paper-with-me

Papers

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

2025-05-21 · Eric J. Michaud, Asher Parker-Sartori, Max Tegmark

We study the problem of creating strong, yet narrow, AI systems. While recent AI progress has been driven by the training of large general-purpose foundation models, the creation of smaller models specialized for narrow domains could be valuable for both efficiency and safety. In this work, we explore two challenges involved in creating such systems, having to do with basic properties of how neural networks learn and structure their representations. The first challenge regards when it is possible to train narrow models from scratch. Through experiments on a synthetic task, we find that it is sometimes necessary to train networks on a wide distribution of data to learn certain narrow skills within that distribution. This effect arises when skills depend on each other hierarchically, and training on a broad distribution introduces a curriculum which substantially accelerates learning. The second challenge regards how to transfer particular skills from large general models into small specialized models. We find that model skills are often not perfectly localized to a particular set of prunable components. However, we find that methods based on pruning can still outperform distillation. We investigate the use of a regularization objective to align desired skills with prunable components while unlearning unnecessary skills.

📄 PDF Abstract BibTeX arXiv:2505.15811

Code (1)

ejmichaud/narrow 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Probing many-body Bell correlation depth with superconducting qubits

2024-06-25 · Ke Wang, Weikang Li, Shibo Xu, Mengyao Hu 외

Quantum nonlocality describes a stronger form of quantum correlation than that of entanglement. It refutes Einstein's belief of local realism and is among the most distinctive and enigmatic features of quantum mechanics.…

SpatialTree: How Spatial Abilities Branch Out in MLLMs

2025-12-23 · Yuxi Xiao, Longfei Li, Shen Yan, Xinhang Liu 외 arxiv

Cognitive science suggests that spatial ability develops progressively-from perception to reasoning and interaction. Yet in multimodal LLMs (MLLMs), this hierarchy remains poorly understood, as most studies focus on a na…

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

2026-05-26 · Huawei Lin, Peng Li, Jie Song, Fuxin Jiang 외 arxiv

Large language model (LLM) agents rely on reusable skills to solve complex tasks, but existing skill creation approaches often treat skills as isolated, static artifacts, limiting reusability, reliability, and long-term …

A New Approach of Learning Hierarchy Construction Based on Fuzzy Logic

2014-12-08 · Ali Aajli, Karim Afdel

In recent years, adaptive learning systems rely increasingly on learning hierarchy to customize the educational logic developed in their courses. Most approaches do not consider that the relationships of prerequisites be…

Creating Multi-Level Skill Hierarchies in Reinforcement Learning

2023-06-16 · NeurIPS 2023 11 · Joshua B. Evans, Özgür Şimşek

What is a useful skill hierarchy for an autonomous agent? We propose an answer based on a graphical representation of how the interaction between an agent and its environment may unfold. Our approach uses modularity maxi…

graph partitioningreinforcement-learningReinforcement Learning