Yuhao Liu

LeoLau's activity

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

upvoted a collection 4 days ago

Emu3.5

Collection

Native Multimodal Models are World Learners 🌍 • 3 items • Updated 3 days ago • 61

New activity in manycore-research/FLUX.1-Panorama-Kontext-dev-lora 7 days ago

resolution

1

#1 opened 7 days ago by

LeoLau

liked a Space 12 days ago

Running on Zero

123

123

HunyuanWorld-Mirror

🌍

Universal 3D World Reconstruction with Any Prior Prompting

liked a model 12 days ago

tencent/HunyuanWorld-Mirror

Image-to-3D • Updated 9 days ago • 20.4k • 404

upvoted 2 papers 18 days ago

FlashWorld: High-quality 3D Scene Generation within Seconds

Paper • 2510.13678 • Published 18 days ago • 70

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published 20 days ago • 160

upvoted 2 papers about 1 month ago

DA^2: Depth Anything in Any Direction

Paper • 2509.26618 • Published Sep 30 • 25

SPATIALGEN: Layout-guided 3D Indoor Scene Generation

Paper • 2509.14981 • Published Sep 18 • 27

liked 2 models about 1 month ago

tencent/Hunyuan3D-Part

Updated 17 days ago • 2.55k • 500

tencent/Hunyuan3D-Omni

Image-to-3D • Updated 17 days ago • 1.73k • 131

published a model about 1 month ago

LeoLau/Shape-for-Motion

Video-to-Video • 0.7B • Updated Sep 25 • 2

updated a model about 1 month ago

LeoLau/Shape-for-Motion

Video-to-Video • 0.7B • Updated Sep 25 • 2

upvoted a paper about 1 month ago

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

Paper • 2509.15178 • Published Sep 18 • 6

commented a paper about 1 month ago

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

Paper • 2509.15178 • Published Sep 18 • 6 •

2

liked a model 2 months ago

tencent/HunyuanWorld-Voyager

Image-to-Video • Updated 17 days ago • 157 • 584

upvoted a paper 3 months ago

Reconstructing 4D Spatial Intelligence: A Survey

Paper • 2507.21045 • Published Jul 28 • 35

authored a paper 3 months ago

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Paper • 2507.21809 • Published Jul 29 • 131

upvoted a paper 3 months ago

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Paper • 2507.21809 • Published Jul 29 • 131

liked a model 3 months ago

tencent/HunyuanWorld-1

Image-to-3D • Updated 14 days ago • 5.99k • 586

authored a paper 3 months ago

HOComp: Interaction-Aware Human-Object Composition

Paper • 2507.16813 • Published Jul 22 • 12