Zekun Qi

qizekun

14 42 65

https://qizekun.github.io/

qizekun

AI & ML interests

Embodied Intelligence, Large Langugae Model, 3D Computer Vision

Recent Activity

upvoted a paper about 9 hours ago

Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy

submitted a paper about 9 hours ago

Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy

liked a dataset 10 days ago

genrobot2025/Gen-HumanEgo

View all activity

Organizations

liked a dataset 10 days ago

genrobot2025/Gen-HumanEgo

Updated 26 days ago • 538k • 80

liked a dataset about 1 month ago

humanplus-ai/humanplus-1000

Viewer • Updated 6 days ago • 178 • 7.23k • 23

liked a model 2 months ago

zbzzbz/DeFI

Updated Mar 6 • 147 • 2

liked a dataset 2 months ago

GalaxyGeneralRobotics/HumanTracker

Viewer • Updated Aug 26 • 6k • 1.47k • 8

liked a dataset 3 months ago

BitRobot/HIW-500

Updated 22 days ago • 92.2k • 60

liked a dataset 4 months ago

CMRobot/MotionDecode

Preview • Updated 30 days ago • 131k • 89

liked a model 5 months ago

ginwind/VLA-JEPA

Updated Mar 25 • 14

liked 3 datasets 7 months ago

liked a dataset 9 months ago

ymccccc/GS-Reasoner-Data

Preview • Updated Oct 20, 2025 • 55 • 4

liked a model 9 months ago

stepfun-ai/Step3-VL-10B-Base

Image-Text-to-Text • 10B • Updated Jan 29 • 403 • 52

liked a dataset 10 months ago

DAVIAN-Robotics/PHUMA

Updated Jun 4 • 420 • 27

liked a model 10 months ago

tencent/HY-Motion-1.0

Text-to-3D • Updated Dec 31, 2025 • 505 • 444

liked a Space 12 months ago

Pi3

📈

Permutation-Equivariant Visual Geometry Learning

liked a model about 1 year ago

Qwen/Qwen3-VL-4B-Instruct

Image-Text-to-Text • 4B • Updated Oct 15, 2025 • 3.54M • • 508

liked 2 Spaces about 1 year ago

Florence 2

📉

848

Generate captions, detections, and OCR from an image

OmniPart

📚

103

Generate part-aware 3D models from a single image

liked a model about 1 year ago

allenai/GraspMolmo

Robotics • 8B • Updated May 5 • 461 • 11

liked a Space over 1 year ago

Better Florence 2

🔥

198

Analyze images to detect objects, generate captions, or perform OCR