The mad dash to build the future of multimedia

The Verge is about technology and how it makes us feel. Founded in 2011, we offer our audience everything from breaking news ...

Dolby sues Snap over video compression patent claims tied to AV1 and HEVC

In a complaint filed in the US District Court for the District of Delaware, Dolby accuses Snap of infringing four video compression patents through Snapchat's use ...

Micron stock's rally looked unstoppable — until Google's TurboQuant hit

Memory stocks such as Micron Technology Inc. MU and Sandisk Corp. SDNK were the consensus AI trade of 2026 — the most direct ...

Google's TurboQuant compression tech cuts LLM memory use by 6x with no accuracy loss

The biggest memory burden for LLMs is the key-value cache, which stores conversational context as users interact with AI ...
Decrypt

Google Shrinks AI Memory With No Accuracy Loss—But There's a Catch

The technique reduces the memory required to run large language models as context windows grow, a key constraint on AI ...
The Next Web

Google’s new compression algorithm cut memory stocks within hours of publication

Google's TurboQuant algorithm compresses LLM key-value caches to 3 bits with no accuracy loss. Memory stocks fell within ...

Google unveils TurboQuant, a new AI memory compression algorithm — and yes, the internet is calling it ‘Pied Piper’

Google’s TurboQuant has the internet joking about Pied Piper from HBO's "Silicon Valley." The compression algorithm promises ...

Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x

Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language ...
IEEE

A MLFMA-enhanced PCA Compression Method for Efficient Direct Solution to Electromagnetic Scattering Problems

Abstract: A novel direct method for electromagnetic scattering analysis is introduced by enhancing the principal component analysis (PCA) compression algorithm with the multilevel fast multipole ...

Nvidia says it can shrink LLM memory 20x without changing model weights

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory ...
IEEE

Optimization and Performance Analysis of the SIREN Algorithm for Lossless Image Compression Across Various Medical Imaging Modalities

Abstract: Modern healthcare depends significantly on medical imaging technology which enables both patient diagnosis and medical treatment development and research activities. Efficient storage and ...