BIOENGINEER

Benchmarking Deep Transfer Learning Models for COVID-19 Lung Ultrasound Detection

A systematic benchmarking study demonstrates that DenseNet-121 paired with the Adam optimizer achieves exceptional diagnostic ...
GitHub

Pi Weight-Space Programming (π · WSP)

A Pi harness extension, tool suite, and skill collection for Weight-Space Programming—enabling language models to natively read, interpret, construct, and surgically edit neural network weights ...

Overview of Weight-Space Programming - GPT-6 Astra directly analyzes, edits, and generates neural network weights

Space Programming".1. Weight-Space ProgrammingOn November 2, 2026, a research team at MIT CSAIL announced a new method called "Weight-Space Programming", in which an LLM directly reads and writes the ...
kucoin

MIT researchers use GPT-6 Astra to enhance Qwen's mathematical ability by 6x

Article by Shenchao TechFlowNo training required, no data needed, no gradient descent.Researchers at MIT fed the weights of ...
xenospectrum

MIT Shows an LLM Can Read and Edit Another Neural Network's Weights Directly

MIT CSAIL's "weight-space programming" has a frontier LLM read and edit neural network weights directly, with no gradient descent. Surgical edits ended Qwen's reasoning loops, but the results come ...
eu.36kr

MIT allowed GPT-6 Astra to directly modify Qwen's weights, and its math scores have soared.

MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
GitHub

Automatic Differentiation-Based Full Waveform Inversion

A new upgoing multi-agent architecture enables ADFWI to coordinate forward modeling, inversion, and interpretation in FWI, allowing information to flow from low-level simulation agents up to ...