XDA Developers on MSN

I tested Google's new Gemma 4 12B on my 8GB GPU, and now I don't want to go back to smaller models

Not bad for limited hardware ...
VentureBeat

Context compression finally works in production: new research cuts LLM input 16x without the accuracy hit

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 ...
IEEE

Visual Evidence-aware for Object Hallucinations Rectification in LLM-based Video Captioning

Abstract: Recent neural models for video captioning are typically built using a framework that combines a pre-trained visual encoder with a large language model(LLM) decoder. However, large language ...
InfoQ

Gemma 4 12B Enables On-Device, Multimodal Agentic Workflows with an Encoder-free Architecture

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 ...
note

Multimodal LLMs That Ditched the Encoder — Reading the "Direct Projection" Architecture of Gemma 4 12B

On June 3, 2026, Google DeepMind released Gemma 4 12B (where 12B = 12G = 12 billion parameters). It is a model capable of handling images, audio, and video, making it an AI that can process multiple ...
note

Gemma 4 12B In-Depth: A New Model Bringing Full-Scale Multimodality to Laptops with an Encoder-Free Design

Gemma 4 12B is a new model in the Gemma 4 family announced by Google on June 3, 2026. It is positioned as an "encoder-free unified multimodal model optimized for laptops." The official blog (Google ...
marktechpost

Google DeepMind Releases Gemma 4 12B: An Encoder-Free Multimodal Model with Native audio that runs on a 16 GB laptop

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 ...
GitHub

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

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 ...
IEEE

A Siamese Encoder-Decoder Model with Attention for LLM Prompt Reconstruction

Abstract: Reconstructing prompts in text generation systems is a significant challenge in natural language processing (NLP). This study presents a novel Siamese encoder-decoder framework augmented ...
Phys.org

AI model learns yeast DNA 'language' to boost protein drug output

Industrial yeasts are a powerhouse of protein production, used to manufacture vaccines, biopharmaceuticals, and other useful compounds. In a new study, MIT chemical engineers have harnessed artificial ...
AppleInsider

Apple AI research shows how MLLMs understand, generate, search for images

Apple's researchers continue to focus on multimodal LLMs, with studies exploring their use for image generation, understanding, and multi-turn web searches with cropped images. Now, the company is ...