Xi Yang

ianyeung's activity

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

upvoted 3 papers 4 days ago

Optimizing Few-Step Generation with Adaptive Matching Distillation

Paper • 2602.07345 • Published 17 days ago • 6

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Paper • 2602.12675 • Published 11 days ago • 49

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 10 days ago • 41

upvoted 3 papers 18 days ago

Context Forcing: Consistent Autoregressive Video Generation with Long Context

Paper • 2602.06028 • Published 18 days ago • 36

Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration

Paper • 2602.04575 • Published 19 days ago • 17

ERNIE 5.0 Technical Report

Paper • 2602.04705 • Published 19 days ago • 254

upvoted a paper 26 days ago

Advancing Open-source World Models

Paper • 2601.20540 • Published 26 days ago • 127

upvoted 2 collections about 1 month ago

HunyuanVideo-1.5

Collection

8 items • Updated Dec 7, 2025 • 6

FLUX.2

Collection

Our second generation of FLUX • 17 items • Updated Jan 18 • 129

upvoted a paper about 2 months ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published Dec 31, 2025 • 309

upvoted a collection 2 months ago

VTP

Collection

Towards Scalable Pre-training of Visual Tokenizers for Generation • 4 items • Updated 10 days ago • 42

upvoted 2 papers 2 months ago

Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets

Paper • 2512.15110 • Published Dec 17, 2025 • 10

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Paper • 2512.14614 • Published Dec 16, 2025 • 71

upvoted an article 3 months ago

view article

Article

Diffusers welcomes FLUX-2

• 
• 
• +6

Nov 25, 2025

•

179

upvoted 2 papers 3 months ago

UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

Paper • 2511.18050 • Published Nov 22, 2025 • 38

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

Paper • 2511.14993 • Published Nov 19, 2025 • 231

upvoted a collection 3 months ago

Wan2.1-Fun-V1.1

Collection

6 items • Updated Oct 9, 2025 • 9

upvoted a paper 4 months ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published Oct 30, 2025 • 125

upvoted a collection 4 months ago

Qwen3-VL

Collection

37 items • Updated Dec 31, 2025 • 636

upvoted a paper 4 months ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13, 2025 • 166