45 278 2247

Shawn Saw

PlayAI

AI & ML interests

generative animation, generative 3d models,

Recent Activity

upvoted a paper about 1 hour ago

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

commented on a paper about 1 hour ago

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

new activity about 1 hour ago

ostris/zimage_turbo_training_adapter:Does Z-Image support embedding/textual-inversion–style adapters? If not, why?

View all activity

Organizations

upvoted a paper about 1 hour ago

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

Paper • 2511.22699 • Published 9 days ago • 145

upvoted an article 1 day ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

6 days ago

•

223

upvoted a paper 1 day ago

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Paper • 2511.21691 • Published 10 days ago • 32

upvoted a collection 3 days ago

Ministral 3

Collection

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 4 days ago • 111

upvoted 5 papers 7 days ago

A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space

Paper • 2511.10555 • Published 23 days ago • 60

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Paper • 2511.15065 • Published 18 days ago • 74

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published 12 days ago • 26

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Paper • 2511.19399 • Published 12 days ago • 54

ROOT: Robust Orthogonalized Optimizer for Neural Network Training

Paper • 2511.20626 • Published 11 days ago • 169

upvoted a collection 13 days ago

DR Tulu

Collection

Models and data associated with DR Tulu, http://allenai-web/papers/drtulu • 5 items • Updated 11 days ago • 30

upvoted a paper 16 days ago

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

Paper • 2511.14993 • Published 18 days ago • 222

upvoted 3 articles 16 days ago

Article

Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models

17 days ago

•

Article

Why Did MiniMax M2 End Up as a Full Attention Model?

Oct 30

•

Article

Norm-Preserving Biprojected Abliteration

30 days ago

•

upvoted 6 articles 19 days ago

Article

Qwen Image Models Realism is Now Next Level & Tutorial for Object Removal, Inpainting & Outpainting

21 days ago

•

Article

AI Model Optimization More Flexible Than Ever

19 days ago

•

Article

📐 Muon Optimizer: The Power of Collective Momentum

23 days ago

•

Article

Effective Prompting for Generative Vision Models

26 days ago

•

Article

Granite 4.0 Nano: Just how small can you go?

Oct 28

•

120

Article

Projected Abliteration

Oct 25

•

Shawn Saw

AI & ML interests

Recent Activity

Organizations

PlayAI's activity

Transformers v5: Simple model definitions powering the AI ecosystem

Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models

Why Did MiniMax M2 End Up as a Full Attention Model?

Norm-Preserving Biprojected Abliteration

Qwen Image Models Realism is Now Next Level & Tutorial for Object Removal, Inpainting & Outpainting

AI Model Optimization More Flexible Than Ever

📐 Muon Optimizer: The Power of Collective Momentum

Effective Prompting for Generative Vision Models

Granite 4.0 Nano: Just how small can you go?

Projected Abliteration