Kehan Li

lkhl's activity

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

upvoted a paper 2 days ago

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published 6 days ago • 196

upvoted 2 papers 9 days ago

RoboTTT: Context Scaling for Robot Policies

Paper • 2607.15275 • Published 10 days ago • 22

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 10 days ago • 169

upvoted 2 papers 18 days ago

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published 19 days ago • 79

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 19 days ago • 95

upvoted an article 3 months ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 173

upvoted 2 papers 3 months ago

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published Apr 17 • 60

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 248

upvoted a paper 4 months ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 236

upvoted a paper 5 months ago

RynnBrain: Open Embodied Foundation Models

Paper • 2602.14979 • Published Feb 13 • 46

upvoted a paper 6 months ago

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

Paper • 2601.22153 • Published Jan 29 • 75

upvoted 2 papers 9 months ago

PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity

Paper • 2510.23603 • Published Oct 27, 2025 • 26

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 183

upvoted 3 papers 10 months ago

High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting

Paper • 2510.10637 • Published Oct 12, 2025 • 15

MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources

Paper • 2509.21268 • Published Sep 25, 2025 • 104

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Paper • 2509.15212 • Published Sep 18, 2025 • 22

upvoted 3 papers 11 months ago

RynnEC: Bringing MLLMs into Embodied World

Paper • 2508.14160 • Published Aug 19, 2025 • 20

DINOv3

Paper • 2508.10104 • Published Aug 13, 2025 • 315

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4, 2025 • 277

upvoted an article 12 months ago

view article

Article

RynnEC: Bringing MLLMs into Embodied World

• 

Alibaba-DAMO-Academy

•

Aug 14, 2025

• 9