JIANYI WANG's picture

In a Training Loop 🔄

JIANYI WANG

Iceclear

·

https://iceclear.github.io

AI & ML interests

Low-level vision

Recent Activity

upvoted a paper about 24 hours ago

FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation

upvoted a paper 9 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

upvoted a paper 10 days ago

Region-Constraint In-Context Generation for Instructional Video Editing

View all activity

Organizations

upvoted a paper about 24 hours ago

FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation

Paper • 2512.24724 • Published 3 days ago • 2

upvoted a paper 9 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 17 days ago • 90

upvoted a paper 10 days ago

Region-Constraint In-Context Generation for Instructional Video Editing

Paper • 2512.17650 • Published 15 days ago • 49

upvoted a paper 16 days ago

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Paper • 2512.15603 • Published 17 days ago • 58

upvoted a collection 16 days ago

Pixio

5 items • Updated 16 days ago • 11

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, 2025 • 227

upvoted 2 papers about 2 months ago

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Paper • 2511.10629 • Published Nov 13, 2025 • 123

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

Paper • 2511.09057 • Published Nov 12, 2025 • 76

upvoted a collection 5 months ago

DeepSeek-V3.1

4 items • Updated Nov 27, 2025 • 257

upvoted a paper 5 months ago

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Paper • 2508.10711 • Published Aug 14, 2025 • 145

upvoted a paper 6 months ago

MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization

Paper • 2507.14683 • Published Jul 19, 2025 • 134

upvoted a collection 6 months ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated 3 days ago • 549

upvoted 2 papers 6 months ago

Scaling RL to Long Videos

Paper • 2507.07966 • Published Jul 10, 2025 • 159

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Paper • 2506.18898 • Published Jun 23, 2025 • 33

upvoted a collection 7 months ago

🍉 June 2025 - Open works from the Chinese community

29 items • Updated Nov 20, 2025 • 7

upvoted an article 7 months ago

Article

Learn the Hugging Face Kernel Hub in 5 Minutes

+5

Jun 12, 2025

•

151

upvoted a paper 7 months ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Paper • 2506.09350 • Published Jun 11, 2025 • 48

upvoted a collection 7 months ago

SeedVR

A diffusion transformer model for high-resolution image and video restoration. • 9 items • Updated Aug 19, 2025 • 9

upvoted a paper 7 months ago

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published Jun 5, 2025 • 58

upvoted a collection 7 months ago

Deepseek Papers

Deepseek papers collection • 28 items • Updated 2 days ago • 295