4 54 20

sdtana

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

Parallelized Autoregressive Visual Generation

upvoted a paper 3 days ago

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

upvoted a paper 16 days ago

APOLLO: SGD-like Memory, AdamW-level Performance

View all activity

Organizations

None yet

sdtana's activity

upvoted a paper 2 days ago

Parallelized Autoregressive Visual Generation

Paper • 2412.15119 • Published 6 days ago • 46

upvoted a paper 3 days ago

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

Paper • 2412.16112 • Published 6 days ago • 17

upvoted 2 papers 16 days ago

APOLLO: SGD-like Memory, AdamW-level Performance

Paper • 2412.05270 • Published 19 days ago • 38

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Paper • 2412.05271 • Published 19 days ago • 121

upvoted a paper 20 days ago

Negative Token Merging: Image-based Adversarial Feature Guidance

Paper • 2412.01339 • Published 24 days ago • 21

upvoted 3 papers 28 days ago

Adaptive Blind All-in-One Image Restoration

Paper • 2411.18412 • Published 29 days ago • 4

ROICtrl: Boosting Instance Control for Visual Generation

Paper • 2411.17949 • Published 29 days ago • 82

Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis

Paper • 2411.17769 • Published 30 days ago • 7

upvoted a paper about 1 month ago

Style-Friendly SNR Sampler for Style-Driven Generation

Paper • 2411.14793 • Published Nov 22 • 36

upvoted a paper about 2 months ago

SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Paper • 2411.05007 • Published Nov 7 • 16

upvoted 2 papers 3 months ago

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Paper • 2409.11355 • Published Sep 17 • 28

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17 • 108

upvoted 2 papers 4 months ago

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Paper • 2409.04410 • Published Sep 6 • 23

FLUX that Plays Music

Paper • 2409.00587 • Published Sep 1 • 31

upvoted a paper 5 months ago

Efficient Training with Denoised Neural Weights

Paper • 2407.11966 • Published Jul 16 • 8

upvoted 4 papers 6 months ago

Vision language models are blind

Paper • 2407.06581 • Published Jul 9 • 82

Dataset Size Recovery from LoRA Weights

Paper • 2406.19395 • Published Jun 27 • 18

Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering

Paper • 2406.10208 • Published Jun 14 • 21

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Paper • 2406.09415 • Published Jun 13 • 50

upvoted an article 7 months ago

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

•

Jun 11

• 49