Meta’s Brain2Qwerty v2 offers a breakthrough non-invasive brain-to-text AI model with 61% word accuracy, challenging Neuralink’s invasive methods by decoding brain signals into text without surgery.

Open-source OCR from Baidu eliminates the GPU memory wall that limits long-document parsing. Unlimited OCR uses a constant KV ...

Google says that Gemma 4 12B is "designed to bring agentic, multimodal intelligence directly to your laptop", further noting that the new model can be combined with Google AI Edge to "build and ...

Gemma 4 12B is a 12-billion-parameter decoder-only transformer. It handles text, images, audio, and video natively. There are no separate vision or audio encoders. The decoder uses the same structure ...

A complete walkthrough of implementing the original Attention Is All You Need encoder-decoder Transformer—no torch. nn.Transformer, no shortcuts. The 2017 paper "Attention Is All You Need" by Vaswani ...

In the study titled MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer, a team of nearly 30 Apple researchers details a novel unified approach that enables both ...

In brief: Small language models are generally more compact and efficient than LLMs, as they are designed to run on local hardware or edge devices. Microsoft is now bringing yet another SLM to Windows ...

A screenshot of Mu performing real-time question answering. Image: Windows YouTube channel The Mu small language model enables an AI agent to take action on hundreds ...