Mike Ravkine PRO

mike-ravkine's activity

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

upvoted an article 6 days ago

view article

Article

We Got Claude to Build CUDA Kernels and teach open models!

• 
• 
• +2

8 days ago

•

113

upvoted an article about 1 month ago

view article

Article

Case Study: The Marcus-Thorne Mystery Cache Standoff

• 

Jan 1

•

3

upvoted a collection about 2 months ago

NVIDIA Nemotron v3

Collection

Open, Production-ready Enterprise Models • 7 items • Updated 6 days ago • 131

upvoted a paper 3 months ago

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published Oct 30, 2025 • 117

upvoted 3 articles 3 months ago

view article

Article

Vision Tokens vs Text Tokens: Understanding the 10× Compression

• 

Oct 22, 2025

•

6

view article

Article

All LLMs Write Great Code, But Some Make (A Lot) Fewer Mistakes

• 

Sep 12, 2024

•

5

view article

Article

Hall of Multimodal OCR VLMs and Demonstrations

• 

Oct 31, 2025

•

7

upvoted a paper 4 months ago

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs

Paper • 2510.05069 • Published Oct 6, 2025 • 13

upvoted a paper 5 months ago

Symbolic Graphics Programming with Large Language Models

Paper • 2509.05208 • Published Sep 5, 2025 • 47

upvoted an article 6 months ago

view article

Article

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

• 

Aug 18, 2025

•

31

upvoted a collection about 1 year ago

Lumimaid 0.2

Collection

4 items • Updated Jul 26, 2024 • 20

upvoted a paper about 1 year ago

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Paper • 2412.11919 • Published Dec 16, 2024 • 36

upvoted a paper over 1 year ago

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Paper • 2410.10139 • Published Oct 14, 2024 • 51

upvoted a collection over 1 year ago

My most recent datasets

Collection

6 items • Updated Oct 8, 2024 • 6

upvoted an article over 1 year ago

view article

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

• 
• 
• +4

Sep 18, 2024

•

274

upvoted a collection over 1 year ago

Qwen2.5-Coder

Collection

Code-specific model series based on Qwen2.5 • 40 items • Updated Dec 31, 2025 • 354

upvoted a paper over 1 year ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published Sep 3, 2024 • 83

upvoted 2 collections over 1 year ago

Multimodal RAG

Collection

10 items • Updated Sep 5, 2024 • 30

Hermes 3

Collection

The Hermes 3 Series of Models • 11 items • Updated Sep 8, 2025 • 132

upvoted a paper over 1 year ago

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Paper • 2407.14057 • Published Jul 19, 2024 • 46