wangshuai

wangsssssss's activity

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

upvoted 2 papers 1 day ago

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Paper • 2512.08153 • Published 3 days ago • 4

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Paper • 2512.08765 • Published 2 days ago • 108

upvoted a paper 2 days ago

LongCat-Image Technical Report

Paper • 2512.07584 • Published 3 days ago • 16

upvoted a paper 3 days ago

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published 8 days ago • 64

upvoted a paper 5 days ago

Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Paper • 2512.04926 • Published 7 days ago • 40

upvoted 2 papers 7 days ago

PixelDiT: Pixel Diffusion Transformers for Image Generation

Paper • 2511.20645 • Published 16 days ago • 26

RELIC: Interactive Video World Model with Long-Horizon Memory

Paper • 2512.04040 • Published 8 days ago • 23

upvoted 4 papers 8 days ago

Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions

Paper • 2511.06876 • Published Nov 10 • 26

Adversarial Flow Models

Paper • 2511.22475 • Published 14 days ago • 21

Vision Bridge Transformer at Scale

Paper • 2511.23199 • Published 13 days ago • 43

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 9 days ago • 199

upvoted a paper 10 days ago

Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment

Paper • 2511.22345 • Published 14 days ago • 12

upvoted a paper 16 days ago

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

Paper • 2511.19365 • Published 17 days ago • 63

upvoted 2 papers 21 days ago

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Paper • 2511.15065 • Published 22 days ago • 74

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

Paper • 2511.14993 • Published 23 days ago • 222

upvoted a paper 23 days ago

Back to Basics: Let Denoising Generative Models Denoise

Paper • 2511.13720 • Published 24 days ago • 65

upvoted 4 papers about 1 month ago

UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

Paper • 2511.03334 • Published Nov 5 • 51

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30 • 107

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published Oct 30 • 117

The Principles of Diffusion Models

Paper • 2510.21890 • Published Oct 24 • 59