Search

We use the reconfiguration framework to analyze problems that involve the rearrangement of items among groups. In various applications, a group of items could correspond to the files or jobs assigned to a particular machine, and the goal of rearrangement could be improving efficiency or increasing locality. To cover problems arising in a wide range of application areas, we define the general Repacking problem as the rearrangement of multisets of multisets. We present hardness results for the general case and algorithms for various classes of instances that arise in real-life scenarios. By limiting the total size of items in each multiset, our results can be viewed as an offline approach to Bin Packing, in which each bin is represented as a multiset. In addition to providing the first results on reconfiguration of multisets, our contributions open up several research avenues: the interplay between reconfiguration and online algorithms and parallel algorithms; the use of the tools of linear programming in reconfiguration; and, in the longer term, a focus on extra resources in reconfiguration., Comment: A preliminary version of this paper appeared in the proceedings of the 18th International Conference and Workshops on Algorithms and Computation (WALCOM 2024)

The integration of new technology with cultural studies enhances our understanding of cultural heritage but often struggles to connect with diverse audiences. It is challenging to align personal interpretations with the intended meanings across different cultures. Our study investigates the important factors in appreciating art from a cross-cultural perspective. We explore the application of Large Language Models (LLMs) to bridge the cultural and language barriers in understanding Traditional Chinese Paintings (TCPs). We present CultiVerse, a visual analytics system that utilizes LLMs within a mixed-initiative framework, enhancing interpretative appreciation of TCP in a cross-cultural dialogue. CultiVerse addresses the challenge of translating the nuanced symbolism in art, which involves interpreting complex cultural contexts, aligning cross-cultural symbols, and validating cultural acceptance. CultiVerse integrates an interactive interface with the analytical capability of LLMs to explore a curated TCP dataset, facilitating the analysis of multifaceted symbolic meanings and the exploration of cross-cultural serendipitous discoveries. Empirical evaluations affirm that CultiVerse significantly improves cross-cultural understanding, offering deeper insights and engaging art appreciation.

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. How well LLMs accomplish event reasoning on various relations and reasoning paradigms remains unknown. To mitigate this disparity, we comprehensively evaluate the abilities of event reasoning of LLMs. We introduce a novel benchmark EV2 for EValuation of EVent reasoning. EV2 consists of two levels of evaluation of schema and instance and is comprehensive in relations and reasoning paradigms. We conduct extensive experiments on EV2. We find that LLMs have abilities to accomplish event reasoning but their performances are far from satisfactory. We also notice the imbalance of event reasoning abilities in LLMs. Besides, LLMs have event schema knowledge, however, they're not aligned with humans on how to utilize the knowledge. Based on these findings, we guide the LLMs in utilizing the event schema knowledge as memory leading to improvements on event reasoning.

We show how to convert the generating series of interpolated multiple zeta values, or multiple $t$ values, with repeating blocks of length 1 into hypergeometric series. Then we invoke creative telescoping on their generating functions, in some known cases for illustration, and in some apparently new cases, reducing them to polynomials in Riemann zeta values. The new evaluations, including $ \zeta^{1/2}(\{\bar2\}^n,3) $, $ \zeta^\star(\{1,3\}^n,1,2) $ and $ t^{1/2}(2,\{1\}^n,2) $, resolve some questions raised elsewhere, and seem to be non-trivial using other methods., Comment: 20 pages

The evolution of artificial intelligence (AI) and neural network theories has revolutionized the way software is programmed, shifting from a hard-coded series of codes, Software 1.0, to a vast neural network, Software 2.0. However, this transition in engineering software has faced challenges such as data scarcity, multi-modality of data, low model accuracy, and slow inference. Here, we propose a new network based on interpolation theories and tensor decomposition, the interpolating neural network (INN) to open the new era of Engineering Software 2.0 that unifies training, solving, and calibration. Instead of interpolating training data, a common notion in computer science, INN interpolates grid points in the physical space whose coordinates and values are trainable. INN features orders of magnitude fewer trainable parameters (or degrees of freedom for solving), faster training/solving, less inference cost, smaller memory footprint, and higher model accuracy compared to multi-layer perceptron (MLP) or physics-informed neural networks (PINN). Various numerical experiments that cover computer science and engineering domains demonstrate that INN can solve over Zetta scale (10^{21}) partial differential equations and train/calibrate a dataset with extraordinary accuracy but fewer parameters using only a single graphics processing unit (GPU)., Comment: 9 pages, 2 figures

We derive explicitly the adapted $2$-Wasserstein distance between non-degenerate Gaussian distributions on $\mathbb{R}^N$ and characterize the optimal bicausal coupling(s). This leads to an adapted version of the Bures-Wasserstein distance on the space of positive definite matrices., Comment: 14 pages, 2 figures. Revised

A representative volume element (RVE) is a reasonably small unit of microstructure that can be simulated to obtain the same effective properties as the entire microstructure sample. Finite element (FE) simulation of RVEs, as opposed to much larger samples, saves computational expense, especially in multiscale modeling. Therefore, it is desirable to have a framework that determines RVE size prior to FE simulations. Existing methods select the RVE size based on when the FE-simulated properties of samples of increasing size converge with insignificant statistical variations, with the drawback that many samples must be simulated. We propose a simulation-free alternative that determines RVE size based only on a micrograph. The approach utilizes a machine learning model trained to implicitly characterize the stochastic nature of the input micrograph. The underlying rationale is to view RVE size as the smallest moving window size for which the stochastic nature of the microstructure within the window is stationary as the window moves across a large micrograph. For this purpose, we adapt a recently developed Fisher score-based framework for microstructure nonstationarity monitoring. Because the resulting RVE size is based solely on the micrograph and does not involve any FE simulation of specific properties, it constitutes an RVE for any property of interest that solely depends on the microstructure characteristics. Through numerical experiments of simple and complex microstructures, we validate our approach and show that our selected RVE sizes are consistent with when the chosen FE-simulated properties converge.

The Internet of Things (IoT) is a communication scheme which allows various objects to exchange several types of information, enabling functions such as home automation, production management, healthcare, etc. In addition, energy-harvesting (EH) technology is considered for IoT environment in order to reduce the need for management and enhance maintainability. Moreover, since environments considering outdoor elements such as pedestrians, vehicles and drones have been on the rise recently, it is important to consider mobility when designing an IoT network management scheme. However, calculating the optimal relaying topology is considered as an NP-hard problem, and finishing computation for mobility environment before the channel status changes is important to prevent delayed calculation results. In this article, our objective is to calculate a sub-optimal relaying topology for stationary and mobile system within reasonable computation time. To achieve our objective, we validate an iterative balancing time slot allocation algorithm introduced in the previous study, and propose a guided-mutation genetic algorithm (GMGA) that modulates the mutation rate based on the channel status for rational exploration. Additionally, we propose a mobility-aware iterative relaying topology algorithm, which calculates relaying topology in a mobility environment using an inheritance of the sub-optimal relaying topology calculations. Simulation results verify that our proposed scheme effectively solves formulated IoT network problems compared to other conventional schemes, and also effectively handles IoT environments including mobility in terms of minimum rate budget and computation time., Comment: 15 pages, 8 figures; this work has been accepted for publication in IEEE Access. Accepted 24 July 2024

This paper introduces the combination of an advanced double-layer model with electrochemical kinetics to explain electrolyte effects on the alkaline hydrogen evolution reaction. It is known from experimental studies that the alkaline hydrogen evolution current shows a strong dependence on the concentration and identity of cations in the electrolyte, but is independent of pH. To explain these effects, we formulate the faradaic current in terms of the electric potential in the double layer, which is calculated using a mean-field model that takes into account the cation and anion sizes as well as the electric dipole moment of water molecules. We propose that the Volmer step consists of two activated processes: a water reduction sub-step, and a sub-step in which a hydroxide ion is transferred away from the reaction plane through the double layer. Either of these sub-steps may limit the rate. The proposed models for these sub-steps qualitatively explain experimental observations, including cation effects, pH-independence, and the trend reversal between gold and platinum electrodes. We also assess the quantitative accuracy of the water-reduction-limited current model; we suggest that the predicted functional relationship is valid as long as the hydrogen bonding structure of water near the electrode is sufficiently maintained., Comment: 45 pages, 18 figures. Submitted to Electrochimica Acta, accepted

Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of texts and table-cells). To this end, we propose visually guided generative text-layout pre-training, named ViTLP. Given a document image, the model optimizes hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. In addition, to address the limitation of processing long documents by Transformers, we introduce a straightforward yet effective multi-segment generative pre-training scheme, facilitating ViTLP to process word-intensive documents of any length. ViTLP can function as a native OCR model to localize and recognize texts of document images. Besides, ViTLP can be effectively applied to various downstream VDU tasks. Extensive experiments show that ViTLP achieves competitive performance over existing baselines on benchmark VDU tasks, including information extraction, document classification, and document question answering., Comment: Accepted to NAACL 2024 main conference. The first version of this paper was submitted to OpenReview (https://openreview.net/forum?id=ARtBIBAmNR) in June 2023

Entanglement, a puzzle since Einstein's time, has become increasingly crucial with the rise of quantum computation. But what exactly is it? Historically , entanglement can be precisely defined, but only negatively. In this article, we explore four interconnected definitions of entangled states.

The pervasive spread of misinformation and disinformation in social media underscores the critical importance of detecting media bias. While robust Large Language Models (LLMs) have emerged as foundational tools for bias prediction, concerns about inherent biases within these models persist. In this work, we investigate the presence and nature of bias within LLMs and its consequential impact on media bias detection. Departing from conventional approaches that focus solely on bias detection in media content, we delve into biases within the LLM systems themselves. Through meticulous examination, we probe whether LLMs exhibit biases, particularly in political bias prediction and text continuation tasks. Additionally, we explore bias across diverse topics, aiming to uncover nuanced variations in bias expression within the LLM framework. Importantly, we propose debiasing strategies, including prompt engineering and model fine-tuning. Extensive analysis of bias tendencies across different LLMs sheds light on the broader landscape of bias propagation in language models. This study advances our understanding of LLM bias, offering critical insights into its implications for bias detection tasks and paving the way for more robust and equitable AI systems

In the age of information overload and polarized discourse, understanding media bias has become imperative for informed decision-making and fostering a balanced public discourse. This paper presents IndiTag, an innovative online media bias analysis and annotation system that leverages fine-grained bias indicators to dissect and annotate bias in digital content. IndiTag offers a novel approach by incorporating large language models, bias indicator, vector database to automatically detect and interpret bias. Complemented by a user-friendly interface facilitating both automated bias analysis and manual annotation, IndiTag offers a comprehensive platform for in-depth bias examination. We demonstrate the efficacy and versatility of IndiTag through experiments on four datasets encompassing news articles from diverse platforms. Furthermore, we discuss potential applications of IndiTag in fostering media literacy, facilitating fact-checking initiatives, and enhancing the transparency and accountability of digital media platforms. IndiTag stands as a valuable tool in the pursuit of fostering a more informed, discerning, and inclusive public discourse in the digital age. The demonstration video can be accessed from https://youtu.be/Gt2T4T7DYqs. We release an online system for end users and the source code is available at https://github.com/lylin0/IndiTag.

Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a stark contrast to the well-explored domain of text-guided image inpainting. To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility. Specifically, we introduce a simple but efficient motion capture module to preserve motion consistency, and design an instance-aware region selection instead of a random region selection to obtain better textual controllability, and utilize a novel strategy to inject some personalized models into our CoCoCo model and thus obtain better model compatibility. Extensive experiments show that our model can generate high-quality video clips. Meanwhile, our model shows better motion consistency, textual controllability and model compatibility. More details are shown in [cococozibojia.github.io](cococozibojia.github.io).

In the cutting-edge domain of medical artificial intelligence (AI), remarkable advances have been achieved in areas such as diagnosis, prediction, and therapeutic interventions. Despite these advances, the technology for image segmentation faces the significant barrier of having to produce extensively annotated datasets. To address this challenge, few-shot segmentation (FSS) has been recognized as one of the innovative solutions. Although most of the FSS research has focused on human health care, its application in veterinary medicine, particularly for pet care, remains largely limited. This study has focused on accurate segmentation of the heart and left atrial enlargement on canine chest radiographs using the proposed deep prototype alignment network (DPANet). The PANet architecture is adopted as the backbone model, and experiments are conducted using various encoders based on VGG-19, ResNet-18, and ResNet-50 to extract features. Experimental results demonstrate that the proposed DPANet achieves the highest performance. In the 2way-1shot scenario, it achieves the highest intersection over union (IoU) value of 0.6966, and in the 2way-5shot scenario, it achieves the highest IoU value of 0.797. The DPANet not only signifies a performance improvement, but also shows an improved training speed in the 2way-5shot scenario. These results highlight our model's exceptional capability as a trailblazing solution for segmenting the heart and left atrial enlargement in veterinary applications through FSS, setting a new benchmark in veterinary AI research, and demonstrating its superior potential to veterinary medicine advances.

In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this challenge, we introduce StickerTAG, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers. Recognizing multiple tags for stickers becomes particularly challenging due to sticker tags usually are fine-grained attribute aware. Hence, we propose an Attentive Attribute-oriented Prompt Learning method, ie, Att$^2$PL, to capture informative features of stickers in a fine-grained manner to better differentiate tags. Specifically, we first apply an Attribute-oriented Description Generation (ADG) module to obtain the description for stickers from four attributes. Then, a Local Re-attention (LoR) module is designed to perceive the importance of local information. Finally, we use prompt learning to guide the recognition process and adopt confidence penalty optimization to penalize the confident output distribution. Extensive experiments show that our method achieves encouraging results for all commonly used metrics.

Using stickers in online chatting is very prevalent on social media platforms, where the stickers used in the conversation can express someone's intention/emotion/attitude in a vivid, tactful, and intuitive way. Existing sticker retrieval research typically retrieves stickers based on context and the current utterance delivered by the user. That is, the stickers serve as a supplement to the current utterance. However, in the real-world scenario, using stickers to express what we want to say rather than as a supplement to our words only is also important. Therefore, in this paper, we create a new dataset for sticker retrieval in conversation, called \textbf{StickerInt}, where stickers are used to reply to previous conversations or supplement our words\footnote{We believe that the release of this dataset will provide a more complete paradigm than existing work for the research of sticker retrieval in the open-domain online conversation.}. Based on the created dataset, we present a simple yet effective framework for sticker retrieval in conversation based on the learning of intention and the cross-modal relationships between conversation context and stickers, coined as \textbf{Int-RA}. Specifically, we first devise a knowledge-enhanced intention predictor to introduce the intention information into the conversation representations. Subsequently, a relation-aware sticker selector is devised to retrieve the response sticker via cross-modal relationships. Extensive experiments on the created dataset show that the proposed model achieves state-of-the-art performance in sticker retrieval\footnote{The dataset and source code of this work are released at \url{https://github.com/HITSZ-HLT/Int-RA}.}.

We point out a correspondence between many classical and $q$-hypergeometric Wilf-Zeilberger seeds, it enables us to find $q$-analogues of many classical hypergeometric series identities, and offers a conceptual explanation to why such $q$-analogue should exist.

The growing interest in Large Language Models (LLMs) for specialized applications has revealed a significant challenge: when tailored to specific domains, LLMs tend to experience catastrophic forgetting, compromising their general capabilities and leading to a suboptimal user experience. Additionally, crafting a versatile model for multiple domains simultaneously often results in a decline in overall performance due to confusion between domains. In response to these issues, we present the RolE Prompting Guided Multi-Domain Adaptation (REGA) strategy. This novel approach effectively manages multi-domain LLM adaptation through three key components: 1) Self-Distillation constructs and replays general-domain exemplars to alleviate catastrophic forgetting. 2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training. 3) Role Integration reuses and integrates a small portion of domain-specific data to the general-domain data, which are trained under the guidance of the central prompt. The central prompt is used for a streamlined inference process, removing the necessity to switch prompts for different domains. Empirical results demonstrate that REGA effectively alleviates catastrophic forgetting and inter-domain confusion. This leads to improved domain-specific performance compared to standard fine-tuned models, while still preserving robust general capabilities.

We modify the JKO scheme, which is a time discretization of Wasserstein gradient flows, by replacing the Wasserstein distance with more general transport costs on manifolds. We show when the cost function has a mixed Hessian which defines a Riemannian metric, our modified JKO scheme converges under suitable conditions to the corresponding Riemannian Fokker--Planck equation. Thus on a Riemannian manifold one may replace the (squared) Riemannian distance with any cost function which induces the metric. Of interest is when the Riemannian distance is computationally intractable, but a suitable cost has a simple analytic expression. We consider the Fokker--Planck equation on compact submanifolds with the Neumann boundary condition and on complete Riemannian manifolds with a finite drift condition. As an application we consider Hessian manifolds, taking as a cost the Bregman divergence., Comment: 27 pages

Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogues. Our research introduces PerLTQA, an innovative QA dataset that combines semantic and episodic memories, including world knowledge, profiles, social relationships, events, and dialogues. This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task. PerLTQA features two types of memory and a comprehensive benchmark of 8,593 questions for 30 characters, facilitating the exploration and application of personalized memories in Large Language Models (LLMs). Based on PerLTQA, we propose a novel framework for memory integration and generation, consisting of three main components: Memory Classification, Memory Retrieval, and Memory Synthesis. We evaluate this framework using five LLMs and three retrievers. Experimental results demonstrate that BERT-based classification models significantly outperform LLMs such as ChatGLM3 and ChatGPT in the memory classification task. Furthermore, our study highlights the importance of effective memory integration in the QA task.

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue. However, most previous work trained independent retrievers for each specific resource, resulting in sub-optimal performance and low efficiency. Thus, we propose a multi-task framework function as a universal retriever for three dominant retrieval tasks during the conversation: persona selection, knowledge selection, and response selection. To this end, we design a dual-encoder architecture consisting of a context-adaptive dialogue encoder and a candidate encoder, aiming to attention to the relevant context from the long dialogue and retrieve suitable candidates by simply a dot product. Furthermore, we introduce two loss constraints to capture the subtle relationship between dialogue context and different candidates by regarding historically selected candidates as hard negatives. Extensive experiments and analysis establish state-of-the-art retrieval quality both within and outside its training domain, revealing the promising potential and generalization capability of our model to serve as a universal retriever for different candidate selection tasks simultaneously.

Mendelian randomization uses genetic variants as instrumental variables to make causal inferences about the effects of modifiable risk factors on diseases from observational data. One of the major challenges in Mendelian randomization is that many genetic variants are only modestly or even weakly associated with the risk factor of interest, a setting known as many weak instruments. Many existing methods, such as the popular inverse-variance weighted (IVW) method, could be biased when the instrument strength is weak. To address this issue, the debiased IVW (dIVW) estimator, which is shown to be robust to many weak instruments, was recently proposed. However, this estimator still has non-ignorable bias when the effective sample size is small. In this paper, we propose a modified debiased IVW (mdIVW) estimator by multiplying a modification factor to the original dIVW estimator. After this simple correction, we show that the bias of the mdIVW estimator converges to zero at a faster rate than that of the dIVW estimator under some regularity conditions. Moreover, the mdIVW estimator has smaller variance than the dIVW estimator.We further extend the proposed method to account for the presence of instrumental variable selection and balanced horizontal pleiotropy. We demonstrate the improvement of the mdIVW estimator over the dIVW estimator through extensive simulation studies and real data analysis., Comment: 33 pages, 6 figures. Statistics in Medicine (2024)

Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets. Previous work on stance detection largely focused on pure texts. In this paper, we study multi-modal stance detection for tweets consisting of texts and images, which are prevalent in today's fast-growing social media platforms where people often post multi-modal messages. To this end, we create five new multi-modal stance detection datasets of different domains based on Twitter, in which each example consists of a text and an image. In addition, we propose a simple yet effective Targeted Multi-modal Prompt Tuning framework (TMPT), where target information is leveraged to learn multi-modal stance features from textual and visual modalities. Experimental results on our five benchmark datasets show that the proposed TMPT achieves state-of-the-art performance in multi-modal stance detection., Comment: ACL'24 Findings

Stance detection is critical for understanding the underlying position or attitude expressed toward a topic. Large language models (LLMs) have demonstrated significant advancements across various natural language processing tasks including stance detection, however, their performance in stance detection is limited by biases and spurious correlations inherent due to their data-driven nature. Our statistical experiment reveals that LLMs are prone to generate biased stances due to sentiment-stance spurious correlations and preference towards certain individuals and topics. Furthermore, the results demonstrate a strong negative correlation between stance bias and stance detection performance, underscoring the importance of mitigating bias to enhance the utility of LLMs in stance detection. Therefore, in this paper, we propose a Counterfactual Augmented Calibration Network (FACTUAL), which a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs. Further, to address the challenge of effectively learning bias representations and the difficulty in the generalizability of debiasing, we construct counterfactual augmented data. This approach enhances the calibration network, facilitating the debiasing and out-of-domain generalization. Experimental results on in-target and zero-shot stance detection tasks show that the proposed FACTUAL can effectively mitigate biases of LLMs, achieving state-of-the-art results.

The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trustworthiness of the generations become essential. However, current LLM confidence estimations in languages other than English remain underexplored. This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks. The benchmark comprises four meticulously checked and human-evaluate high-quality multilingual datasets for LA tasks and one for the LS task tailored to specific social, cultural, and geographical contexts of a language. Our experiments reveal that on LA tasks English exhibits notable linguistic dominance in confidence estimations than other languages, while on LS tasks, using question-related language to prompt LLMs demonstrates better linguistic dominance in multilingual confidence estimations. The phenomena inspire a simple yet effective native-tone prompting strategy by employing language-specific prompts for LS tasks, effectively improving LLMs' reliability and accuracy on LS tasks., Comment: Comments: n pages; Previously this version appeared as arXiv:2410.12478 which was submitted as a new work by accident