 2 months ago

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

cheryyunl authored a paper about 2 months ago

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

View all activity

cheryyunl

submitted a paper to Daily Papers 15 days ago

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning

Paper • 2512.16909 • Published 16 days ago • 1

cheryyunl

authored 2 papers about 2 months ago

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

Paper • 2511.01163 • Published Nov 3, 2025 • 31

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

Paper • 2511.11434 • Published Nov 14, 2025 • 44

cheryyunl

authored a paper 7 months ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published Jun 11, 2025 • 22

cheryyunl

authored a paper 11 months ago

Magma: A Foundation Model for Multimodal AI Agents

Paper • 2502.13130 • Published Feb 18, 2025 • 58

cheryyunl

authored a paper about 1 year ago

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Paper • 2412.10345 • Published Dec 13, 2024 • 2

Huazhe-Xu

authored a paper about 1 year ago

GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs

Paper • 2410.03645 • Published Oct 4, 2024 • 3

piao-0429

authored 2 papers about 1 year ago

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Paper • 2310.19668 • Published Oct 30, 2023 • 3

GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs

Paper • 2410.03645 • Published Oct 4, 2024 • 3

Huazhe-Xu

authored a paper over 1 year ago

Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning

Paper • 2407.15815 • Published Jul 22, 2024 • 14

cheryyunl

authored 4 papers over 1 year ago

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Paper • 2310.19668 • Published Oct 30, 2023 • 3

Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Paper • 2402.06187 • Published Feb 9, 2024 • 11

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Paper • 2402.12673 • Published Feb 20, 2024

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Paper • 2307.12062 • Published Jul 22, 2023

Huazhe-Xu

authored 2 papers almost 2 years ago

3D Diffusion Policy

Paper • 2403.03954 • Published Mar 6, 2024 • 13

Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Paper • 2402.06187 • Published Feb 9, 2024 • 11

Huazhe-Xu

authored a paper about 2 years ago

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Paper • 2310.20587 • Published Oct 31, 2023 • 18

Huazhe-Xu

authored 2 papers over 2 years ago

ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch

Paper • 2306.16857 • Published Jun 29, 2023 • 5

RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools

Paper • 2306.14447 • Published Jun 26, 2023 • 6

AI & ML interests

Recent Activity

Team members 7

TEA-Lab's activity