sdtana's picture

sdtana

sdtana

·

roxani_17

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

upvoted a paper 2 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

upvoted a paper 4 days ago

Transformers without Normalization

View all activity

Organizations

sdtana's activity

upvoted 2 papers 2 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 37

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published Feb 25 • 56

upvoted a paper 4 days ago

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 160

upvoted 2 papers 5 days ago

Gaussian Mixture Flow Matching Models

Paper • 2504.05304 • Published 16 days ago • 12

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Paper • 2504.10483 • Published 9 days ago • 20

upvoted a paper 8 days ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published 9 days ago • 239

upvoted a paper 9 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 13 days ago • 19

upvoted an article 17 days ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

• 233

upvoted a paper 21 days ago

Multi-Token Attention

Paper • 2504.00927 • Published 22 days ago • 45

upvoted a paper about 2 months ago

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

Paper • 2502.20172 • Published Feb 27 • 28

upvoted 2 papers 2 months ago

TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation

Paper • 2502.07870 • Published Feb 11 • 44

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Paper • 2502.04320 • Published Feb 6 • 37

upvoted 2 papers 3 months ago

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Paper • 2502.01105 • Published Feb 3 • 20

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

Paper • 2502.01639 • Published Feb 3 • 25