MeiYi's picture

MeiYi

natalie5

·

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

microsoft/TRELLIS.2-4B

liked a model 1 day ago

animetimm/convnextv2_huge.dbv4-full

liked a model 1 day ago

Ex0bit/MiniMax-M2.1-PRISM

View all activity

Organizations

None yet

upvoted a paper 3 days ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 4 days ago • 176

upvoted a paper 10 days ago

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

Paper • 2512.21338 • Published 11 days ago • 20

upvoted a paper 12 days ago

SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published 12 days ago • 88

upvoted a collection 12 days ago

NextStep-1

9 items • Updated 12 days ago • 31

upvoted a paper 16 days ago

Speedrunning ImageNet Diffusion

Paper • 2512.12386 • Published 22 days ago • 3

upvoted a collection 18 days ago

SiD-DiT

Collection of Distilled Flow Matching Models with Score Identity Distillation • 17 items • Updated Nov 29, 2025 • 1

upvoted a paper 18 days ago

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

Paper • 2512.14614 • Published 19 days ago • 67

upvoted a collection 19 days ago

Chatterbox Turbo

Ultra-Fast, Open-Source Text-to-Speech for Real-Time Voice AI • 3 items • Updated 20 days ago • 14

upvoted a collection 20 days ago

Edit-R1

5 items • Updated Oct 21, 2025 • 8

upvoted a paper 22 days ago

Distribution Matching Variational AutoEncoder

Paper • 2512.07778 • Published 27 days ago • 28

upvoted a paper 26 days ago

LongCat-Image Technical Report

Paper • 2512.07584 • Published 27 days ago • 18

upvoted a paper 27 days ago

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published Dec 3, 2025 • 74

upvoted 2 collections about 1 month ago

Video Foundation Models

A list of all the (usable) video generation diffusion models. Models that are not upto current standards are skipped. • 10 items • Updated Dec 3, 2025 • 1

Ovis-Image

Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering under stringent computational constraints. • 7 items • Updated Dec 4, 2025 • 6

upvoted 4 papers about 1 month ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published Nov 27, 2025 • 221

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 244

Glance: Accelerating Diffusion Models with 1 Sample

Paper • 2512.02899 • Published Dec 2, 2025 • 29

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published Nov 25, 2025 • 47

upvoted a collection about 1 month ago

Z-Image

4 items • Updated Dec 1, 2025 • 97

upvoted a paper about 1 month ago

Video Generation Models Are Good Latent Reward Models

Paper • 2511.21541 • Published Nov 26, 2025 • 45