🤝 Open to Collab

Tolga Cangöz

tolgacangoz

57 229 181

standard_ai

AI & ML interests

AIGC

Recent Activity

upvoted an article 4 days ago

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

upvoted an article 5 days ago

Security incident disclosure — July 2026

liked a model 5 days ago

Photoroom/prxpixel-t2i

View all activity

Organizations

upvoted an article 4 days ago

Article

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

nvidia

•

4 days ago

• 77

upvoted an article 5 days ago

Article

Security incident disclosure — July 2026

system

•

6 days ago

• 278

liked a model 5 days ago

Photoroom/prxpixel-t2i

Text-to-Image • 7B • Updated Jun 16 • 5.38k • 50

commented on PRX Part 4: Our Data Strategy 5 days ago

Thanks so much, Photoroom team, for sharing your experiences from PRX so far!! Learned a lot.

upvoted a paper 5 days ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published Feb 2 • 47

liked a dataset 5 days ago

yandex/alchemist

Viewer • Updated Jun 6, 2025 • 3.35k • 105 • 55

upvoted 2 papers 5 days ago

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published May 25, 2025 • 86

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Paper • 2501.04765 • Published Jan 8, 2025 • 1

upvoted a paper 6 days ago

Contrastive Flow Matching

Paper • 2506.05350 • Published Jun 5, 2025 • 1

upvoted an article 7 days ago

Article

Sensitivity Aware Mixed Precision Quantization V1

badaoui

•

Jun 13, 2025

• 27

liked 2 models 7 days ago

HiDream-ai/HiDream-O1-Image-Dev-2604

Image-Text-to-Image • 9B • Updated May 15 • 1.06k • 82

HiDream-ai/HiDream-O1-Image

Image-Text-to-Image • 9B • Updated 29 days ago • 18.3k • 509

upvoted 2 papers 10 days ago

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Paper • 2505.16792 • Published May 22, 2025 • 1

What matters for Representation Alignment: Global Information or Spatial Structure?

Paper • 2512.10794 • Published Dec 11, 2025 • 11

commented on Profiling in PyTorch (Part 3): Attention is all you profile 11 days ago

Thanks for the series, really delightful!

upvoted a paper 11 days ago

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published Apr 2 • 57

upvoted an article 11 days ago

Article

Profiling in PyTorch (Part 3): Attention is all you profile

ariG23498, sergiopaniego, sayakpaul, ror

•

12 days ago

• 36

upvoted 3 papers 13 days ago

Tolga Cangöz

AI & ML interests

Recent Activity

Organizations

tolgacangoz's activity

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

Security incident disclosure — July 2026

Sensitivity Aware Mixed Precision Quantization V1

Profiling in PyTorch (Part 3): Attention is all you profile