Kang Liao PRO

KangLiao's activity

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

liked a dataset 9 days ago

stanford-vision-lab/gpic

Updated 16 days ago • 196k • 140

upvoted a paper 12 days ago

Direct 3D-Aware Object Insertion via Decomposed Visual Proxies

Paper • 2606.06601 • Published 17 days ago • 26

upvoted a paper about 1 month ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 193

liked 2 datasets 3 months ago

nvidia/dynpose-100k

Updated May 12, 2025 • 329 • 57

quchenyuan/360x_dataset_HR

Updated Jan 6, 2025 • 2.26k • 8

upvoted a paper 3 months ago

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published Mar 3 • 145

authored a paper 3 months ago

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published Mar 3 • 145

updated a model 4 months ago

KangLiao/Puffin

Text-to-3D • Updated Mar 6 • 24

liked a model 4 months ago

DravenALG/VLANeXt

Robotics • Updated Apr 21 • 5

upvoted a paper 4 months ago

VLANeXt: Recipes for Building Strong VLA Models

Paper • 2602.18532 • Published Feb 20 • 52

updated a dataset 5 months ago

KangLiao/Puffin-4M

Viewer • Updated Jan 10 • 3.19B • 4.17k • 35

upvoted a paper 6 months ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published Dec 22, 2025 • 68

liked 2 Spaces 6 months ago

Runtime error

Agents

69

Wan 2 2 First Last Frame

💻

69

Generate a video by interpolating between two images with a text prompt

Running on Zero

Agents

472

vggt

🏆

472

VGGT (CVPR 2025)

liked 2 datasets 7 months ago

kwhuang/C3

Viewer • Updated Jan 5 • 89.7k • 131 • 5

nvidia/vipe-wild-sdg-1m

Viewer • Updated Sep 1, 2025 • 966k • 2.11k • 7