Patryk Binkowski

ismu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 13 days ago

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Paper • 2602.02361 • Published 26 days ago • 60

upvoted a collection 22 days ago

NVFP4 Models

Collection

17 items • Updated 10 days ago • 15

upvoted 2 collections about 1 month ago

TorchAO Quantized gemma-3-it

Collection

8 items • Updated Jan 13 • 3

TranslateGemma

Collection

3 items • Updated Jan 15 • 215

upvoted 3 collections 2 months ago

sam-audio

Collection

11 items • Updated Dec 16, 2025 • 128

perception-encoder-audio-visual

Collection

9 items • Updated Dec 16, 2025 • 25

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 3 days ago • 123

upvoted a paper 3 months ago

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

Paper • 2510.13999 • Published Oct 15, 2025 • 14

upvoted a collection 4 months ago

Ming-V2

Collection

Ming is the multi-modal series of any-to-any models developed by Ant Ling team. • 14 items • Updated 14 days ago • 35

upvoted 2 papers 4 months ago

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

Paper • 2509.26507 • Published Sep 30, 2025 • 547

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6, 2025 • 509

upvoted an article 4 months ago

view article

Article

🪆 Introduction to Matryoshka Embedding Models

• 
• 
• +1

Feb 23, 2024

•

194

upvoted 3 papers 5 months ago

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published Aug 21, 2025 • 268

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26, 2025 • 188

Democratizing AI scientists using ToolUniverse

Paper • 2509.23426 • Published Sep 27, 2025 • 40

upvoted a collection 5 months ago

Qwen3-Omni

Collection

6 items • Updated Dec 31, 2025 • 183

upvoted 3 collections 6 months ago

Hunyuan-MT

Collection

4 items • Updated 23 days ago • 41

Bark

Collection

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

Collection

9 items • Updated 14 days ago • 29

upvoted a paper 6 months ago

Deep Think with Confidence

Paper • 2508.15260 • Published Aug 21, 2025 • 90