Leheng Li

lilelife's activity

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

upvoted a paper about 15 hours ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 1 day ago • 39

upvoted a paper 13 days ago

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Paper • 2606.26907 • Published 15 days ago • 49

upvoted a paper 24 days ago

BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering

Paper • 2606.17049 • Published 25 days ago • 27

upvoted 5 papers about 1 month ago

Mind to Hand: Purposeful Robotic Control via Embodied Reasoning

Paper • 2512.08580 • Published Dec 9, 2025 • 1

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 140

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

Paper • 2606.03748 • Published Jun 2 • 18

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Paper • 2606.03159 • Published Jun 2 • 23

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Paper • 2605.26494 • Published May 26 • 41

upvoted a paper about 2 months ago

RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

Paper • 2605.13775 • Published May 13 • 7

upvoted a paper 2 months ago

RLDX-1 Technical Report

Paper • 2605.03269 • Published May 5 • 126

upvoted 5 papers 3 months ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 168

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Paper • 2604.09132 • Published Apr 10 • 56

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published Apr 10 • 51

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 117

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 203

upvoted a paper 4 months ago

DVD: Deterministic Video Depth Estimation with Generative Priors

Paper • 2603.12250 • Published Mar 12 • 27

upvoted 2 papers 6 months ago

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization

Paper • 2601.12993 • Published Jan 19 • 77

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Paper • 2601.08303 • Published Jan 13 • 21

upvoted 2 papers 7 months ago

Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface

Paper • 2512.19402 • Published Dec 22, 2025 • 8

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Paper • 2512.17532 • Published Dec 19, 2025 • 68