ACRouter, a new open-source AI router, learns from execution feedback to pick the best coding model per task, cutting costs 2 ...

By combining native vision, audio, and reasoning in a compact model, Gemma provides a compelling platform for local AI agents ...

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

Context windows are becoming a computational bottleneck. The longer an agent runs, the more tokens accumulate from retrieved documents, reasoning traces and conversation history, and the more memory ...

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 ...

Abstract: Code search is essential for code reuse, allowing developers to efficiently locate relevant code snippets. The advent of powerful decoder-only Large Language Models (LLMs) has revolutionized ...

This repository contains code and models for vision transformers that generate representations which not only do well for standard recognition tasks (classification, segmentation), but also support ...

Chinese outfit Zhipu AI claims it trained a new model entirely using Huawei hardware, and that it’s the first company to build an advanced model entirely on Chinese hardware. Zhipu, which styles ...

We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our framework uniquely ...

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 ...