Waterloo's PAW compiles task specs into 23MB LoRA adapters a 600M-parameter model runs entirely offline.

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...
Tech Times

Compile Once, Run Offline: New AI Method Matches 32B Models With a 23MB File

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...

DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%

DSpark can make decoding faster, but acceptance quality still determines how much speed the system actually realizes.
GitHub

Turn documents into structured JSON with local-first document AI.

ParseHawk turns PDFs, scans, images, text, and Markdown into validated JSON. It is built for private document workflows where you want to define the output contract and keep control of files, models, ...
IEEE

A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs

Abstract: As modern web services increasingly rely on REST APIs, their thorough testing has become crucial. Furthermore, the advent of REST API documentation languages, such as the OpenAPI ...
GitHub

A Python API for the National Data Buoy Center

The National Oceanic and Atmospheric Association's National Data Buoy Center maintains marine monitoring and observation stations around the world 1. These stations report atmospheric, oceanographic, ...
BMJ

Substandard and counterfeit medicines: a systematic review of the literature

Objective To explore the evidence available of poor-quality (counterfeit and substandard) medicines in the literature. Design Systematic review. Data sources Databases used were EMBASE, MEDLINE, ...