Xirui Li PRO

AIcell's activity

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

upvoted 2 papers 10 days ago

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

Paper • 2610.13947 • Published 14 days ago • 24

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

Paper • 2610.12369 • Published 15 days ago • 26

upvoted a paper 11 days ago

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

Paper • 2610.10409 • Published 16 days ago • 40

upvoted a paper 16 days ago

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 21 days ago • 34

upvoted 2 papers 20 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 22 days ago • 48

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 22 days ago • 112

upvoted a paper 21 days ago

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

Paper • 2610.02160 • Published 22 days ago • 39

upvoted a collection 22 days ago

Guava

Collection

An effective and universal harness for embodied manipulation • 3 items • Updated 22 days ago • 1

upvoted a paper 23 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 25 days ago • 104

upvoted 3 papers about 1 month 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 Sep 21 • 221

Transferring the Intelligence of VLMs to Robotic Control

Paper • 2609.22966 • Published Sep 19 • 70

upvoted 4 papers about 2 months ago

Code World Model: Coding Agent as World Brain

Paper • 2608.25927 • Published Aug 26 • 41

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published Aug 27 • 75

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Paper • 2608.27549 • Published Aug 27 • 48

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

Paper • 2608.24680 • Published Aug 25 • 11

upvoted 4 papers 2 months ago

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published Aug 17 • 154

aDSL: Agentic 3D Creation via Joint Agent-Program Design

Paper • 2608.17975 • Published Aug 18 • 7

TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation

Paper • 2608.16765 • Published Aug 17 • 14

MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

Paper • 2608.14783 • Published Aug 14 • 20