Valeriy Selitskiy's picture

Valeriy Selitskiy PRO

WaveCut

·

https://selit.ski

AI & ML interests

Looking to switch from hobby to career

Recent Activity

liked a model about 20 hours ago

Lightricks/LTX-2

liked a model 1 day ago

zai-org/GLM-Image

liked a model 1 day ago

google/medgemma-1.5-4b-it

View all activity

Organizations

upvoted 2 collections 1 day ago

Baichuan-M3

Modeling Clinical Inquiry for Reliable Medical Decision-Making • 3 items • Updated about 3 hours ago • 9

EvoCUA

EvoCUA • 2 items • Updated 2 days ago • 6

upvoted an article 3 days ago

Article

TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell

10 days ago

•

11

upvoted 3 collections 6 days ago

K-EXAONE

First journey to foundation models with frontier-level performance. • 4 items • Updated 6 days ago • 31

Qwen3-VL-Reranker

2 items • Updated 7 days ago • 32

Qwen3-VL-Embedding

2 items • Updated 7 days ago • 50

upvoted an article 7 days ago

Article

Introducing Falcon H1R 7B

10 days ago

•

57

upvoted a collection 28 days ago

FunctionGemma

3 items • Updated 28 days ago • 32

upvoted a paper 28 days ago

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Paper • 2512.15603 • Published 29 days ago • 60

upvoted 3 collections about 1 month ago

Olmo 3.1

The latest members of the Olmo 3 family: another 3 weeks of RL for 32B Think, the 32B Instruct model, large post-training research datasets... • 9 items • Updated 23 days ago • 44

Tiny-A2D

Small diffusion language models adapted from AR models • 4 items • Updated Dec 6, 2025 • 13

GLM-4.6V

3 items • Updated Dec 8, 2025 • 47

upvoted a paper about 1 month ago

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

Paper • 2511.22699 • Published Nov 27, 2025 • 226

upvoted 2 articles about 2 months ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

302

Article

Diffusers welcomes FLUX-2

+6

Nov 25, 2025

•

170

upvoted 5 collections about 2 months ago

KVAE 1.0

KVAE 1.0 tokenizers are for images (KVAE-2D-1.0) and video (KVAE-3D-1.0) are distributed under MIT license (commercial use is possible). • 2 items • Updated Dec 14, 2025 • 6

Kandinsky 5.0 Image Lite Diffusers

4 items • Updated Dec 14, 2025 • 8

GigaChat Lite

8 items • Updated Nov 19, 2025 • 2

GigaEmbeddings

1 item • Updated Nov 19, 2025 • 2

GigaChat3

6 items • Updated Dec 5, 2025 • 15