Patryk Binkowski's picture

Patryk Binkowski

ismu

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 1 day ago

upvoted a collection 1 day ago

perception-encoder-audio-visual

upvoted a collection 1 day ago

View all activity

Organizations

None yet

upvoted 3 collections 1 day ago

sam-audio

11 items • Updated 1 day ago • 52

perception-encoder-audio-visual

9 items • Updated 1 day ago • 9

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 8 days ago • 59

upvoted a paper 5 days ago

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15 • 6

upvoted a collection about 2 months ago

Ming-V2

10 items • Updated Nov 11 • 30

upvoted 2 papers 2 months ago

The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain

Paper • 2509.26507 • Published Sep 30 • 535

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6 • 497

upvoted an article 2 months ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

•

182

upvoted 3 papers 3 months ago

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published Aug 21 • 256

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26 • 184

Democratizing AI scientists using ToolUniverse

Paper • 2509.23426 • Published Sep 27 • 39

upvoted a collection 3 months ago

Qwen3-Omni

6 items • Updated Oct 9 • 174

upvoted 3 collections 4 months ago

Hunyuan-MT

4 items • Updated Nov 4 • 38

Bark

Bark is a transformer-based text-to-audio model created by Suno. Currently, two checkpoints are supported: a small and a large version. • 3 items • Updated Sep 14, 2023 • 20

Intern-S1

7 items • Updated Aug 22 • 25

upvoted a paper 4 months ago

Deep Think with Confidence

Paper • 2508.15260 • Published Aug 21 • 89

upvoted a collection 4 months ago

Wan2.2

5 items • Updated Sep 22 • 70

upvoted 2 collections 6 months ago

MultiSlav

Multilingual Machine Translation Open-Source Slavic models • 19 items • Updated Mar 7 • 9

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 7 items • Updated Oct 30 • 77

upvoted a paper 6 months ago

Kimi-VL Technical Report

Paper • 2504.07491 • Published Apr 10 • 132