Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond

TL;DR

The paper presents Model Feedback Learning (MFL), a test-time optimization method that adapts pre-trained models to new tasks without retraining, demonstrated in semiconductor manufacturing and other industrial processes.

Contribution

MFL introduces a lightweight reverse model for efficient input optimization at test time, enabling adaptation without retraining or hardware modification.

Findings

MFL achieves target recipes in five iterations for semiconductor plasma etching.

Outperforms Bayesian optimization and human experts in efficiency and accuracy.

Demonstrates broad applicability across chemical and electronic manufacturing processes.

Abstract

We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring any retraining of the models or modifications to the hardware. In contrast to existing methods that rely on adjusting model parameters, MFL leverages a lightweight reverse model to iteratively search for optimal inputs, enabling efficient adaptation to new objectives under deployment constraints. This framework is particularly advantageous in real-world settings, such as semiconductor manufacturing recipe generation, where modifying deployed systems is often infeasible or cost-prohibitive. We validate MFL on semiconductor plasma etching tasks, where it achieves target recipe generation in just five iterations, significantly outperforming both Bayesian optimization and human experts. Beyond semiconductor applications, MFL also demonstrates strong performance in chemical processes (e.g., chemical vapor deposition) and electronic systems (e.g., wire bonding), highlighting its broad applicability. Additionally, MFL incorporates stability-aware optimization, enhancing robustness to process variations and surpassing conventional supervised learning and random search methods in high-dimensional control settings. By enabling few-shot adaptation, MFL provides a scalable and efficient paradigm for deploying intelligent control in real-world environments.