The art of literary translation exposes the limits of AI

AI-powered translation tools are certainly impressive. But there is an important frontier for translation technology, one AI ...
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

Integrating Prior Translation Knowledge Into Neural Machine Translation

Abstract: Neural machine translation (NMT), which is an encoder-decoder joint neural language model with an attention mechanism, has achieved impressive results on various machine translation tasks in ...
GitHub

GCP-VQVAE: A Geometry-Complete Language for Protein 3D Structure

Converting protein tertiary structure into discrete tokens via vector-quantized variational autoencoders (VQ-VAEs) creates a language of 3D geometry and provides a natural interface between sequence ...
VentureBeat

Meta's new BLT architecture replaces tokens to make LLMs more efficient and versatile

The AI research community continues to find new ways to improve large language models (LLMs), the latest being a new architecture introduced by scientists at Meta and the University of Washington.
Slator

A Primer on Decoder-Only vs Encoder-Decoder Models for AI Translation

Large language models (LLMs) have changed the game for machine translation (MT). LLMs vary in architecture, ranging from decoder-only designs to encoder-decoder frameworks. Encoder-decoder models, ...