Kehan Li

lkhl's activity

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

upvoted a paper about 1 month ago

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

Paper • 2510.23603 • Published Oct 27 • 22

upvoted 2 papers about 2 months ago

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

Paper • 2510.11696 • Published Oct 13 • 176

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

Paper • 2510.10637 • Published Oct 12 • 12

upvoted a paper 3 months ago

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

Paper • 2509.21268 • Published Sep 25 • 103

updated a Space 3 months ago

Runtime error

7

RynnEC

👁

7

Generate masks and answers for video frames

updated a model 3 months ago

lkhl/VideoLLaMA3-7B-Image-HF

Any-to-Any • 8B • Updated Sep 20 • 12

published a model 3 months ago

lkhl/VideoLLaMA3-7B-Image-HF

Any-to-Any • 8B • Updated Sep 20 • 12

liked 2 datasets 3 months ago

mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M

Viewer • Updated 17 days ago • 91.5M • 214k • 48

mvp-lab/LLaVA-OneVision-1.5-Instruct-Data

Viewer • Updated 20 days ago • 21.9M • 78.9k • 54

upvoted a paper 3 months ago

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Paper • 2509.15212 • Published Sep 18 • 21

updated a model 3 months ago

lkhl/VideoLLaMA3-2B-Image-HF

Any-to-Any • 2B • Updated Sep 16 • 1.56k

liked 2 models 3 months ago

nvidia/audio-flamingo-3-chat

Updated Jul 14 • 130 • 43

openbmb/MiniCPM-V-4_5

Image-Text-to-Text • 9B • Updated Oct 10 • 50.7k • 1.02k

published a model 4 months ago

lkhl/VideoLLaMA3-2B-Image-HF

Any-to-Any • 2B • Updated Sep 16 • 1.56k

liked a model 4 months ago

DAMO-NLP-SG/VideoLLaMA3-2B-Image

Visual Question Answering • 2B • Updated Mar 20 • 219 • 8

upvoted 3 papers 4 months ago

RynnEC: Bringing MLLMs into Embodied World

Paper • 2508.14160 • Published Aug 19 • 19

DINOv3

Paper • 2508.10104 • Published Aug 13 • 285

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4 • 264

upvoted an article 4 months ago

view article

Article

RynnEC: Bringing MLLMs into Embodied World

• 

Aug 14

•

7

published an article 4 months ago

view article

Article

RynnEC: Bringing MLLMs into Embodied World

• 

Aug 14

•

7