IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models

Researchers at Tsinghua University and Z.ai built IndexCache to eliminate redundant computation in sparse attention models ...

Groundbreaking iPhone App Runs Optimized GPT AI Models Entirely Offline and On-Device, for a Greener, More Private Alternative to Data Centre Driven Products.

N6, an independent British software developer, has released LiberaGPT, a free iPhone app that runs multiple GPT models ...
Nature

Tile Assembly Models and Universal Computation

Tile assembly models form a robust theoretical framework for understanding how simple components, such as molecular tiles, can organise themselves into complex structures. At the core of these models ...
mccormick.northwestern.edu

COMP_SCI 335: Intro to the Theory of Computation

This course gives an introduction to the mathematical foundations of computation. The course will look at Turing machines, universal computation, the Church-Turing thesis, the halting problem and ...
Boston College

Hsin-Hao Su Receives NSF Award

BC Computer Science Assistant Professor Hsin-Hao Su has received funding from the National Science Foundation for a research project entitled Combinatorial Optimization Problems in Vertex Centric ...