跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25476 · v1

WeightCode: Installing New Capabilities into Neural Networks via Weight-Space Programming

首次提交 2026-11-19 12:04
版本更新 2026-11-19 12:04
雷达观测 2026-11-20 10:50
arXiv ↗PDF ↗

摘要

Neural networks encode learned capabilities in their weights, yet extending those capabilities with explicit task knowledge remains a fundamental challenge. Here we show that Weight-Space Programming (WSP), in which executable programs read, construct or modify a network's weights directly, can install new capabilities within trained neural networks. WeightCode, a WSP framework, uses a frozen language model to write executable weight programs that install new computations into trained neural networks using task knowledge and their existing weights, without gradient-based training. Once installed, the new capabilities run independently of the language model. Given a grammar or eight demonstrations, weight programs enable previously unseen command compositions (0% to 99.8% exact match) and a new pickup action (0% to 98.4% success), while preserving the original command and navigation capabilities. On ImageNet, four weight programs achieve net gains of 8.84-17.62 points while preserving clean accuracy, outperforming the best of eight fine-tuning methods under matched examples, checks, and retention constraints. In a Vision Transformer, causal interventions show that installed noise-correction gates drive robustness gains, while their selective activation preserves clean accuracy. Rerun on five independently trained Vision Transformers without further language model calls, ten weight programs retain 83-110% of their source-network gains on average, whereas copying their fixed weight edits yields negligible gains. Six programs written for an already edited network add 5.23-14.50 points of contrast robustness while retaining the previously installed noise gain. Together, these results establish WSP as a new route to acquiring and accumulating capabilities in trained neural networks through reusable weight programs.

作者备注:26 pages, 11 figures, including appendix. Code: https://github.com/Gen-Verse/WeightCode

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 12:04 · 最新观测版本

WeightCode: Installing New Capabilities into Neural Networks via Weight-Space Programming

Neural networks encode learned capabilities in their weights, yet extending those capabilities with explicit task knowledge remains a fundamental challenge. Here we show that Weight-Space Programming (WSP), in which executable programs read, construct or modify a network's weights directly, can install new capabilities within trained neural networks. WeightCode, a WSP framework, uses a frozen language model to write executable weight programs that install new computations into trained neural networks using task knowledge and their existing weights, without gradient-based training. Once installed, the new capabilities run independently of the language model. Given a grammar or eight demonstrations, weight programs enable previously unseen command compositions (0% to 99.8% exact match) and a new pickup action (0% to 98.4% success), while preserving the original command and navigation capabilities. On ImageNet, four weight programs achieve net gains of 8.84-17.62 points while preserving clean accuracy, outperforming the best of eight fine-tuning methods under matched examples, checks, and retention constraints. In a Vision Transformer, causal interventions show that installed noise-correction gates drive robustness gains, while their selective activation preserves clean accuracy. Rerun on five independently trained Vision Transformers without further language model calls, ten weight programs retain 83-110% of their source-network gains on average, whereas copying their fixed weight edits yields negligible gains. Six programs written for an already edited network add 5.23-14.50 points of contrast robustness while retaining the previously installed noise gain. Together, these results establish WSP as a new route to acquiring and accumulating capabilities in trained neural networks through reusable weight programs.

查看此版本解读 →查看此版本原文 ↗