Valeriy Selitskiy's picture

Open to Work

Valeriy Selitskiy PRO

WaveCut

·

AI & ML interests

Looking to switch from hobby to career

Recent Activity

liked a model 28 minutes ago

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

liked a model about 1 hour ago

FireRedTeam/FireRed-OCR

liked a Space about 6 hours ago

victor/dlss-5-anything

View all activity

Organizations

upvoted a collection 1 day ago

TranslateGemma

3 items • Updated 7 days ago • 222

upvoted 2 collections 3 days ago

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 3 days ago • 54

Helios

Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 4 days ago • 22

upvoted a collection 8 days ago

MiroThinker-1.7

2 items • Updated 8 days ago • 49

upvoted an article 9 days ago

Article

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

9 days ago

•

38

upvoted a collection 15 days ago

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled

18 items • Updated 9 days ago • 91

upvoted 2 collections 16 days ago

IQuest-Coder

14 items • Updated 16 days ago • 106

Jan-code

2 items • Updated 17 days ago • 19

upvoted a collection 17 days ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 8 days ago • 115

upvoted a collection 18 days ago

Quantized Qwen3.5

Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 9 items • Updated 7 days ago • 9

upvoted a paper 23 days ago

The Free Transformer

Paper • 2510.17558 • Published Oct 20, 2025 • 6

upvoted 2 collections 23 days ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 28 items • Updated 5 days ago • 146

ParoQuant

Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 16 items • Updated 5 days ago • 14

upvoted 6 collections about 1 month ago

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated about 1 month ago • 64

BitDance

BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model. • 10 items • Updated 17 days ago • 11

Nanbeige4.1-3B

4 items • Updated Feb 16 • 3

Qwen3.5

21 items • Updated 10 days ago • 1.24k

NextStep-1

10 items • Updated 17 days ago • 34

Intern-S1

9 items • Updated Feb 14 • 30

upvoted a paper about 1 month ago

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published Feb 9 • 70