snowflakewang

SnowflakeWang's activity

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

upvoted 2 papers 6 days ago

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Paper • 2509.22647 • Published 8 days ago • 30

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published 8 days ago • 167

upvoted 2 papers 9 days ago

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Paper • 2509.21245 • Published 9 days ago • 36

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published 10 days ago • 91

upvoted 3 papers 11 days ago

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Paper • 2509.18154 • Published 18 days ago • 46

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Paper • 2509.19296 • Published 11 days ago • 21

VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

Paper • 2509.17985 • Published 12 days ago • 25

upvoted a paper 12 days ago

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

Paper • 2509.17627 • Published 12 days ago • 63

New activity in lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v 15 days ago

Can I use the framework to distill a bidirectional HunyuanVideo(-I2V) model?

#4 opened 15 days ago by

SnowflakeWang

New activity in lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill 16 days ago

Can I use the framework to distill a bidirectional HunyuanVideo(-I2V) model?

#13 opened 16 days ago by

SnowflakeWang

upvoted a paper 18 days ago

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

Paper • 2509.12815 • Published 18 days ago • 38

upvoted a paper 19 days ago

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published 19 days ago • 103

upvoted 2 papers 21 days ago

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Paper • 2509.09595 • Published 23 days ago • 47

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Paper • 2509.08519 • Published 24 days ago • 124

upvoted 3 papers 29 days ago

Towards a Unified View of Large Language Model Post-Training

Paper • 2509.04419 • Published 30 days ago • 73

From Editor to Dense Geometry Estimator

Paper • 2509.04338 • Published about 1 month ago • 91

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

Paper • 2509.04406 • Published about 1 month ago • 11

upvoted a paper about 1 month ago

Kwai Keye-VL 1.5 Technical Report

Paper • 2509.01563 • Published Sep 1 • 36

upvoted 2 papers about 2 months ago

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Paper • 2508.13009 • Published Aug 18 • 24

VertexRegen: Mesh Generation with Continuous Level of Detail

Paper • 2508.09062 • Published Aug 12 • 36