Kairun Wen

kairunwen

7 28 89

https://kairunwen.github.io/

AI & ML interests

Computer Vision、Machine Learning

Recent Activity

upvoted a paper 24 days ago

InterleaveThinker: Reinforcing Agentic Interleaved Generation

updated a dataset about 1 month ago

kairunwen/d4

upvoted a paper about 2 months ago

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

View all activity

Organizations

liked 2 Spaces 2 months ago

AllTracker

⚡

Track and visualize points in a video

Depth Anything 3

🏢

430

Generate depth maps from your photos

liked a dataset 3 months ago

InternRobotics/SynthVerse

Viewer • Updated May 27 • 1.22k • 10k • 14

liked 2 datasets 4 months ago

LouisChen15/ConstructionSite

Viewer • Updated May 11 • 10k • 569 • 53

yu2hi13/Dyn-Bench

Viewer • Updated Mar 10 • 10k • 39 • 3

liked a model 6 months ago

InternRobotics/InternVLA-A1-3B

Robotics • 3B • Updated Feb 27 • 114 • 40

liked a dataset 6 months ago

lifuguan/IGGT_Benchmark

Viewer • Updated Nov 17, 2025 • 662 • 197 • 2

liked a dataset 7 months ago

InternRobotics/OmniWorld

Viewer • Updated Apr 17 • 7.09B • 37.4k • 95

liked a Space 8 months ago

QR Code AI Art Generator

📱

1.99k

QR Code AI Art Generator Blend QR codes with AI Art

liked a dataset 8 months ago

kairunwen/InstantSplat

Viewer • Updated Dec 30, 2024 • 2.15k • 62 • 5

liked a model 8 months ago

facebook/map-anything

Image-to-3D • 1B • Updated Jan 20 • 29.8k • 90

liked a dataset 8 months ago

InternRobotics/InternData-N1

Updated Feb 6 • 58.8k • 80

liked a Space 9 months ago

Qwen3 VL Demo

😻

112

Chat with a multimodal AI using text and images

liked a dataset 9 months ago

nvidia/vipe-dynpose-100kpp

Viewer • Updated Sep 1, 2025 • 99.5k • 979 • 8

liked a Space 10 months ago

Mapanything Gradio

🐠

123

Convert images to 3D models and depth maps

liked a model 10 months ago

lhjiang/anysplat

Image-to-3D • Updated Sep 17, 2025 • 7.53k • 13

liked 2 Spaces 10 months ago

ReconViaGen

🖥

178

High-fidelity 3D Geometry Generation from multi-view images

Grounding DINO Demo

💻

123

Cutting edge open-vocabulary object detection app

liked 2 Spaces 12 months ago

StreamVGGT

🔥

Create 3D reconstructions from images or videos

Pi3

📈

Permutation-Equivariant Visual Geometry Learning