Liu Songhua

Huage001's activity

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

upvoted 5 papers about 12 hours ago

Streaming Video Instruction Tuning

Paper • 2512.21334 • Published 4 days ago • 7

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Paper • 2512.21004 • Published 4 days ago • 11

Region-Constraint In-Context Generation for Instructional Video Editing

Paper • 2512.17650 • Published 9 days ago • 48

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 10 days ago • 74

SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published 5 days ago • 87

upvoted a paper 5 days ago

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

Paper • 2512.19678 • Published 6 days ago • 26

upvoted a paper 9 days ago

DeContext as Defense: Safe Image Editing in Diffusion Transformers

Paper • 2512.16625 • Published 10 days ago • 24

upvoted 2 papers 23 days ago

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Paper • 2512.02589 • Published 26 days ago • 63

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Paper • 2512.04677 • Published 24 days ago • 168

authored a paper 27 days ago

Vision Bridge Transformer at Scale

Paper • 2511.23199 • Published 30 days ago • 44

upvoted a paper 27 days ago

Vision Bridge Transformer at Scale

Paper • 2511.23199 • Published 30 days ago • 44

upvoted a paper about 1 month ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19 • 226

upvoted 2 papers 3 months ago

Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

Paper • 2509.25161 • Published Sep 29 • 25

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

Paper • 2509.19244 • Published Sep 23 • 11

upvoted 6 papers 4 months ago

From Editor to Dense Geometry Estimator

Paper • 2509.04338 • Published Sep 4 • 92

Autoregressive Universal Video Segmentation Model

Paper • 2508.19242 • Published Aug 26 • 28

MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

Paper • 2508.19320 • Published Aug 26 • 29

Mixture of Contexts for Long Video Generation

Paper • 2508.21058 • Published Aug 28 • 35

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

Paper • 2508.18966 • Published Aug 26 • 56

Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

Paper • 2508.17437 • Published Aug 20 • 38