Subscribe to Updates
Subscribe to get the latest content in real time.
Author: Emma Thompson
Authors: Mengkang Hu、Tianxing Chen、Qiguang Chen、Yao Mu、Wenqi Shao、Ping Luo Paper: https://arxiv.org/abs/2408.09559 Introduction In recent years, Large Language Models (LLMs) have demonstrated significant potential in various domains, including software development, robotic planning, and simulating human behavior. These LLM-based agents operate as interactive systems that process environmental observations to generate executable actions for target tasks. A critical component of these agents is their memory mechanism, which records historical experiences as sequences of action-observation pairs. Memory can be categorized into two types: cross-trial memory, accumulated across multiple attempts, and in-trial memory (working memory), accumulated within a single attempt. While considerable research has optimized performance…
Authors: Tatjana Legler、Vinit Hegiste、Ahmed Anwar、Martin Ruskowski Paper: https://arxiv.org/abs/2408.09556 Introduction Federated Learning (FL) is a collaborative learning approach that enables the training of models across multiple decentralized devices or servers holding local data samples, without exchanging their data. This is achieved by training multiple clients on their local data, computing model updates, and then aggregating them on a central server. By keeping data on local devices and only sharing model updates, FL minimizes the risk of data breaches and preserves user privacy. Techniques such as differential privacy and secure multi-party computation can be applied to further enhance security and privacy. In…
Authors: Xingbo Fu、Zihan Chen、Binchi Zhang、Chen Chen、Jundong Li Paper: https://arxiv.org/abs/2408.09393 Federated Graph Learning with Structure Proxy Alignment: An In-Depth Analysis Introduction Graph Neural Networks (GNNs) have emerged as a powerful tool for learning from graph-structured data, enabling applications such as node classification and link prediction. However, traditional GNNs are typically trained in a centralized manner, which poses significant challenges in scenarios where data is distributed across multiple owners due to privacy concerns and commercial competition. Federated Learning (FL) offers a solution by allowing multiple data owners to collaboratively train models without sharing their private data. Federated Graph Learning (FGL) extends FL…
Authors: Jinhui Pang、Zixuan Wang、Jiliang Tang、Mingyan Xiao、Nan Yin Paper: https://arxiv.org/abs/2408.09189 Introduction Graph neural networks (GNNs) have demonstrated remarkable performance in various graph-related tasks, such as node classification. However, most GNNs are designed for supervised learning within a single domain, requiring extensive labeled data. This limitation poses challenges when transferring models to new domains with scarce labels. Addressing this issue, the paper introduces Spectral Augmentation for Graph Domain Adaptation (SA-GDA), a novel approach for unsupervised domain adaptation in graph node classification. The key idea is to leverage spectral domain characteristics to align category features across different domains, thereby improving classification performance in…
Authors: Thomas Thebaud、Gaël Le Lan、Anthony Larcher Paper: https://arxiv.org/abs/2408.08918 Introduction Biometric recognition systems have become integral to modern security frameworks, leveraging intrinsic properties of users such as voice, handwriting, and other behavioral traits. These systems encode user data into high-dimensional vectors known as embeddings. The theft of these embeddings poses a significant threat, as they are far more difficult to replace than traditional passwords or keys. This study, conducted by Thomas Thebaud, Gaël Le Lan, and Anthony Larcher, explores the vulnerabilities of behavioral biometric systems to spoofing attacks, specifically focusing on automatic speaker verification and handwritten digit analysis systems. Related Work…
Authors: Geonhee Kim、Marco Valentino、André Freitas Paper: https://arxiv.org/abs/2408.08590 Introduction Transformer-based Language Models (LMs) have achieved remarkable success across various natural language processing tasks. This success has led to increased interest in understanding the reasoning capabilities that emerge during pre-training. Recent studies suggest that logical reasoning abilities may emerge in large-scale models or through transfer learning on specialized datasets. However, there is ongoing debate about whether these models apply systematic inference rules or merely reuse superficial patterns learned during pre-training. This paper aims to provide a deeper understanding of the low-level logical inference mechanisms in LMs by focusing on mechanistic interpretability. Methodology…
Authors: Shaojun Xu、Xusheng Luo、Yutong Huang、Letian Leng、Ruixuan Liu、Changliu Liu Paper: https://arxiv.org/abs/2408.08188 Introduction Long-horizon planning in multi-robot systems is fraught with challenges such as uncertainty accumulation, computational complexity, delayed rewards, and incomplete information. This paper proposes a novel approach to exploit task hierarchy from human instructions to facilitate multi-robot planning. By leveraging Large Language Models (LLMs), the authors introduce a two-step method to translate multi-sentence instructions into a structured language, Hierarchical Linear Temporal Logic (LTL), which serves as a formal representation for planning. Related Work Language-Conditioned Robotic Planning There are two primary methods for generating actions from instructions: 1. Deep-Learning Techniques: These…
Authors: Giovanni Varricchione、Natasha Alechina、Mehdi Dastani、Brian Logan Paper: https://arxiv.org/abs/2408.08059 Maximally Permissive Reward Machines: A Detailed Exploration Introduction Reward machines (RMs) are a powerful tool for defining temporally extended tasks and behaviors in reinforcement learning (RL). They represent tasks as sequences of abstract steps or phases, with transitions corresponding to high-level events in the environment. However, generating informative RMs can be challenging, and existing planning-based approaches often limit the flexibility of the learning agent by relying on a single plan. This paper introduces a novel approach to synthesizing RMs based on the set of partial-order plans for a goal, resulting in “maximally…
Authors: Stefano Woerner、Christian F. Baumgartner Paper: https://arxiv.org/abs/2408.08058 Introduction Machine learning has significantly advanced medical imaging and diagnostics, but these advancements often rely on large, well-annotated datasets. For many medical applications, especially rare diseases, collecting such datasets is challenging. Few-shot learning (FSL) offers a potential solution by enabling the training of models with minimal data. This study benchmarks the performance of various foundation models in FSL and zero-shot learning (ZSL) across diverse medical imaging datasets. Methods Dataset The study utilizes the MedIMeta dataset, which includes 19 publicly available datasets covering 10 different imaging modalities. This standardized meta-dataset allows for a comprehensive…
Authors: Seon-Hoon Kim、Dae-won Chung Paper: https://arxiv.org/abs/2408.07947 Introduction Synthetic Aperture Radar (SAR) imaging technology offers the unique advantage of data collection regardless of weather conditions and time. However, SAR images are often complex due to backscatter patterns and speckle noise, making them difficult to interpret. Translating SAR images into optical-like representations can aid in their interpretation. Existing methods, primarily based on Generative Adversarial Networks (GANs), face challenges such as training instability and low fidelity, especially when dealing with low-resolution satellite imagery datasets. This paper introduces a novel approach using the Conditional Brownian Bridge Diffusion Model (BBDM) for translating Very-High-Resolution (VHR) SAR…