NEO-unify: Building Native Multimodal Unified Models End to End
•
126
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
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
Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts
•
9
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
•
9
When Speech AI Meets the Long Tail of Languages: Inside the VAANI Dataset
•
8
Stop benchmarking inference providers
•
8
NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots
•
8
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
299
Uncensor any LLM with abliteration
•
844
Using OCR models with llama.cpp
•
25
easyaligner: Forced alignment of text and audio, made easy
•
5
Mastering Tensor Dimensions in Transformers
•
163
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
•
12
Qwen3.5: Nobody Agrees on Attention Anymore
•
22
ALTK‑Evolve: On‑the‑Job Learning for AI Agents
•
27
How I contributed a new model to the Transformers library using Codex
•
48
Releasing LiteCoder-Terminal-SFT
•
4
Vessel Browser: The Open Source Browser Designed for Autonomous Agents
•
3
Introduction to State Space Models (SSM)
•
222
Understanding Vector Quantization in VQ-VAE
•
58