Compression’s new goal: Reducing how much an AI ‘overthinks’

We compress not to shrink data, but to make it cheaper for AI to “think”.

Nota AI Signs AI Optimization Technology Supply and Strategic Partnership Agreement with Mobilint Accelerating Commercialization of On-Device AI on Dome…

Nota AI (CEO Myung-su Chae), a specialist in AI model compression and optimization, announced that it has signed an agreement ...

Multiverse Computing Launches LittleLamb Model Family on Hugging Face, Expanding Compact AI for Edge, On-Device, and Agentic Use Cases

New open-source releases LittleLamb 0.3B, LittleLamb 0.3B Tool-Calling, and LittleLamb 0.3B Mobile pair ultra-compact deployment with bilingual reasoning in 50% compressed versions of ...
Your Story

How CLIKA’s automated hardware-aware AI compression toolkit efficiently enables scalable deployment of AI on any target hardware

With democratising AI and greater access to open-source AI models, enterprises today have made AI adoption a mission-critical imperative. According to Menlo Venture’s report, “2024: The State of ...
Ars Technica

AI language models can exceed PNG and FLAC in lossless compression, says study

Effective compression is about finding patterns to make data smaller without losing information. When an algorithm or model can accurately guess the next piece of data in a sequence, it shows it’s ...
Morning Overview on MSN

Tencent open-sources 440MB on-device translation model covering 33 languages

A translation model that fits in 440 megabytes, runs entirely offline, and handles 33 languages just landed on Hugging Face, ...