May 2023 arXiv papers — page 57

Salvatore Giorgi, Shreya Havaldar, Farhan Ahmed, Zuhaib Akhtar

We present metrics for evaluating dialog systems through a psychologically-grounded "human" lens in which conversational agents express a diversity of both states (e.g., emotion) and traits (e.g., personality), just as people do. We present five interpretable metrics from established psychology that are fundamental to human communication and relationships: e

Aditya Lahiri, Naigam Shah, Shivaank Agarwal, Vignesh Nandakumar

Wordle is a single-player word-based game where the objective is to guess the 5-letter word in a maximum of 6 tries. The game was released to the public in October 2021 and has since gained popularity with people competing against each other to maintain daily streaks and guess the word in a minimum number of tries. There have been works using probabilistic a

Akhila Yerukola, Xuhui Zhou, Elizabeth Clark, Maarten Sap

Most existing stylistic text rewriting methods and evaluation metrics operate on a sentence level, but ignoring the broader context of the text can lead to preferring generic, ambiguous, and incoherent rewrites. In this paper, we investigate integrating the preceding textual context into both the $\textit{rewriting}$ and $\textit{evaluation}$ stages of styli

Yi-Zhan Xu, Chih-Yao Chen, Cheng-Te Li

Unsupervised learning has grown in popularity because of the difficulty of collecting annotated data and the development of modern frameworks that allow us to learn from unlabeled data. Existing studies, however, either disregard variations at different levels of similarity or only consider negative samples from one batch. We argue that image pairs should ha

Weihua Zhang, Xiaodong Zhang, Barbara Dietz

We investigate the fluctuation properties in the eigenfrequency spectra of flat cylindrical microwave cavities that are homogeneously filled with magnetized ferrite. These studies are motivated by experiments in which only small pieces of ferrite were embedded in the cavity and magnetized with an external static magnetic field to induce partial time-reversal

Norbert Tihanyi, Ridhi Jain, Yiannis Charalambous, Mohamed Amine Ferrag

This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify vulnerabilities and extract counterexamples. These counterexamples are supported by mathematical proofs and the stack trace of th

Zefan Cai, Xin Zheng, Tianyu Liu, Xu Wang

In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added data, new intents would emerge and might have semantic entanglement with the existing intents, e.g. new intent

Nishant Balepur, Jie Huang, Samraj Moorjani, Hari Sundaram

When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question. While existing self-evaluation techniques aim to detect if such answers are correct, these techniques are unable to determine which criteria of the question are satisfied by the generated answers. To address this issue, we prop

Chaitanya K. Joshi, Arian R. Jamasb, Ramon Viñas, Charles Harris

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D conformational diversity. We introduce gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. gRNA

Dan Lin, Jiajing Wu, Qishuang Fu, Yunmei Yu

With the overall momentum of the blockchain industry, crypto-based crimes are becoming more and more prevalent. After committing a crime, the main goal of cybercriminals is to obfuscate the source of the illicit funds in order to convert them into cash and get away with it. Many studies have analyzed money laundering in the field of the traditional financial

Jan Helbing, Peter Hamm

Several ways to electronically synchronize different types of amplified femtosecond laser systems are presented, based on a single freely programmable electronics hardware: Arbitrary-detuning asynchronous optical sampling, as well as actively locking two femtosecond laser oscillators, albeit not necessarily to the same round-trip frequency. They allow us to

Nhat-Minh Nguyen, Minh-Ngoc Tran, Christopher Drovandi, David Nott

The Bayesian Synthetic Likelihood (BSL) method is a widely-used tool for likelihood-free Bayesian inference. This method assumes that some summary statistics are normally distributed, which can be incorrect in many applications. We propose a transformation, called the Wasserstein Gaussianization transformation, that uses a Wasserstein gradient flow to approx

Hamida Ashna, Ziaullah Momand

Fake currency, unauthorized imitation money lacking government approval, constitutes a form of fraud. Particularly in Afghanistan, the prevalence of fake currency poses significant challenges and detrimentally impacts the economy. While banks and commercial establishments employ authentication machines, the public lacks access to such systems, necessitating

Liangzu Peng, René Vidal

Block coordinate descent is an optimization paradigm that iteratively updates one block of variables at a time, making it quite amenable to big data applications due to its scalability and performance. Its convergence behavior has been extensively studied in the (block-wise) convex case, but it is much less explored in the non-convex case. In this paper we a

Hanming Ma, Dilip Bhoi, Jun Gouchi, Hiroyasu Sato

When pressurized, the heavy fermion compound CeNiC$_2$ reveals a rich electronic phase diagram and shows unconventional superconductivity with a transition temperature $T_c$ $\sim$ 3.7 K, the highest among Ce-based heavy fermion superconductors [S. Katano et al., Phys. Rev. B. 99, 100501(R) (2019)]. Understanding of this appearance of superconductivity in th

Dongxu Yue, Qin Guo, Munan Ning, Jiaxi Cui

Editing real facial images is a crucial task in computer vision with significant demand in various real-world applications. While GAN-based methods have showed potential in manipulating images especially when combined with CLIP, these methods are limited in their ability to reconstruct real images due to challenging GAN inversion capability. Despite the succ

Akshath Jain, David Rodriguez, Jose M. del Alamo, Norman Sadeh

Privacy policies are long, complex documents that end-users seldom read. Privacy labels aim to ameliorate these issues by providing succinct summaries of salient data practices. In December 2020, Apple began requiring that app developers submit privacy labels describing their apps' data practices. Yet, research suggests that app developers often struggle to

Naoya Ando

The conformal Gauss maps of time-like minimal surfaces in $E^3_1$ give sections of the time-like twistor spaces associated with the pull-back bundles such that the covariant derivatives are fully light-like, that is, these are either light-like or zero, and do not vanish at any point. For an oriented neutral $4n$-manifold $(M, h)$, if $J$ is an $h$-reversing

Per H. Enflo

In this paper we show that every bounded linear operator T on a Hilbert space H has a closed non-trivial invariant subspace.

Yuxi Xie, Guanzhen Li, Min-Yen Kan

We introduce ECHo (Event Causality Inference via Human-Centric Reasoning), a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios. ECHo employs real-world human-centric deductive information building on a television crime drama. ECHo requires the Theory-of-Mind (ToM) ability to understand and reason about social inter

Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov

Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a contrastive output distribution that amplifies the difference between the output probabilities when a model is used with and witho

Jaekwan Jeon, Dongsoo Shin

We prove Koll\'{a}r conjecture for weighted homogeneous surface singularities with big central node. More precisely, we show that every irreducible component of the deformation space of the singularity is parametrized by a certain partial resolution which is known as a $P$-resolution.

Valentín Vergara Hidd, Mailun Zhang, Simone Centellegher, Sam G. B. Roberts

A fundamental question of any new relationship is, will it last? Transient relationships, recently defined by the authors, are an ideal type of social tie to explore this question: these relationships are characterized by distinguishable starting and ending temporal points, linking the question of tie longevity to relationship finite lifetime. In this study,

Krishna C. Kalagarla, Dhruva Kartik, Dongming Shen, Rahul Jain

Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially observable. Moreover, it could encompass a team of multiple agents with a common objective but disparate information structures

Vyoma Raman, Eve Fleisig, Dan Klein

The impact of AI models on marginalized communities has traditionally been measured by identifying performance differences between specified demographic subgroups. Though this approach aims to center vulnerable groups, it risks obscuring patterns of harm faced by intersectional subgroups or shared across multiple groups. To address this, we draw on theories

Bashar Alhafni, Go Inoue, Christian Khairallah, Nizar Habash

Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been limited due to challenges such as data scarcity and language complexity. In this paper, we present the first results on Arabic GEC using two newly developed Transformer-based pret

A. D. Cameron, M. Bailes, D. J. Champion, P. C. C. Freire

PSR J1757$-$1854 is one of the most relativistic double neutron star binary systems known in our Galaxy, with an orbital period of $P_\text{b}=4.4\,\text{hr}$ and an orbital eccentricity of $e=0.61$. As such, it has promised to be an outstanding laboratory for conducting tests of relativistic gravity. We present the results of a 6-yr campaign with the 100-m

Jacopo Guanetti, Yeojun Kim, Xu Shen, Joel Donham

This work presents a novel hierarchical approach to increase Battery Electric Buses (BEBs) utilization in transit fleets. The proposed approach relies on three key components. A learning-based BEB digital twin cloud platform is used to accurately predict BEB charge consumption on a per vehicle, per driver, and per route basis, and accurately predict the time

Peyman Gholami, Robert Xiao

Depth cameras have found applications in diverse fields, such as computer vision, artificial intelligence, and video gaming. However, the high latency and low frame rate of existing commodity depth cameras impose limitations on their applications. We propose a fast and accurate depth map reconstruction technique to reduce latency and increase the frame rate

Junrui Xiao, Zhikai Li, Lianwei Yang, Qingyi Gu

Vision Transformers (ViTs) have emerged as the fundamental architecture for most computer vision fields, but the considerable memory and computation costs hinders their application on resource-limited devices. As one of the most powerful compression methods, binarization reduces the computation of the neural network by quantizing the weights and activation v

Nobuyuki Shukuno, Yuto Sano, Makoto Tsubota

We numerically study the dynamics of Faraday waves for Bose-Einstein condensates(BECs) trapped by anisotropic potentials using the three-dimensional Gross-Pitaevskii equation. In previous studies, Faraday waves were excited by periodic modulation of the interaction or potential; in contrast, this study systematically addresses the excitations of the two meth

Victoria Lin, Louis-Philippe Morency

Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model's decision-making process. This necessitates not only an interpretable model but also interpretable features. In particular, language must be featurized in a way that is interpretable while sti

Angelo Saadeh, Pierre Senellart, Stéphane Bressan

Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from disagreeing sources. For each query it receives, a truth-finding algorithm predicts a truth value of the answer, possibly updat

Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang

Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected examples. We present a cross-entropy difference (CED) method for selecting in-context demonstrations. Our method is based o

Barry Menglong Yao, Sijia Wang, Yu Chen, Qifan Wang

We propose attribute-aware multimodal entity linking, where the input consists of a mention described with a text paragraph and images, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where each entity is also accompanied by a text description, visual images, and a collection of attributes that present the met

Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn, Artemis Panagopoulou

Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a new task of generating visual metaphors from linguistic metaphors. This is a challenging task for diffusion-based text-

Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai, Marc Delcroix

Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise robustness of the SSL is one of the important challenges to expanding its application. We can use speech enhancement (SE) to tackle this issue. However, the mismatch between the SE

Hao Chen, Haotian Zhang, Keyan Chen, Chenyao Zhou

Most contemporary supervised Remote Sensing (RS) image Change Detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the need for cross-resolution change detection, aka, CD based on bitemporal images with different spatial resolutions. Given training samples of a fixed bitemporal resolution difference (

Manil T. Mohan

In this article, we consider two- and three- dimensional stochastic convective Brinkman-Forchheimer extended Darcy (CBFeD) equations \begin{equation*} \frac{\partial \boldsymbol{u}}{\partial t}-\mu \Delta\boldsymbol{u}+(\boldsymbol{u}\cdot\nabla)\boldsymbol{u}+\alpha|\boldsymbol{u}|^{q-1}\boldsymbol{u}+\beta|\boldsymbol{u}|^{r-1}\boldsymbol{u}+\nabla p=\bold

Dongxu Li, Junnan Li, Steven C. H. Hoi

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consu

Michael Kranzlein, Nathan Schneider, Kevin Tobia

Most judicial decisions involve the interpretation of legal texts; as such, judicial opinion requires the use of language as a medium to comment on or draw attention to other language. Language used this way is called metalanguage. We develop an annotation schema for categorizing types of legal metalanguage and apply our schema to a set of U.S. Supreme Court

Ashutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras

Reinforcement Learning with Human Feedback (RLHF) is the most prominent method for Language Model (LM) alignment. However, RLHF is an unstable and data-hungry process that continually requires new high-quality LM-generated data for finetuning. We introduce Advantage-Leftover Lunch RL (A-LoL), a new class of offline policy gradient algorithms that enable RL t

Linhan Zhang, Qian Chen, Wen Wang, Yuxin Jiang

Definition modeling is an important task in advanced natural language applications such as understanding and conversation. Since its introduction, it focus on generating one definition for a target word or phrase in a given context, which we refer to as Single Definition Modeling (SDM). However, this approach does not adequately model the correlations and pa

Yueqi Song, Catherine Cui, Simran Khanuja, Pengfei Liu

Despite the major advances in NLP, significant disparities in NLP system performance across languages still exist. Arguably, these are due to uneven resource allocation and sub-optimal incentives to work on less resourced languages. To track and further incentivize the global development of equitable language technology, we introduce GlobalBench. Prior multi

Daehee Park, Hobin Ryu, Yunseo Yang, Jegyeong Cho

Understanding the interaction between multiple agents is crucial for realistic vehicle trajectory prediction. Existing methods have attempted to infer the interaction from the observed past trajectories of agents using pooling, attention, or graph-based methods, which rely on a deterministic approach. However, these methods can fail under complex road struct

Ximo Gallud, Paulo C. Lozano

Electrohydrodynamic modeling and experimental observations indicate that the ion evaporation current emitted by passively-fed electrospray sources is independent of the electrical conductivity of the ionic liquid. This contrasts with cone-jet electrosprays, in which current depends on conductivity at fixed flow rates. The current in the pure ionic regime is

Yixiong Yan, Liangzhu Cheng, Yongxu Li, Xinjuan Tuo

Fisheye cameras are widely employed in automatic parking, and the video stream object detection (VSOD) of the fisheye camera is a fundamental perception function to ensure the safe operation of vehicles. In past research work, the difference between the output of the deep learning model and the actual situation at the current moment due to the existence of d

Mingyang Yi, Jiacheng Sun, Zhenguo Li

The diffusion probabilistic generative models are widely used to generate high-quality data. Though they can synthetic data that does not exist in the training set, the rationale behind such generalization is still unexplored. In this paper, we formally define the generalization of the generative model, which is measured by the mutual information between the

Haoyi Qiu, Zi-Yi Dou, Tianlu Wang, Asli Celikyilmaz

Model-based evaluation metrics (e.g., CLIPScore and GPTScore) have demonstrated decent correlations with human judgments in various language generation tasks. However, their impact on fairness remains largely unexplored. It is widely recognized that pretrained models can inadvertently encode societal biases, thus employing these models for evaluation purpose

Jiashu Xu, Mingyu Derek Ma, Fei Wang, Chaowei Xiao

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject backdoors by issuing very few malicious instructions (~1000 tokens) and control model behavior through data poisoning, withou

Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee

Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery. Moreover, recent advances on fast convergence in games are limited to no-regret algorithms such as online mirror descent, which satisfy stability. In this paper, we first give co

Yichen Chi, Junhao Gu, Jiamiao Zhang, Wenming Yang

Due to the limitations of capture devices and scenarios, egocentric videos frequently have low visual quality, mainly caused by high compression and severe motion blur. With the increasing application of egocentric videos, there is an urgent need to enhance the quality of these videos through super-resolution. However, existing Video Super-Resolution (VSR) w

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabás Póczos

Due to the prohibitively high cost of creating error correction datasets, most Factual Claim Correction methods rely on a powerful verification model to guide the correction process. This leads to a significant drop in performance in domains like scientific claims, where good verification models do not always exist. In this work, we introduce SciFix, a scien

Yushan Su, Vishvak Murahari, Karthik Narasimhan, Kai Li

As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications. Prior work has investigated techniques like model pruning, knowledge distillation, and data multiplexing to increase model throughput without sacrificing accuracy. In this paper, we combine two such methods -

Sheng Shen, Le Hou, Yanqi Zhou, Nan Du

Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches, as we find that MoE models benefit more from instruction tun

Zezhong Zhang, Ted Yuan

Online controlled experiments have emerged as industry gold standard for assessing new web features. As new web algorithms proliferate, experimentation platform faces an increasing demand on the velocity of online experiments, which encourages adaptive traffic testing methods to speed up identifying best variant by efficiently allocating traffic. This paper

Ting Wang, Petr Plechac, Jaroslaw Knap

We develop a class of data-driven generative models that approximate the solution operator for parameter-dependent partial differential equations (PDE). We propose a novel probabilistic formulation of the operator learning problem based on recently developed generative denoising diffusion probabilistic models (DDPM) in order to learn the input-to-output mapp

Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang

Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tasks to compare outputs from various systems, complementing existing automatic metrics. Despite their significance, however, there has been limited research probing these pairwise or

R. Thomas McCoy, Thomas L. Griffiths

Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Bayesian models that build in strong inductive biases - factors that guide generalization - have been successful at explaining how humans might generalize from few examples in controlled sett

Zihui Wu, Haichang Gao, Bingqian Zhou, Ping Wang

\emph{Consistent teaching} is an effective paradigm for implementing knowledge distillation (KD), where both student and teacher models receive identical inputs, and KD is treated as a function matching task (FunMatch). However, one limitation of FunMatch is that it does not account for the transfer of adversarial robustness, a model's resistance to adversar

Shizhuo Dylan Zhang, Curt Tigges, Stella Biderman, Maxim Raginsky

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to what degree popular neural architectures like transformers are capable of modeling that information. This paper examines the behavior of neura

Dorothy Kronick, Francisco Rodríguez

Venezuela has suffered three economic catastrophes since independence: one each in the nineteenth, twentieth, and twenty-first centuries. Prominent explanations for this trilogy point to the interaction of class conflict and resource dependence. We turn attention to intra-class conflict, arguing that the most destructive policy choices stemmed not from the r

Yan Fang, Artem M. Rumyantsev, Angelika E. Neitzel, Heyi Liang

Polyelectrolyte complexation plays an important role in materials science and biology. The internal structure of the resultant polyelectrolyte complex (PEC) phase dictates properties such as physical state, response to external stimuli, and dynamics. Small-angle scattering experiments with X-rays and neutrons have revealed structural similarities between PEC

Jingtao Guo, Ivan Wang-Hei Ho

Nowadays, Coronavirus disease (COVID-19) has become a global pandemic because of its fast spread in various countries. To build an anti-epidemic barrier, self-isolation is required for people who have been to any at-risk places or have been in close contact with infected people. However, existing camera or wearable device-based monitoring systems may present

Dheeraj Mekala, Adithya Samavedhi, Chengyu Dong, Jingbo Shang

Deep neural classifiers trained with cross-entropy loss (CE loss) often suffer from poor calibration, necessitating the task of out-of-distribution (OOD) detection. Traditional supervised OOD detection methods require expensive manual annotation of in-distribution and OOD samples. To address the annotation bottleneck, we introduce SELFOOD, a self-supervised

Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou

Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it is hard to precisely estimate the parameters of underlying causal models in practice. The rise of black-box LLMs also ma

Keith Paarporn, Shouhuai Xu

In this paper, we analyze the infection spreading dynamics of malware in a population of cyber nodes (i.e., computers or devices). Unlike most prior studies where nodes are reactive to infections, in our setting some nodes are active defenders meaning that they are able to clean up malware infections of their neighboring nodes, much like how spreading malwar

Xiaoyang Song, Akshat Gupta, Kiyan Mohebbizadeh, Shujie Hu

Have Large Language Models (LLMs) developed a personality? The short answer is a resounding "We Don't Know!". In this paper, we show that we do not yet have the right tools to measure personality in language models. Personality is an important characteristic that influences behavior. As LLMs emulate human-like intelligence and performance in various tasks, a

Rahulkrishna Yandrapally, Saurabh Sinha, Rachel Tzoref-Brill, Ali Mesbah

Modern web applications make extensive use of API calls to update the UI state in response to user events or server-side changes. For such applications, API-level testing can play an important role, in-between unit-level testing and UI-level (or end-to-end) testing. Existing API testing tools require API specifications (e.g., OpenAPI), which often may not be

Jiajia Li, Dong Chen, Xinda Qi, Zhaojian Li

The past decade has witnessed many great successes of machine learning (ML) and deep learning (DL) applications in agricultural systems, including weed control, plant disease diagnosis, agricultural robotics, and precision livestock management. Despite tremendous progresses, one downside of such ML/DL models is that they generally rely on large-scale labeled

Tongtong Fang, Nan Lu, Gang Niu, Masashi Sugiyama

Distribution shift (DS) may have two levels: the distribution itself changes, and the support (i.e., the set where the probability density is non-zero) also changes. When considering the support change between the training and test distributions, there can be four cases: (i) they exactly match; (ii) the training support is wider (and thus covers the test sup

Xinyue Li, Rishi Sonthalia

The relationship between the number of training data points, the number of parameters, and the generalization capabilities of models has been widely studied. Previous work has shown that double descent can occur in the over-parameterized regime and that the standard bias-variance trade-off holds in the under-parameterized regime. These works provide multiple

Benfeng Xu, An Yang, Junyang Lin, Quan Wang

The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts. In this paper, we propose ExpertPrompting to elicit the potential of LLMs to answer as distinguished experts. We first utilize In-Context Learning to automatically synthesize detailed and customized descriptions of the expert

Bocong Chen, Yuqing Fu, Hongwei Liu

Let C be an arbitrary simple-root cyclic code and let G be the subgroup of Aut(C) (the automorphism group of C) generated by the multiplier, the cyclic shift and the scalar multiplications. To the best of our knowledge, the subgroup G is the largest subgroup of Aut(C). In this paper, an explicit formula, in some cases an upper bound, for the number of orbits

Yinghan Long, Sayeed Shafayet Chowdhury, Kaushik Roy

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained applications. To counter this, our approach is to divide the whole sequence into segments and apply attention to the indiv

Yu Chen, Jin Cheng, Shuai Lu, Masahiro Yamamoto

It is well known that Cauchy problem for Laplace equations is an ill-posed problem in Hadamard's sense. Small deviations in Cauchy data may lead to large errors in the solutions. It is observed that if a bound is imposed on the solution, there exists a conditional stability estimate. This gives a reasonable way to construct stable algorithms. However, it is

Shi Yu, Chenghao Fan, Chenyan Xiong, David Jin

Common document ranking pipelines in search systems are cascade systems that involve multiple ranking layers to integrate different information step-by-step. In this paper, we propose a novel re-ranker Fusion-in-T5 (FiT5), which integrates text matching information, ranking features, and global document information into one single unified model via templated

Zehong Zhou, Fei Zhou, Guoping Qiu

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively annotated data. This paper presents a novel BIQA method which overcomes this fundamental obstacle. Specifically, we design a

Lachlan Ewen MacDonald, Jack Valmadre, Simon Lucey

We present a new approach to understanding the relationship between loss curvature and input-output model behaviour in deep learning. Specifically, we use existing empirical analyses of the spectrum of deep network loss Hessians to ground an ansatz tying together the loss Hessian and the input-output Jacobian over training samples during the training of deep

Jian Wu, Yicheng Xu, Yan Gao, Jian-Guang Lou

Hybrid Question-Answering (HQA), which targets reasoning over tables and passages linked from table cells, has witnessed significant research in recent years. A common challenge in HQA and other passage-table QA datasets is that it is generally unrealistic to iterate over all table rows, columns, and linked passages to retrieve evidence. Such a challenge mad

James A. Michaelov, Benjamin K. Bergen

Does inverse scaling only occur as a function of model size, or can it also occur over the course of training? We carry out an exploratory study investigating whether the performance of language models on specific tasks can decrease (while general performance remains high) during training on the language modeling task. We find 8 tasks on which Pythia 12B (Bi

Zhichao Liu, Zhouyu Lu, Ali-akbar Agha-mohammadi, Konstantinos Karydis

The article develops an impact-resilient aerial robot (s-ARQ) equipped with a compliant arm to sense contacts and reduce collision impact and featuring a real-time contact force estimator and a non-linear motion controller to handle collisions while performing aggressive maneuvers and stabilize from high-speed wall collisions. Further, a new collision-inclus

Masahiro Kojima

Information borrowing from historical data is gaining attention in clinical trials of rare and pediatric diseases, where statistical power may be insufficient for confirmation of efficacy if the sample size is small. Although Bayesian information borrowing methods are well established, test-then-pool and equivalence-based test-then-pool methods have recently

Zhonghai Zhao, Yang Xu, Jia Liu, Li Zhao

The rapid development and integration of automotive manufacturing, sensor, and communication technologies have facilitated the emergence of the Internet of Vehicles (IoV). However, the explosive growing demand for parking spots has become a challenging issue to be addressed in IoV. In this paper, we propose a novel Smart Parking System (SPS) for IoV by apply

Zhongjie Duan, Chengyu Wang, Cen Chen, Jun Huang

In recent years, diffusion models have become the most popular and powerful methods in the field of image synthesis, even rivaling human artists in artistic creativity. However, the key issue currently limiting the application of diffusion models is its extremely slow generation process. Although several methods were proposed to speed up the generation proce

Woojeong Jin, Subhabrata Mukherjee, Yu Cheng, Yelong Shen

Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks. However, such generalization to vision-language tasks including grounding and generation tasks has been under-explored; existing few-shot VL models struggle to handle tasks that involve object grounding and multiple imag

Yiheng Jiang, Yuanbo Xu, Yongjian Yang, Funing Yang

In this paper, we present a MLP-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications. In designing Triangular Mixer, we simplify the cross-token operation in MLP as the basic matrix multiplication, and drop the lower-triangle neurons of the weight matrix to block the anti-chronological o

Kangfu Mei, Mo Zhou, Vishal M. Patel

Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. While DPF shows great potential for unifying data generation of various modalities including images, videos, and 3D geometry, it does not scale to a higher data resolution. This can be attributed to the ``scaling property'', where it is difficult f

Xiao Liang, Shan Lin, Fei Liu, Dimitri Schreiber

Deformable Image Registration (DIR) plays a significant role in quantifying deformation in medical data. Recent Deep Learning methods have shown promising accuracy and speedup for registering a pair of medical images. However, in 4D (3D + time) medical data, organ motion, such as respiratory motion and heart beating, can not be effectively modeled by pair-wi

Xinmei Yang, Abhishek Arora, Shao-Yu Jheng, Melissa Dell

Record linkage is a bedrock of quantitative social science, as analyses often require linking data from multiple, noisy sources. Off-the-shelf string matching methods are widely used, as they are straightforward and cheap to implement and scale. Not all character substitutions are equally probable, and for some settings there are widely used handcrafted list

Hao Zou, Zae Myung Kim, Dongyeop Kang

This survey paper provides a comprehensive review of the use of diffusion models in natural language processing (NLP). Diffusion models are a class of mathematical models that aim to capture the diffusion of information or signals across a network or manifold. In NLP, diffusion models have been used in a variety of applications, such as natural language gene

Ben Kane, Zichen Yang

In this paper, we consider mixed sums of generalized polygonal numbers. Specifically, we obtain a finiteness condition for universality of such sums; this means that it suffices to check representability of a finite subset of the positive integers in order to conclude that the sum of generalized polygonal numbers represents every positive integer. The sub-cl

Yexing Song, Meilin Wang, Zhijing Yang, Xiaoyu Xian

The capability of video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. However, applying the VSR model to real-world video with unknown and complex degradation remains a challenging task. First, existing degradation metrics in most VSR methods are not able to effectively simulate real-

Artur Jesslen, Guofeng Zhang, Angtian Wang, Wufei Ma

Discriminative models for object classification typically learn image-based representations that do not capture the compositional and 3D nature of objects. In this work, we show that explicitly integrating 3D compositional object representations into deep networks for image classification leads to a largely enhanced generalization in out-of-distribution scen

Feng Wang, Chuan-Fu Yang

We consider the vector-impulsive Sturm-Liouville problem with Neumann conditions. The Ambarzumyan$^{\textbf{,}}$s theorem for the problem is proved, which states that if the eigenvalues of the problem coincide with those of the zero potential, then the potential is zero.

Tian Xia, Luca Scardovi

This paper presents a synchronization criterion for networks of infinite-dimensional linear systems, extending a previous result for finite-dimensional systems. Our result, established in the general framework of input-output relations, requires an additional input-output stability property, compared to the finite-dimensional counterpart. We show that this t

Kuan-Ming Hung, Tung-Ho Shieh

In cuprate superconductors, superconductivity is consistently accompanied by antiferromagnetism. This raises the question of a potential causal link between superconductivity and antiferromagnetic mechanisms. In this study, we consider the non-local Coulomb interaction and solve the single-particle Green function exactly. The exact solution shows the existen

Michael McGuigan

We identify the Riemann Xi function as the Baker-Akhiezer function for a (p,1) two matrix model as p goes to infinity. We solve the two matrix model using biorthogonal polynomials and study the zeros of the polynomials in the double scaling limit as N goes to infinity. We find zeros off the critical line at finite N which possibly go to infinity as N goes to

Naihao Deng, Xinliang Frederick Zhang, Siyang Liu, Winston Wu

Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotator

Honglin Wen

Probabilistic wind power forecasting approaches have significantly advanced in recent decades. However, forecasters often assume data completeness and overlook the challenge of missing values resulting from sensor failures, network congestion, etc. Traditionally, this issue is addressed during the data preprocessing procedure using methods such as deletion a