Xirui Li PRO

AIcell's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 9 days ago

AIcell/Guava-4B

Image-Text-to-Text • 504k • Updated 9 days ago • 101 • 1

upvoted 2 papers 9 days ago

Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark

Paper • 2610.13947 • Published 13 days ago • 23

Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement

Paper • 2610.12369 • Published 14 days ago • 24

upvoted a paper 10 days ago

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

Paper • 2610.10409 • Published 15 days ago • 40

upvoted a paper 15 days ago

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 20 days ago • 34

upvoted 2 papers 19 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 21 days ago • 48

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 21 days ago • 112

upvoted a paper 20 days ago

4Director: Controlling Video World Models with Rigid 3D Geometry

Paper • 2610.02160 • Published 21 days ago • 39

authored a paper 21 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 24 days ago • 130

upvoted a collection 21 days ago

Guava

Collection

An effective and universal harness for embodied manipulation • 3 items • Updated 21 days ago • 1

updated a collection 21 days ago

Guava

Collection

An effective and universal harness for embodied manipulation • 3 items • Updated 21 days ago • 1

upvoted a paper 22 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 24 days ago • 130

submitted a paper to Daily Papers 22 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 24 days ago • 130

liked a model 22 days ago

lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct

Image-Text-to-Text • 9B • Updated Aug 30 • 6.97k • 16

upvoted 3 papers 29 days ago

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published Sep 18 • 138

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published about 1 month ago • 221

Transferring the Intelligence of VLMs to Robotic Control

Paper • 2609.22966 • Published Sep 19 • 90

published a model about 1 month ago

AIcell/Guava-4B

Image-Text-to-Text • 504k • Updated 9 days ago • 101 • 1

published a dataset about 1 month ago

AIcell/Guava-4B-SFT-data

Updated Sep 11 • 215