Viral News

Evaluating Language Models on Entity Disambiguation in Tables

Evaluating Language Models on Entity Disambiguation in Tables

arXiv:2408.06423v1 Announce Type: new Abstract: Tables are crucial containers of information, but understanding their meaning may be challenging. Indeed, recently, there has been a focus on Semantic Table Interpretation (STI), i.e., the task that involves the semantic annotation of tabular data to disambiguate their meaning. Over the years, there has been a surge in interest in data-driven approaches based on deep learning that have increasingly been combined with heuristic-based approaches. In the last period, the advent of Large Language Models (LLMs) has led to a new category of approaches for table annotation. The interest in this research field, characterised by…
Read More
Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks

Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks

arXiv:2408.05496v1 Announce Type: new Abstract: Weight space symmetries in neural network architectures, such as permutation symmetries in MLPs, give rise to Bayesian neural network (BNN) posteriors with many equivalent modes. This multimodality poses a challenge for variational inference (VI) techniques, which typically rely on approximating the posterior with a unimodal distribution. In this work, we investigate the impact of weight space permutation symmetries on VI. We demonstrate, both theoretically and empirically, that these symmetries lead to biases in the approximate posterior, which degrade predictive performance and posterior fit if not explicitly accounted for. To mitigate this behavior, we leverage the…
Read More
Multimodal generative semantic communication based on latent diffusion model

Multimodal generative semantic communication based on latent diffusion model

arXiv:2408.05455v1 Announce Type: new Abstract: In emergencies, the ability to quickly and accurately gather environmental data and command information, and to make timely decisions, is particularly critical. Traditional semantic communication frameworks, primarily based on a single modality, are susceptible to complex environments and lighting conditions, thereby limiting decision accuracy. To this end, this paper introduces a multimodal generative semantic communication framework named mm-GESCO. The framework ingests streams of visible and infrared modal image data, generates fused semantic segmentation maps, and transmits them using a combination of one-hot encoding and zlib compression techniques to enhance data transmission efficiency. At the receiving…
Read More
WiDe-analysis: Enabling One-click Content Moderation Analysis on Wikipedia’s Articles for Deletion

WiDe-analysis: Enabling One-click Content Moderation Analysis on Wikipedia’s Articles for Deletion

arXiv:2408.05655v1 Announce Type: new Abstract: Content moderation in online platforms is crucial for ensuring activity therein adheres to existing policies, especially as these platforms grow. NLP research in this area has typically focused on automating some part of it given that it is not feasible to monitor all active discussions effectively. Past works have focused on revealing deletion patterns with like sentiment analysis, or on developing platform-specific models such as Wikipedia policy or stance detectors. Unsurprisingly, however, this valuable body of work is rather scattered, with little to no agreement with regards to e.g., the deletion discussions corpora used for…
Read More
Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

arXiv:2408.05486v1 Announce Type: new Abstract: Topological deep learning (TDL) facilitates learning from data represented by topological structures. The primary model utilized in this setting is higher-order message-passing (HOMP), which extends traditional graph message-passing neural networks (MPNN) to diverse topological domains. Given the significant expressivity limitations of MPNNs, our paper aims to explore both the strengths and weaknesses of HOMP's expressive power and subsequently design novel architectures to address these limitations. We approach this from several perspectives: First, we demonstrate HOMP's inability to distinguish between topological objects based on fundamental topological and metric properties such as diameter, orientability, planarity, and homology.…
Read More
EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency

EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion

Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion

[Submitted on 10 Aug 2024] View a PDF of the paper titled Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion, by Jacob K Christopher and 3 other authors View PDF HTML (experimental) Abstract:Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling parallel sequence verification, its efficiency remains inherently limited by the reliance on incremental token generation in existing draft models. To overcome this limitation, this paper proposes an adaptation of speculative decoding which uses discrete diffusion…
Read More
Homomorphic Encryption Library Open Sourced by Apple

Homomorphic Encryption Library Open Sourced by Apple

(wk1003mike/Shutterstock) Apple recently open sourced its homomorphic encryption library for Swift, enabling developers who use the Apple programming language to implement the privacy-preserving technology. Homomorphic encryption (HE) is a relatively new technology that allows encrypted data to be processed without first decrypting it into clear text. For example, a user can send sensitive data in encrypted form as part of a query to a server, and the server can respond to that query and the encrypted data without decrypting it. While it may sound impossible at first, HE has been proven mathematically to be accurate and effective. Apple developed its…
Read More
A Structural Feature-Based Approach for Comprehensive Graph Classification

A Structural Feature-Based Approach for Comprehensive Graph Classification

arXiv:2408.05474v1 Announce Type: new Abstract: The increasing prevalence of graph-structured data across various domains has intensified greater interest in graph classification tasks. While numerous sophisticated graph learning methods have emerged, their complexity often hinders practical implementation. In this article, we address this challenge by proposing a method that constructs feature vectors based on fundamental graph structural properties. We demonstrate that these features, despite their simplicity, are powerful enough to capture the intrinsic characteristics of graphs within the same class. We explore the efficacy of our approach using three distinct machine learning methods, highlighting how our feature-based classification leverages the inherent…
Read More
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

arXiv:2408.05446v1 Announce Type: new Abstract: Adversarial examples pose a significant challenge to the robustness, reliability and alignment of deep neural networks. We propose a novel, easy-to-use approach to achieving high-quality representations that lead to adversarial robustness through the use of multi-resolution input representations and dynamic self-ensembling of intermediate layer predictions. We demonstrate that intermediate layer predictions exhibit inherent robustness to adversarial attacks crafted to fool the full classifier, and propose a robust aggregation mechanism based on Vickrey auction that we call textit{CrossMax} to dynamically ensemble them. By combining multi-resolution inputs and robust ensembling, we achieve significant adversarial robustness on CIFAR-10…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.