March 2024 arXiv papers — page 4

Xuewen Zhang, Minghao Han, Xunyuan Yin

In this paper, we propose an efficient data-driven predictive control approach for general nonlinear processes based on a reduced-order Koopman operator. A Kalman-based sparse identification of nonlinear dynamics method is employed to select lifting functions for Koopman identification. The selected lifting functions are used to project the original nonlinea

Hao Gong, Michel Desvignes

Decomposition of skin pigment plays an important role in medical fields. Human skin can be decomposed into two primitive components, hemoglobin and melanin. It is our goal to apply these results for diagnosis of skin cancer. In this paper, various methods for skin pigment decomposition are reviewed comparatively and the performance of each method is evaluate

Yuan Gao, Jian Huang, Yuling Jiao, Shurong Zheng

Continuous normalizing flows (CNFs) are a generative method for learning probability distributions, which is based on ordinary differential equations. This method has shown remarkable empirical success across various applications, including large-scale image synthesis, protein structure prediction, and molecule generation. In this work, we study the theoreti

Tim Dalby

Another proof that uniformly nonsquare Banach spaces have the fixed point property is presented.

Jiaming Deng, Zhenglin Chen, Minjiang Chen, Lulu Xu

Mycoplasma pneumoniae pneumonia (MPP) poses significant diagnostic challenges in pediatric healthcare, especially in regions like China where it's prevalent. We introduce PneumoniaAPP, a mobile application leveraging deep learning techniques for rapid MPP detection. Our approach capitalizes on convolutional neural networks (CNNs) trained on a comprehensive d

Jiading Li, Zhiyu Zhu, Jinhui Hou, Junhui Hou

This paper tackles the problem of passive gaze estimation using both event and frame data. Considering the inherently different physiological structures, it is intractable to accurately estimate gaze purely based on a given state. Thus, we reformulate gaze estimation as the quantification of the state shifting from the current state to several prior register

Andrii Arman, Andriy Bondarenko, Andriy Prymak

Let $H_n$ be the minimal number such that any $n$-dimensional convex body can be covered by $H_n$ translates of interior of that body. Similarly $H_n^s$ is the corresponding quantity for symmetric bodies. It is possible to define $H_n$ and $H_n^s$ in terms of illumination of the boundary of the body using external light sources, and the famous Hadwiger's cov

Mubariz Zaffar, Liangliang Nan, Julian F. P. Kooij

In Visual Place Recognition (VPR) the pose of a query image is estimated by comparing the image to a map of reference images with known reference poses. As is typical for image retrieval problems, a feature extractor maps the query and reference images to a feature space, where a nearest neighbor search is then performed. However, till recently little attent

Charles Dove, Jatearoon Boondicharern, Laura Waller

Simulators based on neural networks offer a path to orders-of-magnitude faster electromagnetic wave simulations. Existing models, however, only address narrowly tailored classes of problems and only scale to systems of a few dozen degrees of freedom (DoFs). Here, we demonstrate a single, unified model capable of addressing scattering simulations with thousan

Tongtong Zhang, Xian Wei, Yuanxiang Li

Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs. We introduce the trick named Deep Extrinsic Manifold Representation (DEMR) for visual tasks in this context. DEMR incorporates extrinsic manifold e

Timothy C. Y. Chan, Jangwon Park, Vahid Sarhangian

We consider the problem of load balancing in parallel queues by transferring customers between them at discrete points in time. Holding costs accrue as customers wait in the queue, while transfer decisions incur both fixed (setup) costs and variable costs that increase with the number of transfers and travel distance, and vary by transfer direction. Our work

Ali Emre Eysen, Vesko Valov

We consider uniformly continuous surjections between $C_p(X)$ and $C_p(Y)$ (resp, $C_p^*(X)$ and $C_p^*(Y$)) and show that if $X$ has some dimensional-like properties, then so does $Y$. In particular, we prove that if $T:C_p(X)\to C_p(Y)$ is a continuous linear surjection, then $\dim Y=0$ if $\dim X=0$. This provides a positive answer to a question raised by

Yasuhiro Ishitsuka, Takashi Taniguchi, Frank Thorne, Stanley Yao Xiao

We investigate exponential sums over singular binary quartic forms, proving an explicit formula for the finite field Fourier transform of this set. Our formula shares much in common with analogous formulas proved previously for other vector spaces, but also exhibits a striking new feature: the point counting function $a_p(E) = p + 1 - \#E(\mathbb{F}_p)$ asso

Lingxuan Wu, Xiao Yang, Yinpeng Dong, Liuwei Xie

The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information to counter adversarial patches, often failing to be confronted with unseen or adaptive adversarial attacks and easily e

Satoko Iida, Ryota Yasudo

Quadratic Assignment Problem (QAP) is a practical combinatorial optimization problems that has been studied for several years. Since it is NP-hard, solving large problem instances of QAP is challenging. Although heuristics can find semi-optimal solutions, the execution time significantly increases as the problem size increases. Recently, solving combinatoria

Anurag Gupta, Vikram Krishnamurthy, Brian M. Sadler

This paper introduces a novel non-parametric change detection algorithm to identify eclipse attacks on a blockchain network; the non-parametric algorithm relies only on the empirical mean and variance of the dataset, making it highly adaptable. An eclipse attack occurs when malicious actors isolate blockchain users, disrupting their ability to reach consensu

S Amrutha, Mousumi Das, Jyoti Yadav

We present a Far-Ultraviolet (FUV) study of sixteen star-forming dwarf galaxies (SFDGs) using the Ultraviolet Imaging Telescope (UVIT). Morphologically, SFDGs are classified as dwarf spirals, dwarf irregulars, and blue compact dwarfs (BCDs). We extracted the star-forming complexes (SFCs) from the sample galaxies, derived their sizes, and estimated the FUV+24

Patricia Commins

The faces of the braid arrangement form a monoid. The associated monoid algebra -- the face algebra -- is well-studied, especially in relation to card shuffling and other Markov chains. In this paper, we explore the action of the symmetric group on the face algebra from the perspective of invariant theory. Bidigare proved the invariant subalgebra of the face

Jialin Chen, Jan Eric Lenssen, Aosong Feng, Weihua Hu

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Co

Jean-Philippe Lessard, Alessandro Pugliese

This paper introduces a novel computer-assisted method for detecting and constructively proving the existence of cusp bifurcations in differential equations. The approach begins with a two-parameter continuation along which a tool based on the theory of Poincar\'e index is employed to identify the presence of a cusp bifurcation. Using the approximate cusp lo

Teruhisa Sugimoto

Sets of three types of convex pentagons that are aperiodic with no matching conditions on the edges are created from a chiral aperiodic monotile Tile(1, 1). This method divides the interior of Tile(1,1) into five convex polygons with five or more edges, and we have so far identified four methods.

J. Mumford, D. Kamp, D. H. J. O'Dell

We perform a theoretical study of the coupled dynamics of two species of Bose-Einstein condensates (BECs) in a double well potential where both the tunneling and the interatomic interactions are driven periodically in time. The population difference between the wells of each species gives rise to a two dimensional lattice in Fock space with dimensions given

Haoxuan Qu, Yujun Cai, Jun Liu

Skeleton-based action recognition has attracted lots of research attention. Recently, to build an accurate skeleton-based action recognizer, a variety of works have been proposed. Among them, some works use large model architectures as backbones of their recognizers to boost the skeleton data representation capability, while some other works pre-train their

Jing-Hui Huang, Kyle M. Jordan, Adetunmise C. Dada, Xiang-Yun Hu

We introduce an ultra-sensitive interferometric protocol that combines weak value amplification (WVA) with traditional interferometry. This protocol WVA + interferometry uses weak value amplification of the relative delay between two paths to enhance interferometric sensitivity. As an example, we demonstrate a proof-of-principle experiment that achieves few-

Hritik Bansal, Ashima Suvarna, Gantavya Bhatt, Nanyun Peng

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the generations are evaluated within an identical context. While effective to such conditional preferences often fail to encompa

Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Sihan Liu

We study the efficient learnability of low-degree polynomial threshold functions (PTFs) in the presence of a constant fraction of adversarial corruptions. Our main algorithmic result is a polynomial-time PAC learning algorithm for this concept class in the strong contamination model under the Gaussian distribution with error guarantee $O_{d, c}(\text{opt}^{1

Yuji Saikai

Accurate and precise crop yield prediction is invaluable for decision making at both farm levels and regional levels. To make yield prediction, crop models are widely used for their capability to simulate hypothetical scenarios. While accuracy and precision of yield prediction critically depend on weather inputs to simulations, surprisingly little attention

Farbod Ekbatani, Rad Niazadeh, Pranav Nuti, Jan Vondrak

Most of the literature on online algorithms in revenue management focuses on settings with irrevocable decisions, where once a decision is made upon the arrival of a new input, it cannot be canceled later. Motivated by modern applications -- such as cloud spot markets, selling banner ads, or online hotel booking -- we introduce and study "prophet inequalitie

Anoop Kumar, Suresh Dodda, Navin Kamuni, Venkata Sai Mahesh Vuppalapati

Video games have played a crucial role in entertainment since their development in the 1970s, becoming even more prominent during the lockdown period when people were looking for ways to entertain them. However, at that time, players were unaware of the significant impact that playtime could have on their feelings. This has made it challenging for designers

Chun Fu, Hussain Kazmi, Matias Quintana, Clayton Miller

Advances in machine learning and increased computational power have driven progress in energy-related research. However, limited access to private energy data from buildings hinders traditional regression models relying on historical data. While generative models offer a solution, previous studies have primarily focused on short-term generation periods (e.g.

Yuxiao Liu, Zhe Li, Yebin Liu, Haoqian Wang

To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos, our method initially back-projects all the available images in the training videos to the

Anoop Kumar, Suresh Dodda, Navin Kamuni, Rajeev Kumar Arora

This study examines the effects of macroeconomic policies on financial markets using a novel approach that combines Machine Learning (ML) techniques and causal inference. It focuses on the effect of interest rate changes made by the US Federal Reserve System (FRS) on the returns of fixed income and equity funds between January 1986 and December 2021. The ana

Congpei An, Jiashu Ran

This paper investigates the algebraic properties of the hyperinterpolation class $\mathbf{HC}(\mathbb{S}^d)$ on the unit sphere $ \mathbb{S}^d $. We focus on operators derived from the classical hyperinterpolation with bounded $ L_2 $ operator norms. By utilizing a discrete (semi) inner product framework, we develop the theory of hyper self-adjoint operators

Neil Mallinar, Austin Zane, Spencer Frei, Bin Yu

Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a notable gap still exists in the theoretical understanding of transfer learning. In-distribution research on high-dimensional

Yao Ni, Piotr Koniusz

Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overfitting and unstable training. Batch Normalization (BN), despite being known for enhancing generalization and training stability, has rarely

Kyoungtae Ji, Sangjae Bae, Nan Li, Kyoungseok Han

This paper presents a game-theoretic strategy for racing, where the autonomous ego agent seeks to block a racing opponent that aims to overtake the ego agent. After a library of trajectory candidates and an associated reward matrix are constructed, the optimal trajectory in terms of maximizing the cumulative reward over the planning horizon is determined bas

Wei Ren, Xi Zhang, Ziyan Zhu, Moosa Khan

Electron collimation via a graphene pn-junction allows electrostatic control of ballistic electron trajectories akin to that of an optical circuit. Similar manipulation of novel correlated electronic phases in twisted-bilayer graphene (tBLG) can provide additional probes to the underlying physics and device components towards advanced quantum electronics. In

Yixiu Xiao, Hongze Li

An explicit upper bound is established for the least non-trivial integer zero of an arbitrary cubic form $C \in \mathbb{Z}[X_1,...,X_n],$ provided that $n \geq 14.$

Oleksandr V. Marchukov, Andrea Trombettoni, Giuseppe Mussardo, Maxim Olshanii

The famous Goldbach conjecture states that any even natural number $N$ greater than $2$ can be written as the sum of two prime numbers $p^{\text{(I)}}$ and $p^{\text{(II)}}$. In this article we propose a quantum analogue device that solves the following problem: given a small prime $p^{\text{(I)}}$, identify a member $N$ of a $\mathcal{N}$-strong set even nu

Jacky Kumar, Emanuele Mereghetti

A fully generic treatment of electric dipole moments (EDMs) is presented in the CP-violating and flavor-conserving weak effective field theory (WET) with five flavors of quarks and three flavors of leptons. We systematically analyze leading contributions to EDMs originating from QCD and QED renormalization group running between the electroweak scale and low

Gustav Lehrer, Ruibin Zhang

We define a class of monoidal categories whose morphisms are diagrams, and which are enhancements and generalisations of the Brauer category obtained by adjoining infinitesimal braids, "coupons" and poles. Properties of these categories are explored, particularly diagrammatic equations. We construct functors from certain of them to categories of representati

Al Jaber Mahmud, Amir Hossain Raj, Duc M. Nguyen, Weizi Li

This paper proposes a new control algorithm for human-robot co-transportation using a robot manipulator equipped with a mobile base and a robotic arm. We integrate the regular Model Predictive Control (MPC) with a novel pose optimization mechanism to more efficiently mitigate disturbances (such as human behavioral uncertainties or robot actuation noise) duri

Qiankun Liu, Yuqi Jiang, Zhentao Tan, Dongdong Chen

Transformer based methods have achieved great success in image inpainting recently. However, we find that these solutions regard each pixel as a token, thus suffering from an information loss issue from two aspects: 1) They downsample the input image into much lower resolutions for efficiency consideration. 2) They quantize $256^3$ RGB values to a small numb

Mehdi Jabbari Zideh, Mohammad Reza Khalghani, Sarika Khushalani Solanki

Detection of cyber attacks in smart power distribution grids with unbalanced configurations poses challenges due to the inherent nonlinear nature of these uncertain and stochastic systems. It originates from the intermittent characteristics of the distributed energy resources (DERs) generation and load variations. Moreover, the unknown behavior of cyber atta

K. El Anouz, A. El Allati, N. Metwally

In this contribution, two versions of teleportation protocol are considered, based on either using a single or two copies of entangled atom-field state, respectively. It is shown that, by using the first version, the fidelity of the teleported state as well as the amount of quantum Fisher information, that contains in the teleported state, are much better th

Zebang Cheng, Fuqiang Niu, Yuxiang Lin, Zhi-Qi Cheng

This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apar

Yang Shao, Toshie Yaguchi, Toshiaki Tanigaki

Digital image devices have been widely applied in many fields, including scientific imaging, recognition of individuals, and remote sensing. As the application of these imaging technologies to autonomous driving and measurement, image noise generated when observation cannot be performed with a sufficient dose has become a major problem. Machine learning deno

Jiantao Wu, Shentong Mo, Sara Atito, Zhenhua Feng

Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled data. Numerous studies underscore the advantages of MIM, highlighting how models pretrained on extensive datasets can enhance the performance of downstream tasks. However, the high

Rohan Chaudhury, Mihir Godbole, Aakash Garg, Jinsil Hwaryoung Seo

Contemporary conversational systems often present a significant limitation: their responses lack the emotional depth and disfluent characteristic of human interactions. This absence becomes particularly noticeable when users seek more personalized and empathetic interactions. Consequently, this makes them seem mechanical and less relatable to human users. Re

Darío Alatorre, Diego Rodríguez-Guzmán

We study tiling spaces in the diffeological context. We prove some basic diffeological properties for tiling spaces and analyze two different fiber bundle structures of tiling spaces over irrational tori. We use the diffeological classification of irrational tori which captures their arithmetical escence in order to inherit the diffeological equivalence in t

Shaofei Shen, Chenhao Zhang, Yawen Zhao, Alina Bialkowski

Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have emerged. However, these methods typically rely on complete supervision throughout the unlearning process. Unfortunately, o

Wei Cui, Wei Yu

In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often need to be optimized on the same set of problem inputs. Instead of independently training a different neural network for e

Diwei Sheng, Anbang Yang, John-Ross Rizzo, Chen Feng

Visual Place Recognition (VPR) in indoor environments is beneficial to humans and robots for better localization and navigation. It is challenging due to appearance changes at various frequencies, and difficulties of obtaining ground truth metric trajectories for training and evaluation. This paper introduces the NYC-Indoor-VPR dataset, a unique and rich col

Sergey Sergeev

Recently, Bazhanov and Sergeev have described an Ising-type integrable model which can be identified as a $\sinh$-Gordon-type model with an infinite number of states but with a real parameter $q$. This model is the subject of Sklyanin's Functional Bethe Ansatz. We develop in this paper the whole technique of the FBA which includes: 1. Construction of eigenst

Minglei Yang, Pengjun Wang, Ming Fan, Dan Lu

We introduce a conditional pseudo-reversible normalizing flow for constructing surrogate models of a physical model polluted by additive noise to efficiently quantify forward and inverse uncertainty propagation. Existing surrogate modeling approaches usually focus on approximating the deterministic component of physical model. However, this strategy necessit

Oluwaleke Yusuf, Adil Rasheed, Frank Lindseth

The expansion of urban centers necessitates enhanced efficiency and sustainability in their transportation infrastructure and mobility systems. The big data obtainable from various transportation modes potentially offers critical insights for urban planning. This study presents analysis of detailed historical public transit data, enriched with relevant tempo

Hokuto Konno, Abhishek Mallick, Masaki Taniguchi

We initiate the study of exotic Dehn twists along 3-manifolds $\neq S^3$ inside $4$-manifolds, which produces the first known examples of exotic diffeomorphisms of contractible 4-manifolds, more generally of definite 4-manifolds, and exotic diffeomorphisms of 4-manifolds with $\neq S^3$ boundary that survive after one stabilization. We also construct the sma

Rei Murakami

We prove that if a pair of K\"ahler classes is $J$-nef, the $J$-flow on a compact K\"ahler surface converges to a weak solution of the Monge-Amp\`ere equation in the sense of currents. We also establish the same convergence behavior for the deformed Hermitian-Yang-Mills flow. The method is based on a property of a limit of viscosity subsolutions.

Ondřej Draganov, Steven Skiena

Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the notion of persistent homology from topological data analysis (TDA) to measure the distances between language

Sergey Sergeev

Faddeev' equations are a set-theoretical and an operator forms of the star-triangle equation. Known solutions of the quantum star-triangle equation, related to the Faddeev equations, are based on various forms of the modular double of the Weyl algebra including its cyclic representation. We show in this paper that Fadeev's equation also leads to a solution o

Keller Jordan

CIFAR-10 is among the most widely used datasets in machine learning, facilitating thousands of research projects per year. To accelerate research and reduce the cost of experiments, we introduce training methods for CIFAR-10 which reach 94% accuracy in 3.29 seconds, 95% in 10.4 seconds, and 96% in 46.3 seconds, when run on a single NVIDIA A100 GPU. As one fa

Stefan Fredenhagen, Filipp Lausch, Karapet Mkrtchyan

All independent interaction vertices involving massless (Fang--Fronsdal) fermions in three dimensions are classified, completing the classification of interactions of massless fields of any spin. Similarly to the bosonic case, we get no independent vertices at quartic or higher order in the fields involving fields with spin $s\geq 3/2$, and cubic vertices on

Sangbae Kim, Joachim Stohr, Fabian Rotermund, Byoung S. Ham

We demonstrate theoretically and experimentally how the diffraction and interferometric resolution limit for single-mode coherent cw laser light can be overcome by multi-photon interference. By use of a Mach-Zehnder interferometer, operated in the single input and single or double output port geometries, we observe a fringe width reduction of the conventiona

Victor Gallego

State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model. To address this, we propose a novel method, Configurable Safety Tuning (CST), that augments DPO using synthetic preference data to facilitate flexible safety configuration of LLMs at i

Nathaniel S. Dennler, Mina Kian, Stefanos Nikolaidis, Maja Matarić

Perceptions of gender are a significant aspect of human-human interaction, and gender has wide-reaching social implications for robots deployed in contexts where they are expected to interact with humans. This work explored two flexible modalities for communicating gender in robots--voice and appearance--and we studied their individual and combined influence

Manohar Kumar, Ramakrishna Nanduri, Kamalesh Saha

In this paper, we study the asymptotic behaviour of the v-number of a Noetherian graded filtration $\mathcal{I}= \{I_{[k]}\}_{k\geq 0}$ of a Noetherian $\mathbb{N}$-graded domain $R$. Recently, it is shown that $\mathrm{v}(I_{[k]})$ is periodically linear in $k$ for $k \gg 0$. We show that all these linear functions have the same slope, i.e. $\displaystyle \

Keyuan Cheng, Gang Lin, Haoyang Fei, Yuxuan zhai

Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we propose a novel framework, namely TEMPoral knowLEdge augmen

Antonio Alfieri, Fraser Binns

In a recent note F. Lin showed that if a rational homology sphere $Y$ admits a taut foliation then the Heegaard Floer module $HF^-(Y)$ contains a copy of $\mathbf{F}[U]/U$ as a summand (arXiv:2309.01222). This implies that either the $L$-space conjecture is false or that Heegaard Floer homology satisfies a geography restriction. We verify that Lin's geograph

Muhammad Asif Ali, Zhengping Li, Shu Yang, Keyuan Cheng

Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to substandard results in terms of readability/

Ritesh Sarkhel, Xiaoqi Ren, Lauro Beltrao Costa, Guolong Su

A visually rich document (VRD) utilizes visual features along with linguistic cues to disseminate information. Training a custom extractor that identifies named entities from a document requires a large number of instances of the target document type annotated at textual and visual modalities. This is an expensive bottleneck in enterprise scenarios, where we

Subigya Nepal, Arvind Pillai, William Campbell, Talie Massachi

MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) to create a new form of contextual AI journaling, promoting self-reflection and well-being. We argue that integrating behavioral sensing in LLMs will likely lead to a new frontier in AI. In t

Thakshila Wimalajeewa Wewelwala, Thomas W. Tedesso, Tony Davis

Reliable detection, localization and identification of small drones is essential to promote safe, secure and privacy-respecting operation of Unmanned-Aerial Systems (UAS), or simply, drones. This is an increasingly challenging problem with only single modality sensing, especially, to detect and identify small drones. In this work, a multi-stage fusion archit

Shu Yang, Jiayuan Su, Han Jiang, Mengdi Li

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively fine-tune LLMs to match preferences in the preference dataset, they often lead LLMs to highly receptive human input and ex

Akash Sengupta, Thiemo Alldieck, Nikos Kolotouros, Enric Corona

We present DiffHuman, a probabilistic method for photorealistic 3D human reconstruction from a single RGB image. Despite the ill-posed nature of this problem, most methods are deterministic and output a single solution, often resulting in a lack of geometric detail and blurriness in unseen or uncertain regions. In contrast, DiffHuman predicts a probability d

Aryo Pradipta Gema, Giwon Hong, Pasquale Minervini, Luke Daines

The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports. In this study, we evaluate various Large Language Models (LLMs) with multiple strategies, including Chain-of-Thought, In-Context Learning, and Parameter-Efficient Fine-Tuning (PEFT). We propose a PEFT method

T. Cisneros-Pérez, E. Cruz-Albaro, A. Y. Ojeda-Castañeda, S. E. Solís-Núñez

In this paper, we research into the anomalous Chromomagnetic Dipole Moment (CMDM), denoted as $\hat{\mu}_{q}^{BLHM}$, of the light quarks $q=(u, c, d, s, b)$ within the framework of the Bestest Little Higgs Model (BLHM) as an extension of the Standard Model (SM). Our investigation encompasses novel interactions among the light quarks, the heavy quark $B$, an

Jakub Piskorski, Michał Marcińczuk, Roman Yangarber

This paper presents a corpus manually annotated with named entities for six Slavic languages - Bulgarian, Czech, Polish, Slovenian, Russian, and Ukrainian. This work is the result of a series of shared tasks, conducted in 2017-2023 as a part of the Workshops on Slavic Natural Language Processing. The corpus consists of 5 017 documents on seven topics. The do

Wenhan Cao, Shiqi Liu, Chang Liu, Zeyu He

Bayesian filtering serves as the mainstream framework of state estimation in dynamic systems. Its standard version utilizes total probability rule and Bayes' law alternatively, where how to define and compute conditional probability is critical to state distribution inference. Previously, the conditional probability is assumed to be exactly known, which repr

Mario Zitelli

A new thermodynamic theory for optical multimode systems is proposed. Theory is based on a weighted Bose-Einstein law, and includes the state equation, the fundamental equation for the entropy and a metric to measure the accuracy of the thermodynamic approach. The theory is used to compare the experimental results of two propagation regimes in multimode fibr

Matteo Bonforte, Ariel Salort

We study regularity properties of solutions to nonlinear and nonlocal evolution problems driven by the so-called \emph{$0$-order fractional $p-$Laplacian} type operators: $$ \partial_t u(x,t)=\mathcal{J}_p u(x,t):=\int_{\mathbb{R}^n} J(x-y)|u(y,t)-u(x,t)|^{p-2}(u(y,t)-u(x,t))\,dy\,, $$ where $n\ge 1$, $p>1$, $J\colon\mathbb{R}^n\to\mathbb{R}$ is a bounded no

Leslie D. McIntosh, Cynthia Hudson Vitale

Forensic Scientometrics (FoSci) is emerging as a vital discipline at the intersection of scientific integrity and security. Scholarship and scholarly communication are critical for maintaining scientific integrity, influencing public trust in science, health, technology, policy, and law. Yet, these foundations are threatened by the misuse of scientific resea

Zhishang Luo, Truong Son Hy, Puoya Tabaghi, Donghyeon Koh

The run-time for optimization tools used in chip design has grown with the complexity of designs to the point where it can take several days to go through one design cycle which has become a bottleneck. Designers want fast tools that can quickly give feedback on a design. Using the input and output data of the tools from past designs, one can attempt to buil

Volodymyr A. Kuznietsov, Mark I. Gorenstein, Volker Koch, Volodymyr Vovchenko

We analyze particle number fluctuations in the crossover region near the critical endpoint of a first-order phase transition by utilizing molecular dynamics simulations of the classical Lennard-Jones fluid. We extend our previous study [V.A. Kuznietsov et al., Phys. Rev. C 105, 044903 (2022)] by incorporating longitudinal collective flow. The scaled variance

Andrew Komo, Scott Duke Kominers, Tim Roughgarden

We characterize single-item auction formats that are shill-proof in the sense that a profit-maximizing seller has no incentive to submit shill bids. We distinguish between strong shill-proofness, in which a seller with full knowledge of bidders' valuations can never profit from shilling, and weak shill-proofness, which requires only that the expected equilib

Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto

Language models (LMs) may lead their users to make suboptimal downstream decisions when they confidently hallucinate. This issue can be mitigated by having the LM verbally convey the probability that its claims are correct, but existing models cannot produce long-form text with calibrated confidence statements. Through the lens of decision-making, we define

Shanglun Feng, Florian Tramèr

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained model's weights, an attacker can fully compromise the privacy of the finetuning data. We show how to build privacy backd

Souvik Mondal, Murilo S. Baptista, Kapil Debnath

The optomechanical systems produce chaotic behaviour due to nonlinear interaction between photons and phonons, and the same systems are used to understand the synthetic fields as well. Here, we report on the study of chaotic behaviour in the presence of a phononic synthetic magnetic field in a closed loop configuration consisting of a single optical mode and

Sreemanti Dey, Snigdha Saha, Berthy T. Feng, Manxiu Cui

Photoacoustic tomography (PAT) is a rapidly-evolving medical imaging modality that combines optical absorption contrast with ultrasound imaging depth. One challenge in PAT is image reconstruction with inadequate acoustic signals due to limited sensor coverage or due to the density of the transducer array. Such cases call for solving an ill-posed inverse reco

Yang Miao, Francis Engelmann, Olga Vysotska, Federico Tombari

We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multiple modalities, including object-level point clouds, images, attributes, and relationships between objects, offering a lightweight and efficient alternative to conventional methods

S Gill Williamson

Our main result, Theorem 3.3, uses Friedman's Jump Free Theorem, Theorem 2.7, which he has shown to be independent of ZFC, the usual axioms of set theory. We conjecture that Theorem 3.3, a straight forward translation of the statement of Theorem 2.7 into sets and functions, is also independent of ZFC as is its immediate Corollary 3.4. It is easy to show that

Seung Whan Chung, Todd A. Oliver, Laxminarayan L. Raja, Robert D. Moser

The predictive capability of a plasma discharge model depends on accurate representations of electron-impact collision cross sections, which determine the key reaction rates and transport properties of the plasma. Although many cross sections have been identified through experiments and quantum mechanical simulations, their uncertainties are not well-investi

Heqiang Wang, Xiang Liu, Yucheng Liu, Jia Zhou

With the increasing number and enhanced capabilities of IoT devices in smart buildings, these devices are evolving beyond basic data collection and control to actively participate in deep learning tasks. Federated Learning (FL), as a decentralized learning paradigm, is well-suited for such scenarios. However, the limited computational and communication resou

A. Prillfool, A. A. Stoffers, I. Juodžbalis, M. S. Bothwell

We present a speculative exploration of the properties of a proposed new Dark Matter (DM) candidate in a heretofore under-explored region of parameter space. Our proposed ultra-cold candidatae has been a matter of speculation for some time,and has recently been tentatively identified via direct-detection. While unconventional, demonstrated existence of this

Matthew West, Colin Magdamo, Lily Cheng, Yingnan He

Alzheimer's disease is a progressive, debilitating neurodegenerative disease that affects 50 million people globally. Despite this substantial health burden, available treatments for the disease are limited and its fundamental causes remain poorly understood. Previous work has suggested the existence of clinically-meaningful sub-types, which it is suggested

Hannah Chen, Yangfeng Ji, David Evans

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Counterfactual data augmentation (CDA) is effective for reducing bias in NLP models, yet models trained with CDA are often evaluated only on m

Zhenjiang Mao, Siqi Dai, Yuang Geng, Ivan Ruchkin

A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models rely solely on statistical learning of how observations change in response to actions, lacking precise quantification of how accurate the surrogate dynamics are, which poses a signif

Alireza Khalili Golmankhaneh, Palle E. T. Jørgensen, Dimiter Prodanov

This paper introduces the concept of Fractal Frenet equations, a set of differential equations used to describe the behavior of vectors along fractal curves. The study explores the analogue of arc length for fractal curves, providing a measure to quantify their length. It also discusses fundamental mathematical constructs, such as the analogue of the unit ta

Xiaopeng Xie, Ming Yan, Xiwen Zhou, Chenlong Zhao

Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown to be vulnerable to backdoor attacks. The current clean-label attack, employing a specific prompt as a trigger, can achieve success without t

Prashanta Garain, Vladimir Gol'dshtein, Alexander Ukhlov

In this article, we investigate the weighted Steklov eigenvalue problem and the weighted Schr\"odinger--Steklov eigenvalue problem in outward cuspidal domains. We prove the solvability of these spectral problems in both linear and non-linear cases.

Eli Schwartz, Leshem Choshen, Joseph Shtok, Sivan Doveh

Language models struggle with handling numerical data and performing arithmetic operations. We hypothesize that this limitation can be partially attributed to non-intuitive textual numbers representation. When a digit is read or generated by a causal language model it does not know its place value (e.g. thousands vs. hundreds) until the entire number is proc