BIOENGINEER

Bird Swarm Optimized Cascaded Network Detects Tuberculosis With High Diagnostic Accuracy

A deep learning framework combining bird swarm optimization with adaptive image segmentation achieved 99.05 percent accuracy ...
BIOENGINEER

Adaptive differential privacy boosts asynchronous federated learning accuracy across simulated satellite networks

Computer scientists have developed an asynchronous federated learning framework that coordinates client trust, adaptive noise ...

Direct Manipulation of Neural Networks via Weight-Space Programming: The Dawn and Ripples of Self-Reorganizing AI Demonstrated by GPT-6 Astra

Box ManipulationIn the history of artificial intelligence and machine learning, the determination of internal parameters ...
runtimewire.com

GPT-6 Astra edited 0.016% of Qwen's weights and its math score went up 6x

MIT CSAIL researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights to fix reasoning loops, lifting MATH-500 from 7.9% to 48.1% without training.
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 ...
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 ...

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 ...
GitHub

Neural Networks and Deep Learning

B.E. CSE at Osmania University (2014-2018) and M.Tech CS / AI at SSSIHL. - saikrishnavadali05/Academic-CSE-Osmania-SSSIHL ...
HackerNoon

Self-Retrospection Distillation Lifts AI Agent Success From 0% to 60.6% When Every Rollout Fails

Salesforce's SRD distills hindsight into foresight, rescuing agent RL when rewards vanish and lifting success from 0% to 60.6 ...
eLife

Dual reinforcement-learning network modules for modeling decision-making with multiple strategies

Laboratory of Neural Computation, Institute for Quantitative Biosciences, the University of Tokyo, Tokyo, Japan Department of Life Sciences, Graduate School of Arts and Sciences, the University of ...
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 ...