May 2024 arXiv papers — page 60

Yuan Feng, Chuanbing Zhao, Feifei Gao, Yong Zhang

In this paper, we propose an environment sensing-aided beam prediction model for smart factory that can be transferred from given environments to a new environment. In particular, we first design a pre-training model that predicts the optimal beam by sensing the present environmental information. When encountering a new environment, it generally requires col

Xinlei Niu, Jing Zhang, Christian Walder, Charles Patrick Martin

We present SoundLoCD, a novel text-to-sound generation framework, which incorporates a LoRA-based conditional discrete contrastive latent diffusion model. Unlike recent large-scale sound generation models, our model can be efficiently trained under limited computational resources. The integration of a contrastive learning strategy further enhances the connec

Lan Tao, Shirong Xu, Chi-Hua Wang, Namjoon Suh

With the proliferation of generative AI and the increasing volume of generative data (also called as synthetic data), assessing the fidelity of generative data has become a critical concern. In this paper, we propose a discriminative approach to estimate the total variation (TV) distance between two distributions as an effective measure of generative data fi

Matthias K. Hoffmann, Julian Mühlenhoff, Zhaoheng Ding, Thomas Sattel

Continuum robots are slender, flexible manipulators that navigate confined, curved workspaces and are gaining traction in aerospace, inspection, automation, and minimally invasive medical applications. Predicting their shape from physics-based models alone remains challenging, making accurate measurement of the deformed backbone essential for model validatio

Ke Zhao, Andreas Larsen

This paper explores the burgeoning field of 3D content generation within the landscape of Artificial Intelligence Generated Content (AIGC) and large-scale models. It investigates innovative methods like Text-to-3D and Image-to-3D, which translate text or images into 3D objects, reshaping our understanding of virtual and real-world simulations. Despite signif

Shuya Lin, Yuxiong Wang, Jonathan Dong, Shiguang Ni

This research introduces a Positive Reconstruction Framework based on positive psychology theory. Overcoming negative thoughts can be challenging, our objective is to address and reframe them through a positive reinterpretation. To tackle this challenge, a two-fold approach is necessary: identifying cognitive distortions and suggesting a positively reframed

Jiaxing Li, Chi Xu, Feng Wang, Isaac M von Riedemann

Large Language Models (LLMs) have become increasingly popular, transforming a wide range of applications across various domains. However, the real-world effectiveness of their query cache systems has not been thoroughly investigated. In this work, we for the first time conducted an analysis on real-world human-to-LLM interaction data, identifying key challen

Waleed Abdallah, Anjan Kumar Barik, Santosh Kumar Rai, Tousik Samui

We study the prospect of heavy singlet neutrinos as a dark matter (DM) candidate within a neutrinophilic U(1) model, where the Standard Model (SM) is extended with a U(1) gauge symmetry, and neutrino mass and oscillation parameters are explained through an inverse see-saw mechanism. The lightest of the heavy neutrinos plays the role of the DM while the newly

Matej Cief, Branislav Kveton, Michal Kompan

We study estimator selection and hyper-parameter tuning in off-policy evaluation. Although cross-validation is the most popular method for model selection in supervised learning, off-policy evaluation relies mostly on theory, which provides only limited guidance to practitioners. We show how to use cross-validation for off-policy evaluation. This challenges

A. Encinas-Bartos, B. Kaszás, S. Servidio, G. Haller

Recent work has identified objective (frame-indifferent) material barriers that inhibit the transport of dynamically active vectorial quantities (such as linear momentum, angular momentum and vorticity) in Navier-Stokes flows. In magnetohydrodynamics (MHD), a similar setting arises: the magnetic field vector impacts the evolution of the velocity field throug

Mingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li

Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion image generator. Despite the success of DPM in practice, the mechanism behind it remains to be explored. To fill this blank,

Minzhi Li, Zhengyuan Liu, Shumin Deng, Shafiq Joty

The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts. They serve as scalable and economical evaluators, but the question of how reliable these evaluators are has emerged as a crucial research question. Prior research efforts in the meta-evaluation of LLMs as judges limit the prompting of an

Yash Sinha, Murari Mandal, Mohan Kankanhalli

User data spread across multiple modalities has popularized multi-modal recommender systems (MMRS). They recommend diverse content such as products, social media posts, TikTok reels, etc., based on a user-item interaction graph. With rising data privacy demands, recent methods propose unlearning private user data from uni-modal recommender systems (RS). Howe

Changfeng Gui, Chunjing Xie, Huan Xu

In this paper, we provide a classification of steady solutions to two-dimensional incompressible Euler equations in terms of the set of flow angles. The first main result asserts that the set of flow angles of any bounded steady flow in the whole plane must be the whole circle unless the flow is a parallel shear flow. In an infinitely long horizontal strip o

Yingfang Yuan, Kefan Chen, Mehdi Rizvi, Lynne Baillie

The growing interest in fair AI development is evident. The ''Leave No One Behind'' initiative urges us to address multiple and intersecting forms of inequality in accessing services, resources, and opportunities, emphasising the significance of fairness in AI. This is particularly relevant as an increasing number of AI tools are applied to decision-making p

Chen Lan, Wei Li, Huifang Geng

The spectral collocation method (SCM) exhibits a clear superiority in solving ordinary and partial differential equations compared to conventional techniques, such as finite difference and finite element methods. This makes SCM a powerful tool for addressing the Schr\"odinger-like equations with boundary conditions in physics. However, the Chebyshev differen

Zijian Li, Yifan Shen, Kaitao Zheng, Ruichu Cai

Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal processes do not have instantaneous relations. Although some recent methods achieve identifiability in the instantaneous causality case, they require either interventions on the lat

Jianbiao Mei, Yukai Ma, Xuemeng Yang, Licheng Wen

Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomou

Kalyani Swain, Mrityunjay Kundu

Collisionless absorption of laser energy by an electron via laser-cluster interaction in an ambient magnetic field ($B_0$) has recently renewed interest. %due to high levels of absorption. Previously, using a rigid sphere model (RSM) and an extensive particle-in-cell (PIC) simulation with linearly polarized (LP) laser light, we have shown that an auxiliary f

Ye Wang, Jian Dong, Ming Han, Jin Wu

Approximate Computing (AC) has emerged as a promising technique for achieving energy-efficient architectures and is expected to become an effective technique for reducing the electricity cost for cloud service providers (CSP). However, the potential misuse of AC has not received adequate attention, which is a coming crisis behind the blueprint of AC. Driven

Guibao Shen, Luozhou Wang, Jiantao Lin, Wenhang Ge

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human exp

Asım Ersoy, Olcay Taner Yıldız

Grammatical Error Correction has seen significant progress with the recent advancements in deep learning. As those methods require huge amounts of data, synthetic datasets are being built to fill this gap. Unfortunately, synthetic datasets are not organic enough in some cases and even require clean data to start with. Furthermore, most of the work that has b

Wenyu Du, Tongxu Luo, Zihan Qiu, Zeyu Huang

LLMs are computationally expensive to pre-train due to their large scale. Model growth emerges as a promising approach by leveraging smaller models to accelerate the training of larger ones. However, the viability of these model growth methods in efficient LLM pre-training remains underexplored. This work identifies three critical $\underline{\textit{O}}$bst

Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao

The learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we argue that the long-LLMs are not a necessity to solve long-context tasks, as common long-context tasks are short-context solvable, i.e. they can be solved by purely working with oracle short-contexts within the long-context tasks' inputs. On top

Jinguo Cheng, Chunwei Yang, Wanlin Cai, Yuxuan Liang

Time series imputation is critical for many real-world applications and has been widely studied. However, existing models often require specialized designs tailored to specific missing patterns, variables, or domains which limits their generalizability. In addition, current evaluation frameworks primarily focus on domain-specific tasks and often rely on time

Zhiyang Dai, Chunyi Zhou, Anmin Fu

In contrast to prevalent Federated Learning (FL) privacy inference techniques such as generative adversarial networks attacks, membership inference attacks, property inference attacks, and model inversion attacks, we devise an innovative privacy threat: the Data Distribution Decompose Attack on FL, termed Decaf. This attack enables an honest-but-curious FL s

Volodymyr Sushch

In this paper, we introduce a discretization scheme for the Yang-Mills equations in the two-dimensional case using a framework based on discrete exterior calculus. Within this framework, we define discrete versions of the exterior covariant derivative operator and its adjoint, which capture essential geometric features similar to their continuous counterpart

Hüseyin Tunç, Doğanay Özese, Ş. İlker Birbil, Donato Maragno

Incorporating domain-specific constraints into machine learning models is essential for generating predictions that are both accurate and feasible in real-world applications. This paper introduces new methods for training Output-Constrained Regression Trees (OCRT), addressing the limitations of traditional decision trees in constrained multi-target regressio

Aoxue Li, Mingyang Yi, Zhenguo Li

Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to systematically improve the text-guided image editing techniques based on diffusion models, by addressing their limitations

Reza Nikandish, Jiayu He, Benyamin Haghi

In this article, we present a resource-efficient approach for electrocardiogram (ECG) based heartbeat classification using multi-feature fusion and bidirectional long short-term memory (Bi-LSTM). The dataset comprises five original classes from the MIT-BIH Arrhythmia Database: Normal (N), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Pre

Khanh-Binh Nguyen, Chae Jung Park

Self-supervised learning (SSL) is gaining attention for its ability to learn effective representations with large amounts of unlabeled data. Lightweight models can be distilled from larger self-supervised pre-trained models using contrastive and consistency constraints. Still, the different sizes of the projection heads make it challenging for students to mi

Duke Nguyen, Du Yin, Aditya Joshi, Flora Salim

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We identify the need for a systematic comparison of different combinations of weight matrices and component functions for atte

Qin Chang, Lei Yang, Zhi-Tian Zou, Ying Li

Based on the fitting results of the LHCb collaboration on the contributions of various intermediate resonances to the $B^{+}\to\pi^{+}\pi^{+}\pi^{-}$ decay, we make systematically calculate the branching fractions and localized $CP$ asymmetries of the quasi-two-body $B^{+}\to \pi^{+} \left( \rho(770), \omega(782), \rho(1450), f_{2}\left(1270\right)\to\right)

Yixin Zou, Khue Le, Peter Mayer, Alessandro Acquisti

We draw on the Protection Motivation Theory (PMT) to design nudges that encourage users to change breached passwords. Our online experiment ($n$=$1,386$) compared the effectiveness of a threat appeal (highlighting negative consequences of breached passwords) and a coping appeal (providing instructions on how to change the breached password) in a 2x2 factoria

Ge Qu, Jinyang Li, Bowen Li, Bowen Qin

Large Language Models (LLMs) driven by In-Context Learning (ICL) have significantly improved the performance of text-to-SQL. Previous methods generally employ a two-stage reasoning framework, namely 1) schema linking and 2) logical synthesis, making the framework not only effective but also interpretable. Despite these advancements, the inherent bad nature o

Jonas Belouadi, Simone Paolo Ponzetto, Steffen Eger

Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are not stored in formats preserving semantic information is equally complex. To tackle this problem, we introduce DeTikZify, a novel multimodal language model that automaticall

Yibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu

3D sketches are widely used for visually representing the 3D shape and structure of objects or scenes. However, the creation of 3D sketch often requires users to possess professional artistic skills. Existing research efforts primarily focus on enhancing the ability of interactive sketch generation in 3D virtual systems. In this work, we propose Diff3DS, a n

Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang

Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising solution to eliminate sensitive concepts from these models. Despite its potential, existing MU methods face two main challe

Guanlin Li, Kangjie Chen, Shudong Zhang, Jie Zhang

Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of which are designed for large language models. Existing methods primarily focus on jailbreak and adversarial attacks, which

Wenyu Wang, Zheyi Fan, Szu Hui Ng

Training machine learning models inherently involves a resource-intensive and noisy iterative learning procedure that allows epoch-wise monitoring of the model performance. However, the insights gained from the iterative learning procedure typically remain underutilized in multi-objective hyperparameter optimization scenarios. Despite the limited research in

Tomoya Yanagi, Shunnosuke Ikeda, Noriyoshi Sukegawa, Yuichi Takano

In order to provide high-quality recommendations for users, it is desirable to share and integrate multiple datasets held by different parties. However, when sharing such distributed datasets, we need to protect personal and confidential information contained in the datasets. To this end, we establish a framework for privacy-preserving recommender systems us

Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou

Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategies, ultimately enhancing their reasoning capability. In this study, we constructed a symbolic multi-step reason

Bowei He, Yunpeng Weng, Xing Tang, Ziqiang Cui

Uplift modeling has been widely employed in online marketing by predicting the response difference between the treatment and control groups, so as to identify the sensitive individuals toward interventions like coupons or discounts. Compared with traditional \textit{conversion uplift modeling}, \textit{revenue uplift modeling} exhibits higher potential due t

Marina Anagnostopoulou-Merkouri, Timothy C. Burness

A $k$-tuple $(H_1, \ldots, H_k)$ of core-free subgroups of a finite group $G$ is said to be regular if $G$ has a regular orbit on the Cartesian product $G/H_1 \times \cdots \times G/H_k$. The regularity number of $G$, denoted $R(G)$, is the smallest positive integer $k$ with the property that every such $k$-tuple is regular. In this paper, we develop some ge

Lang Zhang, Jinling He, Dong Liang, Hairong Zheng

Magnetic resonance diffusion tensor imaging (DTI) is a critical tool for neural disease diagnosis. However, long scan time greatly hinders the widespread clinical use of DTI. To accelerate image acquisition, a feature-enhanced joint diffusion model (Diff-DTI) is proposed to obtain accurate DTI parameter maps from a limited number of diffusion-weighted images

Yifan Zhou, Wanli Peng, Zhongyu Yang, He Liu

The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties. These properties lead to gaps and inaccuracies in the depth maps of the transparent objects captured by depth sensor

Xiao-Fan Zhen, Mao-Sheng Li, Hui-Juan Zuo

Strong nonlocality, proposed by Halder {\it et al}. [\href{https://doi.org/10.1103/PhysRevLett.122.040403}{Phys. Rev. Lett. \textbf{122}, 040403 (2019)}], is a stronger manifestation than quantum nonlocality. Subsequently, Shi {\it et al}. presented the concept of the strongest nonlocality [\href{https://doi.org/10.22331/q-2022-01-05-619}{Quantum \textbf{6},

J. H. Zhang, L. Lin, C. Dong, Y. T. Chang

Among the 3d transition metal ions doped polar Ni3TeO6, Mn-doped Ni3TeO6 has stimulated great interest due to its high magnetic ordering temperature and complex magnetic phases, but the mechanism of magnetoelectric (ME) coupling is far from understood. Herein we report our systematic investigation of the chemical control of magnetism, metamagnetic transition

Vinita Khatri, C. P. Singh, Milan Srivastava

In the present work, we study a cosmological model composed of a viscous dark matter interacting with decaying vacuum energy in a spatially flat Universe. In the first part, we find the analytical solution of different cosmological parameters by assuming the physically viable forms of bulk viscosity and decaying vacuum density with the interaction term. The

Brett McInnes

It has been argued that the rate at which the interior of an AdS black hole evolves is dual to the rate of evolution of the (quantum state of the) strongly coupled matter on the boundary which, according to holography, is dual to the black hole. However, we have shown elsewhere that it seems to be possible, by adjusting the specific angular momentum of an Ad

Stefan Dietrich, Julian Rodemann, Christoph Jansen

We provide a theoretical and computational investigation of the Gamma-Maximin method with soft revision, which was recently proposed as a robust criterion for pseudo-label selection (PLS) in semi-supervised learning. Opposed to traditional methods for PLS we use credal sets of priors ("generalized Bayes") to represent the epistemic modeling uncertainty. Thes

Limeng Zhang, Rui Zhou, Qing Liu, Chengfei Liu

In the Bitcoin system, transaction fees serve as an incentive for blockchain confirmations. In general, a transaction with a higher fee is likely to be included in the next block mined, whereas a transaction with a smaller fee or no fee may be delayed or never processed at all. However, the transaction fee needs to be specified when submitting a transaction

Jokin Alcibar, Jose I. Aizpurua, Ekhi Zugasti

Batteries are a key enabling technology for the decarbonization of transport and energy sectors. The safe and reliable operation of batteries is crucial for battery-powered systems. In this direction, the development of accurate and robust battery state-of-health prognostics models can unlock the potential of autonomous systems for complex, remote and reliab

Satoshi Nakajima, Hiroyasu Tajima

In practical measurements, it is widely recognized that reducing the measurement time leads to decreased accuracy. However, whether an inherent speed-accuracy trade-off exists as a fundamental physical constraint for quantum measurements is not obvious, and the answer remains unknown. Here, we establish a fundamental speed-accuracy trade-off relation based o

M. Sipilä, F. Mehryary, S. Pyysalo, F. Ginter

Scientific text is a promising source of data in materials science, with ongoing research into utilising textual data for materials discovery. In this study, we developed and tested a novel approach to extract material-property relationships from scientific publications using the Question Answering (QA) method. QA performance was evaluated for information ex

Guang Lin, Toshihisa Tanaka, Qibin Zhao

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed textual perturbations. In this paper, we introduce a novel defense technique named Large LAnguage MOdel Sentinel (LLAMOS)

Zeen Song, Siyu Zhao, Xingyu Zhang, Jiangmeng Li

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, but its performance can degrade when fine-tuned in out-of-distribution (OOD) scenarios. We model the prediction process using a Structural Causal Model (SCM) and show that the causal mechanism involving both invariant and variant factors in training environments differs from that

Johnnatan Messias, Krzysztof Gogol, Maria Inês Silva, Benjamin Livshits

This paper examines inscription-related transactions on Ethereum and major EVM-compatible rollups, assessing their impact on scalability during transaction surges. Our results show that, on certain days, inscriptions accounted for nearly 90% of transactions on Arbitrum and ZKsync Era, while 53% on Ethereum, with 99% of these inscriptions involving meme coin

Chengming Xu, Kai Hu, Qilin Wang, Donghao Luo

Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. In this paper, we present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion (SD) to address challenges such as misinterpreted styles and inconsistent semantics. Our approach introduces two innovative modules: the mixed style de

Boyi Sun, Yuhang Liu, Xingxia Wang, Bin Tian

Point cloud data labeling is considered a time-consuming and expensive task in autonomous driving, whereas annotation-free learning training can avoid it by learning point cloud representations from unannotated data. In this paper, we propose AFOV, a novel 3D \textbf{A}nnotation-\textbf{F}ree framework assisted by 2D \textbf{O}pen-\textbf{V}ocabulary segment

Zheyi Fan, Wenyu Wang, Szu Hui Ng, Qingpei Hu

Local Bayesian optimization is a promising practical approach to solve the high dimensional black-box function optimization problem. Among them is the approximated gradient class of methods, which implements a strategy similar to gradient descent. These methods have achieved good experimental results and theoretical guarantees. However, given the distributio

Mathis Caprais, Oriane Shviro, Ugo Pensec, Hermann Zeyen

Modeling underground temperatures provides a practical application of the one-dimensional heat equation. In this work, the one-dimensional heat equation in surface soil is extended to include heat carried by the vertical flow of rainwater through the soil. Analytical solutions, with and without water flow, illustrate the influence of rainwater circulation on

M. Köpf, S. H. Lee, Z. Q. Mao, C. A. Kuntscher

The van der Waals material MnBi$_2$Te$_4$ and the related Sb-substituted compounds Mn(Bi$_{1-x}$Sb$_x$)$_2$Te$_4$ are prominent members of the family of magnetic topological insulators, in which rare quantum mechanical states can be realized. In this work, we study the evolution of the charge dynamics in MnBi$_2$Te$_4$ and the Sb-substituted compound Mn(Bi$_

Abhinav Jain, Swarat Chaudhuri, Thomas Reps, Chris Jermaine

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as these adapters must be housed and run at the FM server. Traditional prompt tuning offers a potential solution by

Yiqing Wu, Ruobing Xie, Zhao Zhang, Xu Zhang

The graph-based recommendation has achieved great success in recent years. However, most existing graph-based recommendations focus on capturing user preference based on positive edges/feedback, while ignoring negative edges/feedback (e.g., dislike, low rating) that widely exist in real-world recommender systems. How to utilize negative feedback in graph-bas

Chengming Xu, Chen Liu, Yikai Wang, Yuan Yao

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample. The fundamental problem in VICL is how to select the best prompt to activate its power as much as possible, which is equivalent to the

Shuai Jiang, Zhu Meng, Haiwen Li, Delong Liu

Aiming to reconstruct visual stimuli from brain signals, brain decoding has recently made significant progress using functional magnetic resonance imaging (fMRI). However, it still has challenging issues such as substantial individual differences and high data collection costs. To simplify these problems, most methods adopt the per-subject-per-model paradigm

Miao Miao Zhao, Lei Meng, Yi Yang Xu, Na Du

While all of the polymorphs of NH$_4$I and NH$_4$Br are non-polar, a reversible electric polarization is established in the ordered $\gamma$ phases of (NH$_4$)$_{0.73}$(ND$_4$)$_{0.27}$I and (NH$_4$)$_{0.84}$(ND$_4$)$_{0.16}$Br (where D is $^2$H) via $dc$ electric fields. The presence of two groups of orbital magnetic moments appears to be responsible for th

Sergey Basalaev

A special type of coarea inequality is proved for compositions of intrinsically Lipschitz mappings of Carnot groups with projections along horizontal vector fields. It is proved that the equality is achieved for mappings with finite codistortion and mappings on the Heisenberg group.

Saul Fuster, Umay Kiraz, Trygve Eftestøl, Emiel A. M. Janssen

The most prevalent form of bladder cancer is urothelial carcinoma, characterized by a high recurrence rate and substantial lifetime treatment costs for patients. Grading is a prime factor for patient risk stratification, although it suffers from inconsistencies and variations among pathologists. Moreover, absence of annotations in medical imaging difficults

Yuhang Liu, Boyi Sun, Guixu Zheng, Yishuo Wang

LiDAR sensors play a crucial role in various applications, especially in autonomous driving. Current research primarily focuses on optimizing perceptual models with point cloud data as input, while the exploration of deeper cognitive intelligence remains relatively limited. To address this challenge, parallel LiDARs have emerged as a novel theoretical framew

Qichao Shentu, Beibu Li, Kai Zhao, Yang Shu

Time series anomaly detection plays a vital role in a wide range of applications. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. Aiming at this problem, we propose c

Keith Davis, Tuukka Ruotsalo

Wearable devices that measure and record physiological signals are now becoming widely available to the general public with ever-increasing affordability and signal quality. The data from these devices introduce serious ethical challenges that remain largely unaddressed. Users do not always understand how these data can be leveraged to reveal private informa

Zhangchen Zhou, Yaoyu Zhang, Zhi-Qin John Xu

Grokking is the phenomenon where neural networks NNs initially fit the training data and later generalize to the test data during training. In this paper, we empirically provide a frequency perspective to explain the emergence of this phenomenon in NNs. The core insight is that the networks initially learn the less salient frequency components present in the

Dingding Liang, Yang Chen, Jiawei Gao, Taixia Shi

Real-time vital sign monitoring is gaining immense significance not only in the medical field but also in personal health management. Facing the needs of different application scenarios of the smart and healthy city in the future, the low-cost, large-scale, scalable, and distributed vital sign monitoring system is of great significance. In this work, a seaml

Andrzej Lingas

We study the possibility of designing $N^{o(1)}$-round protocols for problems of substantially super-linear polynomial-time (sequential) complexity on the congested clique with about $N^{1/2}$ nodes, where $N$ is the input size. We show that the average time complexity of the local computation performed at a clique node (in terms of the size of the data rece

Yuwei Niu, Shuo He, Qi Wei, Zongyu Wu

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks on CLIP, existing defense methods focus on either the pre-training stage or the fine-tuning stage, which would unfortunat

Zhangkai Wu, Xuhui Fan, Jin Li, Zhilin Zhao

The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic representation from the parameter space since {common encoders, which encode data into one static representation, cannot capt

Haoxuan Qu, Zhaoyang He, Zeyu Hu, Yujun Cai

To facilitate the application of motion prediction in practice, recently, the few-shot motion prediction task has attracted increasing research attention. Yet, in existing few-shot motion prediction works, a specific model that is dedicatedly trained over human motions is generally required. In this work, rather than tackling this task through training a spe

Binzhao Xu, Muhayy Ud Din, Irfan Hussain

The dynamic motion primitive-based (DMP) method is an effective method of learning from demonstrations. However, most of the current DMP-based methods focus on learning one task with one module. Although, some deep learning-based frameworks can learn to multi-task at the same time. However, those methods require a large number of training data and have limit

Jiayi Chen, Rong Quan, Jie Qin

Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-FSS. However, they completely rely on support images for feature transformation, and repeatedly utilizing a few

Saul Fuster, Farbod Khoraminia, Julio Silva-Rodríguez, Umay Kiraz

We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique challenge as the ground truth labels are inherently weak, and the model must anticipate future events that are not directly

Marek Balcerzak, Tomasz Natkaniec, Piotr Szuca

Given a metric space $X$, we consider certain families of functions $f:X\to\mathbb{R}$ having the hereditary oscillation property HSOP and the hereditary continuous restriction property HCRP on large sets. When $X$ is Polish, among them there are families of Baire measurable functions, $\overline{\mu}$-measurable functions (for a finite nonatomic Borel measu

Thomas Siegert, Michael M. Schulreich, Niklas Bauer, Rudi Reinhardt

Deep-sea archives that include intermediate-lived radioactive $^{60}\mathrm{Fe}$ particles suggest the occurrence of several recent supernovae inside the present-day volume of the Local Bubble during the last $\sim 10$ Myr. The isotope $^{60}\mathrm{Fe}$ is mainly produced in massive stars and ejected in supernova explosions, which should always result in a

Yi Yang Xu, Lei Meng, Miao Miao Zhao, Chu Xin Peng

While all of the polymorphs of pure NH$_4$I and KI are non-polar, we identify that (NH$_4$)$_{0.95}$K$_{0.05}$I is ferroelectric and (NH$_4$)$_{0.87}$K$_{0.13}$I and (NH$_4$)$_{0.83}$K$_{0.17}$I are pyroelectric through measurements of their pyroelectric current and complex dielectric constant. The order to disorder phase transitions occur near 245 K. Magnet

Uriya First, Ben Williams

Suppose $A$ is an Azumaya algebra over a ring $R$ and $\sigma$ is an involution of $A$ extending an order-$2$ automorphism $\lambda:R\to R$. We say $\sigma$ is extraordinary if there does not exist a Brauer-trivial Azumaya algebra $\mathrm{End}_R(P)$ over $R$ carrying an involution $\tau$ so that $(A, \sigma)$ and $(\mathrm{End}_R(P), \tau)$ become isomorphi

Tian Liu, Su Wang, Danny H. K. Tsang

With more renewable energy sources (RES) integrated into the power system, the intermittency of RES places a heavy burden on the system. The uncertainty of RES is traditionally handled by controllable generators to balance the real time wind power deviation. As the demand side management develops, the flexibility of aggregate loads can be leveraged to mitiga

Zehang Deng, Ruoxi Sun, Minhui Xue, Sheng Wen

AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency, security and resilience. While adopting decentralized AI approaches (such as federated learning technology) in ACIs is plausi

Andy Manapany, Loriane Didier, Leïla Moueddene, Bertrand Berche

We report a model for hyperthermia therapies based on heat diffusion in a biological tissue containing a topological defect. Biological tissues behave like active liquid crystals with the presence of topological defects which are likely to anchor tumors during the metastatic phase of cancer evolution and the therapy challenge is to destroy the cancer cells w

Zhengnan Li, Yunxiao Qin, Xilong Cheng, Yuting Tan

Time series data can be represented in both the time and frequency domains, with the time domain emphasizing local dependencies and the frequency domain highlighting global dependencies. To harness the strengths of both domains in capturing local and global dependencies, we propose the Frequency and Time Domain Mixer (FTMixer). To exploit the global characte

Rahul Chhimpa, Abha Singh, Avinash Chand Yadav

We study the Bak-Sneppen evolution model on a regular hypercubic lattice in high dimensions. Recent work [Phys. Rev. E 108, 044109 (2023)] has shown the emergence of the $1/f^{\alpha}$ noise for the ``fitness'' observable with $\alpha \approx 1.2$ in one-dimension (1D) and $\alpha \approx 2$ for the random neighbor (mean-field) version of the model. We exami

Alistair Shilton, Sunil Gupta, Santu Rana, Svetha Venkatesh

This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology, assuming only finite-energy neural activations; and a novel representor theory for neural networks in terms of a matrix-valued kernel. The first model is exact (un-approximated) and global, casting the neural network as a

Leif Bergerhoff

We come up with a novel application for image analysis methods in the context of direction dependent signal characteristics. For this purpose, we describe an inpainting approach adding benefit to technical signal information which are typically only used for monitoring and control purposes in ground station operations. Recalling the theoretical properties of

Haokai Hong, Wanyu Lin, Kay Chen Tan

This paper proposes a new 3D molecule generation framework, called GOAT, for fast and effective 3D molecule generation based on the flow-matching optimal transport objective. Specifically, we formulate a geometric transport formula for measuring the cost of mapping multi-modal features (e.g., continuous atom coordinates and categorical atom types) between a

Xiaohan Chen, Jialin Liu, Wotao Yin

Learning to Optimize (L2O) stands at the intersection of traditional optimization and machine learning, utilizing the capabilities of machine learning to enhance conventional optimization techniques. As real-world optimization problems frequently share common structures, L2O provides a tool to exploit these structures for better or faster solutions. This tut

Riku Arakawa, Hiromu Yakura

Chatbots' role in fostering self-reflection is now widely recognized, especially in inducing users' behavior change. While the benefits of 24/7 availability, scalability, and consistent responses have been demonstrated in contexts such as healthcare and tutoring to help one form a new habit, their utilization in coaching necessitating deeper introspective di

Fengkui Ju

In this paper, we present a logic for conditional strong historical necessity in branching time and apply it to analyze a nontheological version of Lavenham's argument for future determinism. Strong historical necessity is motivated from a linguistical perspective, and an example of it is ``If I had not gotten away, I must have been dead''. The approach of t

Leif Bergerhoff

We propose an efficient offline pointing calibration method for operational antenna systems which does not require any downtime. Our approach minimizes the calibration effort and exploits technical signal information which is typically used for monitoring and control purposes in ground station operations. Using a standard antenna interface and data from an o

Yonglong Ding

Fractals are ubiquitous in the natural world, and their connection with phase transitions has been widely observed. This study investigates mechanisms of fractal formation from the perspective of phase transitions. A novel set of probability calculation methods is introduced to establish a direct link between fractals and phase transitions. Notably, in the I

Mengtong Gao, Yifei Zou, Zuyuan Zhang, Xiuzhen Cheng

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized reinforcement learning scenario. Differing from the existing methods that hide a whole backdoor attack behind their shared policie