AI Technology Database

Graph neural networks (GNNs) have become the state of the art for various graph-related tasks and are particularly prominent in heterogeneous graphs (HetGs). However, several issues plague this paradigm: first, the difficulty in fully utilizing long-range...

Asteroid shape inversion using photometric data has been a key area of study in planetary science and astronomical this http URL, the current methods for asteroid shape inversion require extensive iterative calculations, making the process time-consuming ...

Recurrent neural networks (RNNs) are central to sequence modeling tasks, yet their high computational complexity poses challenges for scalability and real-time deployment. Traditional pruning techniques, predominantly based on weight magnitudes, often ove...

We extend a recently introduced deep unrolling framework for learning spatially varying regularisation parameters in inverse imaging problems to the case of Total Generalised Variation (TGV). The framework combines a deep convolutional neural network (CNN...

Galaxy mergers are crucial for understanding galaxy evolution, and with large upcoming datasets, automated methods, such as Convolutional Neural Networks (CNNs), are needed for efficient detection. It is understood that these networks work by identifying ...

Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the potential to produce smaller, high...

How can we subsample graph data so that a graph neural network (GNN) trained on the subsample achieves performance comparable to training on the full dataset? This question is of fundamental interest, as smaller datasets reduce labeling costs, storage req...

Modern recommender systems use ML models to predict consumer preferences from consumption history. Although these black-box models achieve impressive predictive performance, they often suffer from a lack of transparency and explainability. Contrary to the...

Sampling from nonsmooth target probability distributions is essential in various applications, including the Bayesian Lasso. We propose a splitting-based sampling algorithm for the time-implicit discretization of the probability flow for the Fokker-Planck...

As a key infrastructure for China's West-to-East Power Transmission project, transmission lines (TL) face the threat of ice accretion under complex microclimatic conditions. This study proposes a plane principal strain sensing method based on a fiber ...

Graph Neural Networks (GNNs) have gained attention for their ability to learn representations from graph data. Due to privacy concerns and conflicts of interest that prevent clients from directly sharing graph data with one another, Vertical Graph Federat...

Physics-Informed Neural Networks (PINNs) have gained increasing attention for solving partial differential equations, including the Helmholtz equation, due to their flexibility and mesh-free formulation. However, their low-frequency bias limits their accu...

Machine-learning-based variational Monte Carlo simulations are a promising approach for targeting quantum many body ground states, especially in two dimensions and in cases where the ground state is known to have a non-trivial sign structure. While m...

Abstract. In this paper, we study the vanishing order of rational L-functions from a data scientificperspective. Each L-function is represented in our data by finitely many Dirichlet coefficients, thenormalisation of which depends on the context. We obser...

Thinker算法允许智能体学习如何自主规划和执行动作，通过与习得模型交互实现更优的性能，为强化学习中规划技能与智能体决策过程的无缝融合提供了新的研究方向。动机：为了填补在模型为学习的情况下，强化学习代理与习得世界模型之间的缺失，使代理能够自主与习得模型交互并利用模...

本文提出了 Adversarial Self-Attention 机制（ASA），利用对抗训练重构 Transformer 的注意力，使模型在被污染的模型结构中得到训练。尝试解决的问题：大量的证据表明，自注意力可以从 allowing bias 中获益，allowing bias 可以将一定程度的先验（如 masking，分布的平滑）加入...

神经算法推理（NAR）是一个专注于设计能够可靠地捕捉经典计算的神经架构的研究领域，通常通过学习执行算法。一种典型的方法是依赖于图神经网络（GNN）架构，该架构对在算法执行过程中重复变换的高维潜在空间中的输入进行编码。在这项工作中，我们对执行算法时由GNN引起的潜在空间...

Challenges and Applications of Large Language ModelsJean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, Robert McHardy大型语言模型（LLM）在短短几年内就从不曾存在到在机器学习领域无处不在。由于该领域的快速发展，我们很难确定仍然存在的...

A Real-World WebAgent with Planning, Long Context Understanding, and Program SynthesisIzzeddin Gur, Hiroki Furuta, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, Aleksandra Faust[Google DeepMindThe University of Tokyo]具备规划长程上下文理解和程序合...

Human-Timescale Adaptation in an Open-Ended Task SpaceAdaptive Agent Team, Jakob Bauer, Kate Baumli, Satinder Baveja, Feryal Behbahani, Avishkar Bhoopchand, Nathalie Bradley-Schmieg, Michael Chang, Natalie Clay, Adrian Collister, Vibhavari Dasagi, Lucy Go...