Nikolay Kozlov's picture

Nikolay Kozlov

NikolayKozloff

·

AI & ML interests

None yet

Recent Activity

liked a model about 8 hours ago

Tongyi-MAI/MAI-UI-8B

liked a model about 8 hours ago

skt/A.X-K1

liked a model about 8 hours ago

DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning

View all activity

Organizations

upvoted a paper about 8 hours ago

Scaling Open-Ended Reasoning to Predict the Future

Paper • 2512.25070 • Published 1 day ago • 11

upvoted 2 collections 2 days ago

HyperCLOVA X SEED

HyperCLOVA X SEED is NAVER's lightweight open-source lineup with a strong focus on Korean language performance • 6 items • Updated 8 days ago • 37

HY-MT1.5

混元翻译模型1.5版本 • 8 items • Updated 1 day ago • 23

upvoted a collection 7 days ago

Openhands Trajectories

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated 9 days ago • 6

upvoted a collection 8 days ago

Plano-Orchestrator

8 items • Updated 9 days ago • 4

upvoted an article 12 days ago

Article

Best Practices for Open Multilingual LLM Evaluation

May 7, 2025

•

5

upvoted 2 collections 14 days ago

FunctionGemma

3 items • Updated 14 days ago • 29

T5Gemma 2

3 items • Updated 14 days ago • 56

upvoted a collection 15 days ago

Bolmo

Artifacts for the Bolmo release: https://allenai.org/papers/bolmo. • 4 items • Updated 9 days ago • 12

upvoted a collection 16 days ago

GLM-V

4 items • Updated 15 days ago • 11

upvoted a paper 22 days ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Paper • 2512.07461 • Published 24 days ago • 74

upvoted a collection 23 days ago

Magic Quant

Hybrid GGUF quants created via an evolutionary quant algorithm. Want the best TPS? Lowest precision loss? Smallest file size? Welcome to MagicQuant! • 8 items • Updated 16 days ago • 22

upvoted an article 24 days ago

Article

We Got Claude to Fine-Tune an Open Source LLM

29 days ago

•

552

upvoted 6 collections about 1 month ago

Step-Audio-R1

Step-Audio-R1 is the first audio language model to successfully unlock test-time compute scaling. • 3 items • Updated Nov 21, 2025 • 15

Kandinsky 5.0 Image Lite

Kandinsky 5.0 Image Lite is a 6B DiT-based model that generates and edits HD images from English and Russian text prompts with high visual quality. • 4 items • Updated 19 days ago • 15

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 19 days ago • 6

Kandinsky 5.0 Image Lite Diffusers

4 items • Updated 19 days ago • 8

Kandinsky 5.0 Video Lite

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 9 items • Updated 19 days ago • 12

Kandinsky 5.0

9 items • Updated Nov 7, 2025 • 31

upvoted a paper about 1 month ago

NVIDIA Nemotron Parse 1.1

Paper • 2511.20478 • Published Nov 25, 2025 • 21