Building a Fast Multilingual OCR Model with Synthetic Data
•
26
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Building a Fast Multilingual OCR Model with Synthetic Data
•
26
DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models
•
16
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
•
10
NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots
•
10
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
301
Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts
•
9
NEO-unify: Building Native Multimodal Unified Models End to End
•
126
How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs
•
58
easyaligner: Forced alignment of text and audio, made easy
•
5
Save the traces! 🐳
•
5
Uncensor any LLM with abliteration
•
844
Code a simple RAG from scratch
•
324
Multilingual Tool Calling in 70+ Languages, On Device
•
4
Mastering Tensor Dimensions in Transformers
•
163
Everything You Need to Know about Knowledge Distillation
•
79
Qwen3.5: Nobody Agrees on Attention Anymore
•
22
Introducing Cohere-transcribe: state-of-the-art speech recognition
•
40
How I contributed a new model to the Transformers library using Codex
•
48
Using OCR models with llama.cpp
•
25
Stop benchmarking inference providers
•
8