DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models
•
31
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models
•
31
Building a Fast Multilingual OCR Model with Synthetic Data
•
28
How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas
•
23
ML Intern Takes Our Post-Training Internship Test
•
23
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
305
NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots
•
10
Multilingual Tool Calling in 70+ Languages, On Device
•
7
Save the traces! 🐳
•
6
mlinter: a linter for Transformers modeling files
•
6
Hy3 preview: A Rebuilt Hunyuan, a 21B-Active MoE, and a New Reasoning Receipe
•
5
Qwen3.5: Nobody Agrees on Attention Anymore
•
23
How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs
•
59
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
•
12
Code a simple RAG from scratch
•
324
Introducing Cohere-transcribe: state-of-the-art speech recognition
•
40
How I contributed a new model to the Transformers library using Codex
•
49
Introducing the Bright Data CLI for Automated Web Data Pipelines
•
3
Vessel Browser: The Open Source Browser Designed for Autonomous Agents
•
3
RL: A Structured Human Action & Intent Dataset for Physical AI and World Models
•
3
Mastering Tensor Dimensions in Transformers
•
164