AI Briefing#on-device-ai
The latest AI and developer news about #on-device-ai, with the original source and a short summary.
The latest AI and developer news about #on-device-ai, with the original source and a short summary.
LG AI Research and LG U+ evolved ixi-O into on-device agentic AI by leveraging the EXAONE model.
LG AI Research and LG Uplus leveraged EXAONE to build an on-device agentic AI service that maximizes both security and efficiency.
POCKET-Image achieves accurate Korean text rendering even on-device through a pipeline that preserves glyph shapes.
Logue, a privacy-focused meeting notes app that runs 100% on-device using MLX on Apple Silicon, has been open-sourced.
mii-llm has released a small language model with about 400 million parameters supporting Portuguese and English.
Cactus added a 68k-parameter probe layer to Gemma 4 E2B and unveiled a hybrid inference system that uses the model's own error detection as a signal for cloud routing.
PrismML has released Bonsai 27B, a compressed version of the Qwen 27B model using 1-bit and ternary methods that can run even on smartphones.
LG AI Research has released 3 EXAONE 3.5 open-source models that maximize performance and efficiency.
LG AI Research has unveiled EXAONE 4.0, a next-generation hybrid AI model with enhanced reasoning capabilities.
LG AI Research has unveiled EXAONE 4.0, a next-generation hybrid AI model that integrates advanced reasoning capabilities.
Google announced Gemma 4 E2B, an on-device AI model that runs natively on the Tensor G5 TPU of the Pixel 10 series.
This showcases innovative AI projects from researchers around the world who used Cohere Labs' lightweight multilingual model Tiny Aya.
Apple's new SpeechAnalyzer API overwhelmed on-device speech recognition performance, recording higher accuracy and faster speed than Whisper models.
PrismML unveils technology that compresses the Qwen-3.6-27B model to under 4GB to run on iPhone.
OpenMed 1.8, an open-source clinical NLP de-identification toolkit that runs locally without data leakage, has been released.
An Apple Silicon executive revealed the demand for Mac mini to power AI agents and Apple's on-device AI strategy.
We propose the K-Merge framework, which continually expands an LLM's capabilities without data even in storage-constrained on-device environments.
Meta is introducing usage limits based on a monthly subscription fee for certain AI features of its smart glasses.
Apple has announced a Creator Studio update introducing AI-powered auto-captioning and masking features, strengthening interoperability.
Liquid AI has launched LFM 2.5-230M, an ultra-lightweight parameter model optimized for agentic workflows.
FUTO has released a lightweight swipe typing model and dataset that runs on-device.
Samsung R&D Institute has proposed PIX-TAB, a highly efficient pixel-precise table structure recognition technology capable of on-device execution.
An ExecuTorch integration has been released that lets React Native apps run Gemma 4 offline.
Apple has unveiled a new Core AI framework for optimizing and running AI models on-device on Apple silicon.