Robustness to Programmable String Transformations via Augmented Abstract Training

Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)

Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However, data augmentation alone is not sufficient to achieve lower generalisation errors. This project proposes a new method that combines data augmentation and domain distance minimisation to address the problems associated with data augmentation and provide a guarantee on the learning performance, under an existing framework. Empirically, our method outperforms b…

A Memory-Augmented Neural Network Model of Abstract Rule Learning

Human intelligence is characterized by a remarkable ability to infer abstract rules from experience and apply these rules to novel domains. As such, designing neural network algorithms with this capacity is an important step toward the development of deep learning systems with more human-like intelligence. However, doing so is a major outstanding challenge, one that some argue will require neural networks to use explicit symbol-processing mechanisms. In this work, we focus on neural networks' capacity for arbitrary role-filler binding, the ability to associate abstract "roles" to context-speci…

分层抽象树用于跨文档检索增强生成

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

本文提出Ψ-RAG框架，通过迭代'合并与坍缩'过程构建分层抽象树索引，并引入多粒度检索代理，解决传统树状RAG在跨文档多跳问题中的分布适应性、结构隔离和抽象粗粒度等挑战，实验表明其在跨文档多跳问答任务中表现更优。

An Interpretable Neural Network for Configuring Programmable Wireless Environments

Software-defined metasurfaces (SDMs) comprise a dense topology of basic elements called meta-atoms, exerting the highest degree of control over surface currents among intelligent panel technologies. As such, they can transform impinging electromagnetic (EM) waves in complex ways, modifying their direction, power, frequency spectrum, polarity and phase. A well-defined software interface allows for applying such functionalities to waves and inter-networking SDMs, while abstracting the underlying physics. A network of SDMs deployed over objects within an area, such as a floorplan walls, creates p…

Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers

A key feature of intelligent behaviour is the ability to learn abstract strategies that scale and transfer to unfamiliar problems. An abstract strategy solves every sample from a problem class, no matter its representation or complexity -- like algorithms in computer science. Neural networks are powerful models for processing sensory data, discovering hidden patterns, and learning complex functions, but they struggle to learn such iterative, sequential or hierarchical algorithmic strategies. Extending neural networks with external memories has increased their capacities in learning such strate…

结构抽象作为非平稳语言模型训练的归纳偏置

Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training

提出抽象增强训练（AAT）方法，通过联合优化具体实例及其结构抽象，减少灾难性干扰并提升关系泛化能力，在非平稳语言模型训练中验证了结构抽象作为稳定学习信号的有效性。