Xi Yang's picture

Xi Yang

ianyeung

·

IanYeung

AI & ML interests

None yet

Recent Activity

liked a model about 5 hours ago

baidu/ERNIE-4.5-VL-424B-A47B-Base-PT

liked a model about 13 hours ago

stepfun-ai/Step-3.5-Flash

liked a model 4 days ago

meituan-longcat/LongCat-Image-Edit

View all activity

Organizations

None yet

upvoted a paper 5 days ago

Advancing Open-source World Models

Paper • 2601.20540 • Published 5 days ago • 104

upvoted a collection 14 days ago

HunyuanVideo-1.5

8 items • Updated Dec 7, 2025 • 6

upvoted a collection 18 days ago

FLUX.2

Our second generation of FLUX • 17 items • Updated 15 days ago • 119

upvoted a paper 30 days ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published Dec 31, 2025 • 292

upvoted a collection about 2 months ago

VTP

Towards Scalable Pre-training of Visual Tokenizers for Generation • 4 items • Updated Dec 16, 2025 • 42

upvoted 2 papers about 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 2 months ago

Article

Diffusers welcomes FLUX-2

+6

Nov 25, 2025

•

177

upvoted 2 papers 2 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

6 items • Updated Oct 9, 2025 • 9

upvoted a paper 3 months ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published Oct 30, 2025 • 121

upvoted a collection 4 months ago

Qwen3-VL

37 items • Updated Dec 31, 2025 • 618

upvoted a paper 4 months ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13, 2025 • 166

upvoted a collection 5 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 474

upvoted 4 papers 5 months ago

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Paper • 2509.09676 • Published Sep 11, 2025 • 33

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published Sep 10, 2025 • 190

CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

Paper • 2508.15774 • Published Aug 21, 2025 • 20

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 212

upvoted a paper 6 months ago

Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

Paper • 2508.12945 • Published Aug 18, 2025 • 14