Mingwei Li

Longxiang-ai's activity

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

New activity in Longxiang-ai/TransNormal-2 20 days ago

Add pipeline tag to metadata

#1 opened 20 days ago by

nielsr

upvoted a paper 21 days ago

TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation

Paper • 2609.06665 • Published 24 days ago • 19

submitted a paper to Daily Papers 21 days ago

TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation

Paper • 2609.06665 • Published 24 days ago • 19

liked a model 21 days ago

Longxiang-ai/TransNormal-2

Image-to-Image • Updated 20 days ago • 96 • • 3

published a model 21 days ago

Longxiang-ai/TransNormal-2

Image-to-Image • Updated 20 days ago • 96 • • 3

updated a model 21 days ago

Longxiang-ai/TransNormal-2

Image-to-Image • Updated 20 days ago • 96 • • 3

liked 4 models about 2 months ago

Remade-AI/Pixar

Text-to-Video • Updated Mar 24, 2025 • 160 • • 14

Inner-Reflections/MiniMax-H3-Looping-Sketch-Anime

Updated Aug 11 • 77

fal/MiniMax-H3-Realism-People-LoRA

Image-Text-to-Video • Updated Aug 12 • 73k • • 437

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 3.63M • • 5.77k

authored 4 papers 2 months ago

TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors

Paper • 2504.12799 • Published Aug 3, 2025 • 1

TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Paper • 2602.00839 • Published Jan 31 • 3

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Paper • 2511.19268 • Published Nov 24, 2025 • 3

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Paper • 2312.15258 • Published Dec 23, 2023 • 13

liked a model 2 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 28 days ago • 1.36M • • 11.5k

upvoted 2 papers 2 months ago

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Paper • 2312.15258 • Published Dec 23, 2023 • 13

TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Paper • 2602.00839 • Published Jan 31 • 3

liked a dataset 3 months ago

FudanCVL/EffectErase

Viewer • Updated Jun 27 • 797k • 533 • 22

upvoted 2 papers 4 months ago

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

Paper • 2606.12303 • Published Jun 10 • 33

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

Paper • 2606.12243 • Published Jun 10 • 37