Xirui Li PRO

AIcell's activity

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

upvoted a paper about 14 hours ago

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 5 days ago • 24

upvoted 2 papers 4 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 6 days ago • 45

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 6 days ago • 102

upvoted a paper 5 days ago

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

Paper • 2610.02160 • Published 6 days ago • 38

upvoted a collection 7 days ago

Guava

Collection

An effective and universal harness for embodied manipulation • 3 items • Updated 7 days ago • 1

upvoted a paper 7 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 9 days ago • 138

upvoted 3 papers 15 days ago

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 19 days ago • 138

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 16 days ago • 223

Transferring the Intelligence of VLMs to Robotic Control

Paper • 2609.22966 • Published 18 days ago • 120

upvoted 5 papers about 1 month ago

Code World Model: Coding Agent as World Brain

Paper • 2608.25927 • Published Aug 26 • 40

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

Paper • 2608.27260 • Published Aug 27 • 74

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

Paper • 2608.27549 • Published Aug 27 • 49

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

Paper • 2608.24680 • Published Aug 25 • 11

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

Paper • 2608.16590 • Published Aug 17 • 153

upvoted 6 papers about 2 months ago

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

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published Jul 31 • 118

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

Paper • 2608.15265 • Published Aug 15 • 61

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published Aug 13 • 64