Xiangpeng Yang PRO

XiangpengYang

4 30 7

https://xiangpengyang.github.io/

AI & ML interests

diffusion models, video generaiton, video editing

Recent Activity

upvoted a paper 1 day ago

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

upvoted a paper 4 days ago

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

upvoted a paper 23 days ago

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

View all activity

Organizations

upvoted a paper 1 day ago

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

Paper • 2607.02508 • Published 3 days ago • 10

upvoted a paper 4 days ago

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Paper • 2606.26740 • Published 10 days ago • 80

upvoted a paper 23 days ago

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

Paper • 2606.07436 • Published 29 days ago • 25

upvoted a paper about 1 month ago

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Paper • 2605.12496 • Published May 12 • 30

upvoted 2 papers about 2 months ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published May 14 • 91

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published May 13 • 105

authored a paper about 2 months ago

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published May 6 • 28

upvoted 2 papers about 2 months ago

Lightning Unified Video Editing via In-Context Sparse Attention

Paper • 2605.04569 • Published May 6 • 18

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published May 6 • 28

upvoted 2 papers 3 months ago

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Paper • 2604.15311 • Published Apr 16 • 14

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

Paper • 2604.11804 • Published Apr 13 • 72

upvoted a paper 4 months ago

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Paper • 2602.24289 • Published Feb 27 • 41

upvoted 2 papers 6 months ago

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

Paper • 2601.02204 • Published Jan 5 • 64

SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time

Paper • 2512.25075 • Published Dec 31, 2025 • 16

liked a dataset 6 months ago

XiangpengYang/VideoCoF-50k

Viewer • Updated Jan 2 • 49.2k • 151 • 8

updated a dataset 6 months ago

XiangpengYang/VideoCoF-50k

Viewer • Updated Jan 2 • 49.2k • 151 • 8

upvoted a paper 6 months ago

Pretraining Frame Preservation in Autoregressive Video Memory Compression

Paper • 2512.23851 • Published Dec 29, 2025 • 25

published a dataset 6 months ago

XiangpengYang/VideoCoF-50k

Viewer • Updated Jan 2 • 49.2k • 151 • 8

liked a dataset 6 months ago

Lewandofski/OpenVE-3M

Viewer • Updated Jan 26 • 4.52M • 3.1k • 94

replied to their post 7 months ago

Thanks! I really love your phrasing of 'refusing to hallucinate success' — that's exactly the mindset we aimed for. Glad the philosophy resonates!

Xiangpeng Yang PRO

AI & ML interests

Recent Activity

Organizations

XiangpengYang's activity