weight-update

The Imprint Reader is a model trained to describe frozen weight updates in language models, enabling behavioral intervention to improve safety and reasoning. It uses SMaRT for training and MetaEdit for intervention, demonstrating feasibility in natural language readout.

This paper investigates using symbolic regression to discover explicit neural network weight-update rules that outperform standard hand-designed optimizers on small symbolic regression benchmarks, achieving an aggregate MSE reduction of 44.47% in 25 out of 30 benchmark/network combinations.

Introduces 'skill neologisms', a method for enabling LLMs to learn new skills without weight updates, addressing catastrophic forgetting. Presented at ICML.

A self-improving AI framework that simultaneously updates both model weights and task-specific agent architecture via a language-model feedback agent, achieving significant gains across legal classification, GPU optimization, and biological denoising tasks.