🔄 In a Training Loop

MeiYi

natalie5

·

AI & ML interests

None yet

Recent Activity

liked a model about 14 hours ago

Qwen/Qwen3.8-27B

liked a model 1 day ago

Qwen/Qwen3.8-27B-FP8

liked a model 2 days ago

MiniMaxAI/MiniMax-Music3

View all activity

Organizations

None yet

upvoted a paper 8 days ago

KVAE: Family of Tokenizers for Multimodal Generative Models

Paper • 2608.05798 • Published 10 days ago • 28

upvoted a collection 11 days ago

Kandinsky WM 1.0

Image-to-Video models for Physical AI: autonomous driving, robotics, general physics. • 3 items • Updated 12 days ago • 3

upvoted a collection 13 days ago

MiniMax H3

4 items • Updated 13 days ago • 6

upvoted a paper 21 days ago

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation

Paper • 2605.30116 • Published May 28 • 4

upvoted a paper 22 days ago

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published 24 days ago • 39

upvoted a collection 29 days ago

Xiaomi-Robotics-U0

Unified embodied synthesis model that bridges foundation image generation and embodied world modeling • 2 items • Updated Jul 13 • 10

upvoted 2 papers about 1 month ago

Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget

Paper • 2607.13125 • Published 29 days ago • 139

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published Jul 8 • 64

upvoted a collection about 1 month ago

LingBot-Video

3 items • Updated Jul 8 • 24

upvoted a paper about 1 month ago

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published Apr 9 • 75

upvoted 2 collections about 1 month ago

KVAE 2.0

KVAE 2.0 is a family of image and video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16 • 3 items • Updated 9 days ago • 5

KVAE-Audio

KVAE-Audio is a continuous full-band audio waveform autoencoder • 2 items • Updated 5 days ago • 7

upvoted a collection about 2 months ago

LTX-2.3 Creative Lab

LoRAs and IC-LoRAs, trained on the LTX-2.3 model • 26 items • Updated 18 days ago • 88

upvoted a collection 2 months ago

Nex-N2

3 items • Updated Jun 11 • 27

upvoted 3 papers 2 months ago

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation

Paper • 2606.03972 • Published Jun 2 • 14

SwiftVR: Real-Time One-Step Generative Video Restoration

Paper • 2606.09516 • Published Jun 8 • 17

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 142

upvoted a collection 3 months ago

Cosmos3

Omnimodal World Models for Physical AI • 6 items • Updated 4 days ago • 185

upvoted 2 papers 3 months ago

Native Audio-Visual Alignment for Generation

Paper • 2605.30073 • Published May 28 • 35

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76