March 2025 arXiv papers — page 161

Yunhao Li, Yifan Jiao, Dan Meng, Heng Fan

Open-Vocabulary Multi-Object Tracking (OV-MOT) aims to enable approaches to track objects without being limited to a predefined set of categories. Current OV-MOT methods typically rely primarily on instance-level detection and association, often overlooking trajectory information that is unique and essential for object tracking tasks. Utilizing trajectory in

Fei Wang, Chengcheng Chen, Hongyu Chen, Yugang Chang

Recently, large language models (LLMs) and vision-language models (VLMs) have achieved significant success, demonstrating remarkable capabilities in understanding various images and videos, particularly in classification and detection tasks. However, due to the substantial differences between remote sensing images and conventional optical images, these model

Mohammad Pouranvari

We investigate the localization properties of a quasi-one-dimensional two-channel system with symmetric and asymmetric onsite energies using the Aubry-Andr\'{e} model. By analyzing the Lyapunov exponent and localization length, we characterize the phase transitions and critical behavior of the system. For the symmetric model, we obtain the phase diagram for

Felix Rydell, Georg Bökman, Fredrik Kahl, Kathlén Kohn

In this paper, we present a new framework for reducing the computational complexity of geometric vision problems through targeted reweighting of the cost functions used to minimize reprojection errors. Triangulation - the task of estimating a 3D point from noisy 2D projections across multiple images - is a fundamental problem in multiview geometry and Struct

Jonas Seng, Florian Peter Busch, Pooja Prasad, Devendra Singh Dhami

Probabilistic circuits (PCs) enable us to learn joint distributions over a set of random variables and to perform various probabilistic queries in a tractable fashion. Though the tractability property allows PCs to scale beyond non-tractable models such as Bayesian Networks, scaling training and inference of PCs to larger, real-world datasets remains challen

Ethan Griffiths, Maryam Haghighat, Simon Denman, Clinton Fookes

We present HOTFormerLoc, a novel and versatile Hierarchical Octree-based TransFormer, for large-scale 3D place recognition in both ground-to-ground and ground-to-aerial scenarios across urban and forest environments. We propose an octree-based multi-scale attention mechanism that captures spatial and semantic features across granularities. To address the var

Zeyan Song, Hanchao Wang

Let A be an n x n symmetric random matrix whose upper-triangular entries are independent and follow possibly non-identical subgaussian distributions. This paper investigates the spectral properties of A, including its eigenvalues and eigenvectors. Firstly, we prove that for k <= n / log n, 1 <= i <= n - k and epsilon >= 0, P(the gap between the (i+k)-th and

Yueh-Ting Yao, Chia-Hung Chu, Arun Bansil, Hsin Lin

Ground state topologies in quantum materials have unveiled many unique topological phases with novel Hall responses. Recently, the orbital Hall effect in insulators has suggested the existence of orbital Chern insulators (OCIs) in which the orbital angular momentum drives the Hall response. Studies on OCIs, however, have so far been restricted to valley-lock

Bojia Lyu

With the continuous advancement and maturity of AMOLED (Active-Matrix Organic Light Emitting Diode) technology, smart wearable products such as watches and bracelets are increasingly incorporating related technologies as display screen implementation solutions. Using standby time is the most critical product performance measurement indicator at the moment, a

Jeongsol Kim, Bryan Sangwoo Kim, Jong Chul Ye

Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related to diffusion models, it provides a more general perspective on generative modeling. Although inverse problem solving has been extensively explored using diffusion models, it has not been rigorously examined withi

Junfu Guo, Yu Xin, Gaoyi Liu, Kai Xu

We tackle the challenge of concurrent reconstruction at the part level with the RGB appearance and estimation of motion parameters for building digital twins of articulated objects using the 3D Gaussian Splatting (3D-GS) method. With two distinct sets of multi-view imagery, each depicting an object in separate static articulation configurations, we reconstru

Yike Xie, Weidong Mei, Dong Wang, Boyu Ning

Analog beamforming holds great potential for future terahertz (THz) communications due to its ability to generate high-gain directional beams with low-cost phase shifters.However, conventional analog beamforming may suffer substantial performance degradation in wideband systems due to the beam-squint effects. Instead of relying on high-cost true time delayer

Taehyeon Eum, Jieun Choi, Tae-Kyun Kim

Diffusion-based methods have achieved significant successes in T2I generation, providing realistic images from text prompts. Despite their capabilities, these models face persistent challenges in generating realistic human hands, often producing images with incorrect finger counts and structurally deformed hands. MGHanD addresses this challenge by applying m

Mohammad Pouranvari

In this study, we perform a detailed investigation into the interplay between disorder-induced electron localization and long-range hopping amplitudes within the Selective Long-Range Tight-Binding Model (SLRTB). Through numerical simulations, we analyze the electronic properties of the system, with a focus on the participation ratio (PR), entanglement entrop

Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao

In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a moderate number of tasks. We introduce a novel approach lever

Baisong Zhang, Bingqiu Chen, Haibo Yuan, Pinjian Chen

The identification of star clusters holds significant importance in studying galaxy formation and evolution history. However, the task of swiftly and accurately identifying star clusters from vast amounts of photometric images presents an immense challenge. To address these difficulties, we employ deep learning models for image classification to identify you

Hyungsoo Kang, Isaac Kaminer, Venanzio Cichella, Naira Hovakimyan

This article presents a novel time-coordination algorithm based on event-triggered communication to ensure multiple UAVs progress along their desired paths in coordination with one another. In the proposed algorithm, a UAV transmits its progression information to its neighbor UAVs only when a decentralized trigger condition is satisfied. Consequently, it sig

Surabhi Chakrabartty, Ranveer Singh

Computing the permanent of a $(0,1)$-matrix is a well-known $\#P$-complete problem. In this paper, we present an expression for the permanent of a bipartite graph in terms of the determinant of the graph and its subgraphs, obtained by successively removing rows and columns corresponding to vertices involved in vertex-disjoint $4k$-cycles. Our formula establi

Sibang Gou, Jingyan Hu, Qi Wang, Feifei Jing

A linear semi-implicit hybridizable discontinuous Galerkin (HDG) scheme is proposed to solve the diffusive Peterlin viscoelastic model, allowing the diffusion coefficient $\ep$ of the conformation tensor to be arbitrarily small. We investigate the well-posedness, stability, and error estimates of the scheme. In particular, we demonstrate that the $L^2$-norm

Matthias Mayr, Alexander Heinlein, Christian Glusa, Siva Rajamanickam

Trilinos is a community-developed, open-source software framework that facilitates building large-scale, complex, multiscale, multiphysics simulation code bases for scientific and engineering problems. Since the Trilinos framework has undergone substantial changes to support new applications and new hardware architectures, this document is an update to ``An

Manru Yin, Shengqian Han, Chenyang Yang

Deep learning-based autoencoders have been employed to compress and reconstruct channel state information (CSI) in frequency-division duplex systems. Practical implementations require judicious quantization of encoder outputs for digital transmission. In this paper, we propose a novel quantization module with bit allocation among encoder outputs and develop

F. J. D. Lange, Juliane C. Wilcke, Sabine Hoffmann, Moritz Herrmann

Empirical substantive research, such as in the life or social sciences, is commonly categorized into the two modes exploratory and confirmatory, both of which are essential to scientific progress. The former is also referred to as hypothesis-generating or data-contingent research, while the latter is also called hypothesis-testing research. In the context of

Renxuan Tan, Rongpeng Li, Zhifeng Zhao

With the advent of 6G systems, emerging hyper-connected ecosystems necessitate agile and adaptive medium access control (MAC) protocols to contend with network dynamics and diverse service requirements. We propose LLM4MAC, a novel framework that harnesses large language models (LLMs) within a reinforcement learning paradigm to drive MAC protocol emergence. B

Soonwoo Kwon, Jin-Young Kim, Hyojun Go, Kyungjune Baek

We present a novel study on enhancing the capability of preserving the content in world models, focusing on a property we term World Stability. Recent diffusion-based generative models have advanced the synthesis of immersive and realistic environments that are pivotal for applications such as reinforcement learning and interactive game engines. However, whi

Huy Nguyen, Kien Nguyen, Akila Pemasiri, Feng Liu

We introduce AG-VPReID, a new large-scale dataset for aerial-ground video-based person re-identification (ReID) that comprises 6,632 subjects, 32,321 tracklets and over 9.6 million frames captured by drones (altitudes ranging from 15-120m), CCTV, and wearable cameras. This dataset offers a real-world benchmark for evaluating the robustness to significant vie

Ziyu Wang, Elahe Khatibi, Kianoosh Kazemi, Iman Azimi

Electrocardiogram (ECG) signals are widely shared across multiple clinical applications for diagnosis, health monitoring, and biometric authentication. While valuable for healthcare, they also carry unique biometric identifiers that pose privacy risks, especially when ECG data shared across multiple entities. These risks are amplified in shared environments,

Shilong Sang, Ke-Jia Chen, Zheng liu

Graph similarity learning (GSL), also referred to as graph matching in many scenarios, is a fundamental problem in computer vision, pattern recognition, and graph learning. However, previous GSL methods assume that graphs are homogeneous and struggle to maintain their performance on heterogeneous graphs. To address this problem, this paper proposes a Heterog

Junzhe Li, Sifan Zhou, Liya Guo, Xuerui Qiu

Unified multimodal models (UMMs) have emerged as a powerful paradigm in fundamental cross-modality research, demonstrating significant potential in both image understanding and generation. However, existing research in the face domain primarily faces two challenges: $\textbf{(1)}$ $\textbf{fragmentation development}$, with existing methods failing to unify u

Deding Yang

Let $X$ be the special fiber of a unitary Shimura variety of hyperspecial level at a prime $p$ inert in the totally real field $F$. Let $Y\to X$ be the associated flag space. For every $L$-dominant weight $\lambda$, let $\mathcal{L}_Y(\lambda)$ denote the corresponding automorphic line bundle. We give an explicit necessary and sufficient criterion, in terms

Büşra Karadeniz Şen

In [19], the authors give minimal embedded toric resolutions of ADE-singularities in C^3 by constructing regular refinements of their dual Newton polyhedrons with the elements of their embedded valuation sets derived from the jet schemes constructed in [18]. On the other hand in [1] and [2], the authors represent the Gr\"obner fan of a Newton non-degenerate

Weiguo Gao, Ming Li

The increasing prevalence of synthetic data in training loops has raised concerns about model collapse, where generative models degrade when trained on their own outputs. While prior work focuses on this self-consuming process, we study an underexplored yet prevalent phenomenon: co-evolving generative models that shape each other's training through iterative

Ruipeng Wang, Junfeng Fang, Jiaqi Li, Hao Chen

Diffusion-based text-to-image models have demonstrated remarkable capabilities in generating realistic images, but they raise societal and ethical concerns, such as the creation of unsafe content. While concept editing is proposed to address these issues, they often struggle to balance the removal of unsafe concept with maintaining the model's general genera

F. Righini, G. Potel, R. Capelli, G. Tiana

The concepts of globule and random coil were developed to describe the phases of homopolymers and then used to characterize the denatured state of structured cytosolic proteins and intrinsically disordered proteins. Using multi-scale molecular dynamics simulations, we were able to explore the conformational space of the disordered conformations of both types

Shoichi Kawamoto, Da-Shin Lee, Chen-Pin Yeh

In this note, we investigate the out-of-time-order correlators (OTOCs) for quantum fields in a holographic framework describing Einstein-Podolsky-Rosen (EPR) pairs. We compute the four-point and six-point OTOCs using the gravity dual, represented by the string worldsheet theory in Anti-de Sitter (AdS) space. These correlators quantify the rate at which infor

Hossein Nourollahi Hokmabad, Tala Hemmati Shahsavar, Pedro P. Vergara, Oleksandr Husev

Buildings are essential components of power grids, and their energy performance directly affects overall power system operation. This paper presents a novel stochastic optimization framework for building energy management systems, aiming to enhance buildings' energy performance and facilitate their effective integration into emerging intelligent power grids.

Runlin Zhu, Zhaoqi Gu, Tianci Shen, Yifei Liu

Dynamic reconfiguration is crucial for nanoplasmonic structures to achieve diversified functions and optimize performances; however, the dynamic reconfiguration of spatial arrangements remains a formidable technological challenge. Here, we showcase in-situ dynamic spatial reconfiguration of plasmonic nanowire devices and circuits on dry solid substrates, by

Jianhui Wang, Zhifei Yang, Yangfan He, Huixiong Zhang

Accurate material retrieval is critical for creating realistic 3D assets. Existing methods rely on datasets that capture shape-invariant and lighting-varied representations of materials, which are scarce and face challenges due to limited diversity and inadequate real-world generalization. Most current approaches adopt traditional image search techniques. Th

Somnath Maity, Pramod Padmanabhan, Vladimir Korepin

We construct invertible spectral parameter dependent Yang-Baxter solutions ($R$-matrices) by Baxterizing constant non-invertible Yang-Baxter solutions. The solutions are algebraic (representation independent). They are constructed using supersymmetry (SUSY) algebras. The resulting $R$-matrices are regular leading to local non-hermitian Hamiltonians written i

Lixin Zhang, Li Xue, Jingyi Luo, Chengzhi Li

The interaction between the accretion disc and its corona plays a critical role in the energy balance and emission mechanisms in astrophysical systems such as active galactic nuclei and X-ray binaries. However, the detailed physics of disc-corona interactions, including the mechanisms driving disc evaporation and the impact of accretion rate and viscosity, r

Jingche Chen, Han Hong, Haizhong Li

In this paper, we prove that complete noncompact constant mean curvature hypersurfaces in $\mathbb{R}^6$ with finite index must be minimal. This provides a positive answer to do Carmo's question in dimension $6$. The proof strategy is also applicable to $\mathbb{R}^4$ and $\mathbb{R}^5$, thereby providing alternative proofs for those previously resolved case

Ratnangshu Das, Pranav Bakshi, Pushpak Jagtap

Prescribed-time reach-avoid-stay (PT-RAS) specifications are crucial in applications requiring precise timing, state constraints, and safety guarantees. While control carrier functions (CBFs) have emerged as a promising approach, providing formal guarantees of safety, constructing CBFs that satisfy PT-RAS specifications remains challenging. In this paper, we

Ayantu Guteta Fite, Hunduma Legesse Geleta

The product of two complex-valued harmonic function is not in general complex-valued harmonic function. In this paper we show that if a complex-valued harmonic function is the product of two complex-valued harmonic functions, then it is the difference of two squares, one is analytic and the other is co-analytic. As a result of this, if one of the factors of

Caichao Ye, Tao Feng, Weishu Liu, Wenqing Zhang

New materials have long marked the civilization level, serving as an impetus for technological progress and societal transformation. The classic structure-property correlations were key of materials science and engineering. However, the knowledge of materials faces significant challenges in adapting to exclusively data-driven approaches for new material disc

Yui Tomo, Daisuke Yoneoka

This study proposes median consensus embedding (MCE) to address variability in low-dimensional embeddings caused by random initialization in nonlinear dimensionality reduction techniques such as $t$-distributed stochastic neighbor embedding. MCE is defined as the geometric median of multiple embeddings. By assuming multiple embeddings as independent and iden

Jiale Wei, Xiang Ying, Tao Gao, Fangyi Bao

Human interaction with the external world fundamentally involves the exchange of personal memory, whether with other individuals, websites, applications, or, in the future, AI agents. A significant portion of this interaction is redundant, requiring users to repeatedly provide the same information across different contexts. Existing solutions, such as browse

Lizhen Xu, Xiuxiu Bai, Xiaojun Jia, Jianwu Fang

Query-based methods with dense features have demonstrated remarkable success in 3D object detection tasks. However, the computational demands of these models, particularly with large image sizes and multiple transformer layers, pose significant challenges for efficient running on edge devices. Existing pruning and distillation methods either need retraining

Zheyi Chen, Sijin Huang, Geyong Min, Zhaolong Ning

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on

Melik Ozolcer, Tongze Zhang, Sang Won Bae

Predicting performance outcomes has the potential to transform training approaches, inform coaching strategies, and deepen our understanding of the factors that contribute to athletic success. Traditional non-automated data analysis in sports are often difficult to scale. To address this gap, this study analyzes factors influencing athletic performance by le

Runxi Cheng, Feng Xiong, Yongxian Wei, Wanyun Zhu

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance degradation. Although prior work has explored many merging strategies, resolving interference without additional data for retrain

Yuheng Ma, Feiyu Jiang, Zifeng Zhao, Hanfang Yang

Motivated by privacy concerns in sequential decision-making on sensitive data, we address the challenge of nonparametric contextual multi-armed bandits (MAB) under local differential privacy (LDP). We develop a uniform-confidence-bound-type estimator, showing its minimax optimality supported by a matching minimax lower bound. We further consider the case whe

Linlin Yu, Kangshuo Li, Pritom Kumar Saha, Yifei Lou

Accurate quantification of both aleatoric and epistemic uncertainties is essential when deploying Graph Neural Networks (GNNs) in high-stakes applications such as drug discovery and financial fraud detection, where reliable predictions are critical. Although Evidential Deep Learning (EDL) efficiently quantifies uncertainty using a Dirichlet distribution over

Xinrui Li, Jinrong Zhang, Jianlong Wu, Chong Chen

Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although bringing high-level semantic priors and dense pixel guidance have led to advances in reconstruction, we identified several critical phenomena by analyzing the behavior of existing

Ritvik Basant, Rafael Luque, Jacob L. Bean, Andreas Seifahrt

Barnard's Star is an old, single M dwarf star that comprises the second-closest extrasolar system. It has a long history of claimed planet detections from both radial velocities and astrometry. However, none of these claimed detections have so far withstood further scrutiny. Continuing this story, extreme precision radial velocity (EPRV) measurements from th

Arghya Pal, Sailaja Rajanala, CheeMing Ting, Raphael Phan

Medical image denoising is essential for improving the reliability of clinical diagnosis and guiding subsequent image-based tasks. In this paper, we propose a multi-scale approach that integrates anisotropic Gaussian filtering with progressive Bezier-path redrawing. Our method constructs a scale-space pyramid to mitigate noise while preserving critical struc

Chenfeng Hou, Qi Xun Yeo, Mengqi Guo, Yongxin Su

3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency fro

Hyeongseok Son, Jia He, Seung-In Park, Ying Min

Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolution and sacrifices z-axis information to reduce the overall feature resolution, which may result in declined accuracy. To tackle the problem

Hao Zhang, Fuhui Zhou, Hongyang Du, Qihui Wu

Wireless signal recognition (WSR) is a crucial technique for intelligent communications and spectrum sharing in the next six-generation (6G) wireless communication networks. It can be utilized to enhance network performance and efficiency, improve quality of service (QoS), and improve network security and reliability. Additionally, WSR can be applied for mil

Weixiao Zhan, Qiyue Dong, Eduardo Sebastián, Nikolay Atanasov

Robot task planning from high-level instructions is an important step towards deploying fully autonomous robot systems in the service sector. Three key aspects of robot task planning present challenges yet to be resolved simultaneously, namely, (i) factorization of complex tasks specifications into simpler executable subtasks, (ii) understanding of the curre

Yifei She, Shen Wang, Ahmad Taha, Xiaofeng Tao

Vehicle platooning with Cooperative Adaptive Cruise Control improves traffic efficiency, reduces energy consumption, and enhances safety but remains vulnerable to cyber-attacks that disrupt communication and cause unsafe actions. To address these risks, this paper investigates control node placement and input bound optimization to balance safety and defense

Andrei Olar

Context: Entity resolution (ER) plays a pivotal role in data management by determining whether multiple records correspond to the same real-world entity. Because of its critical importance across domains such as healthcare, finance, and machine learning and its long research history designing and implementing ER systems remains challenging in practice due to

Rui Meng, Zhuo Meng, Jiaqi Lu, Xiaodong Xu

With the advancement of the Industrial Internet of Things (IIoT), IIoT services now exhibit diverse Quality of Service (QoS) requirements in terms of delay, determinacy, and security, which pose significant challenges for alignment with existing network resources. Reconfigurable Intelligent Surface (RIS), a key enabling technology for IIoT, not only optimize

Kyeongkook Seo, Dong-Jun Han, Jaejun Yoo

Despite recent advancements in federated learning (FL), the integration of generative models into FL has been limited due to challenges such as high communication costs and unstable training in heterogeneous data environments. To address these issues, we propose PRISM, a FL framework tailored for generative models that ensures (i) stable performance in heter

Fangyuan Wang, Shipeng Lyu, Peng Zhou, Anqing Duan

Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language models (LLMs), there has been a notable increase in the development of LLM-based planners. These approaches either utilize h

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

Task decomposition is a fundamental mechanism in program synthesis, enabling complex problems to be broken down into manageable subtasks. ExeDec, a state-of-the-art program synthesis framework, employs this approach by combining a Subgoal Model for decomposition and a Synthesizer Model for program generation to facilitate compositional generalization. In thi

In Cho, Youngbeom Yoo, Subin Jeon, Seon Joo Kim

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing quality. COD-VAE introduces a two-stage autoencoder scheme to improve compression and decoding efficiency. First, our enco

J. C. Chen

Health evaluation for lithium-ion batteries (LIBs) typically relies on constant charging/discharging protocols, often neglecting scenarios involving dynamic current profiles prevalent in electric vehicles. Conventional health indicators for LIBs also depend on the uniformity of measured data, restricting their adaptability to non-uniform conditions. In this

Daqian Ding, Haorui Li, Yibo Pi, Xudong Wang

The interference graph, depicting the intra- and inter-cell interference channel gains, is indispensable for resource allocation in multi-cell networks.However, there lacks viable methods of interference graph estimation (IGE) for multi-cell multi-numerology (MN) networks. To fill this gap, we propose an efficient power-domain approach to IGE for the resourc

Jamie Gardner, Ben Wooding, Amy Nejati, Abolfazl Lavaei

TRUST is an open-source software tool developed for data-driven controller synthesis of dynamical systems with unknown mathematical models, ensuring either stability or safety properties. By collecting only a single input-state trajectory from the unknown system and satisfying a rank condition that ensures the system is persistently excited according to the

Ruiting Wang, Antoine Martinez, Zaid Allybokus, Wente Zeng

The advantages and disadvantages of Battery Swapping Stations (BSS) for heavy-duty trucks are poorly understood, relative to Fast Charging Stations (FCS) systems. This study evaluates these two charging mechanisms for electric heavy-duty trucks, aiming to compare the systems' efficiency and identify their optimal design. A model was developed to address the

Jingyuan Yi, Peiyang Yu, Tianyi Huang, Xiaochuan Xu

This work proposes an LSTM-based sentiment classification model with multi-head attention mechanism and TF-IDF optimization. Through the integration of TF-IDF feature extraction and multi-head attention, the model significantly improves text sentiment analysis performance. Experimental results on public data sets demonstrate that the new method achieves subs

Yingjie Chen, Jiarui Zhang, Tao Wang, Yun Liang

With the increasing need for facial behavior analysis, semi-supervised AU intensity estimation using only keyframe annotations has emerged as a practical and effective solution to relieve the burden of annotation. However, the lack of annotations makes the spurious correlation problem caused by AU co-occurrences and subject variation much more prominent, lea

Sanchayan Dutta

We provide a streamlined elaboration on existing ideas that link Ising anyon (or equivalently, Majorana) stabilizer codes to certain classes of binary classical codes. The groundwork for such Majorana-based quantum codes can be found in earlier works (including, for example, Bravyi (arXiv:1004.3791) and Vijay et al. (arXiv:1703.00459)), where it was observed

Andy Hammerlindl, Rafael Potrie

We show exactly which Seifert manifolds support partially hyperbolic dynamical systems. In particular, a circle bundle over a higher-genus surface supports a partially hyperbolic system if and only if it supports an Anosov flow. We also show for these systems that the center-stable and center-unstable foliations can be isotoped so that their leaves are trans

Mengke Zhang, Zhihao Tian, Yaoguang Xia, Chao Xu

With the increasing integration of robots into human life, their role in architectural spaces where people spend most of their time has become more prominent. While motion capabilities and accurate localization for automated robots have rapidly developed, the challenge remains to generate efficient, smooth, comprehensive, and high-quality trajectories in the

Lehan Yang, Jincen Song, Tianlong Wang, Daiqing Qi

We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption. We treat the dense prediction task of matting as video generation, leveraging the text-to-video alignment prior of video diffusion models to generate alpha mattes that are temporally coherent and closely related to the corre

Haji Gul, Abdul Ghani Naim, Ajaz Ahmad Bhat

Accurate prediction of drug target interactions is critical for accelerating drug discovery and elucidating complex biological mechanisms. In this work, we frame drug target prediction as a link prediction task on heterogeneous biomedical knowledge graphs (KG) that integrate drugs, proteins, diseases, pathways, and other relevant entities. Conventional KG em

Venkat Ram Reddy Ganuthula, Krishna Kumar Balaraman, Nimish Vohra

The fast paced progress of artificial intelligence (AI) through scaling laws connecting rising computational power with improving performance has created tremendous technological breakthroughs. These breakthroughs do not translate to corresponding user satisfaction improvements, resulting in a general mismatch. This research suggests that hedonic adaptation

Beibei Lin, Stephen Lin, Robby Tan

Nighttime image dehazing is particularly challenging when dense haze and intense glow severely degrade or entirely obscure background information. Existing methods often struggle due to insufficient background priors and limited generative capability, both of which are highly important under such conditions. In this paper, we introduce BeyondHaze, a generati

Huimin Zhang, Zhengfei Wang, Michael Weinert, Lian Li

Crystal defects, whether intrinsic or engineered, drive many fundamental phenomena and novel functionalities of quantum materials. Here, we report symmetry-breaking phenomena induced by Sn-vacancy defects on the surface of epitaxial Kagome antiferromagnet FeSn films using low-temperature scanning tunneling microscopy and spectroscopy. Near the Sn-vacancy def

Kai Deng, Yigong Zhang, Jian Yang, Jin Xie

Tracking and mapping in large-scale, unbounded outdoor environments using only monocular RGB input presents substantial challenges for existing SLAM systems. Traditional Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) SLAM methods are typically limited to small, bounded indoor settings. To overcome these challenges, we introduce GigaSLAM, the

Jameel-Un Nabi, Mavra Ishfaq, Mahmut Boyukata, Muhammad Riaz

At finite temperatures ($\geq 10^7$K), $^{76}$Se is abundant in the core of massive stars and electron capture on $^{76}$Se has a consequential role to play in the dynamics of core collapse. The present work may be classified into two main categories. In the first phase, we study the nuclear structure properties of $^{76}$Se using the interacting boson model

Weizhong Huang, Haiping Huang

Chaos is ubiquitous in high-dimensional neural dynamics. A strong chaotic fluctuation may be harmful to information processing. A traditional way to mitigate this issue is to introduce Hebbian plasticity, which can stabilize the dynamics. Here, we introduce another distinct way without synaptic plasticity. An Onsager reaction term due to the feedback of the

Ali Veisi, Hamidreza Amirzadeh, Amir Mansourian

Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing either fixed linear biases or globally learned biases, which lack the capacity to adapt to different input contexts. In this

Mahdieh Zaker, Amy Nejati, Abolfazl Lavaei

We offer a compositional data-driven scheme for synthesizing controllers that ensure global asymptotic stability (GAS) across large-scale interconnected networks, characterized by unknown mathematical models. In light of each network's configuration composed of numerous subsystems with smaller dimensions, our proposed framework gathers data from each subsyst

Hyundong Jin, Eunwoo Kim

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which limits their applicability in scenarios involving multiple modalities. In this work, we propose a novel continual learni

Guy Paić, Leonid Serkin

In this paper, we examine the wide-ranging impact of artificial intelligence on society, focusing on its potential to both help and harm global equity, cognitive abilities, and economic stability. We argue that while artificial intelligence offers significant opportunities for progress in areas like healthcare, education, and scientific research, its rapid g

Ping Tuo, Zezhu Zeng, Jiale Chen, Bingqing Cheng

Generative models have advanced significantly in sampling material systems with continuous variables, such as atomistic structures. However, their application to discrete variables, like atom types or spin states, remains underexplored. In this work, we introduce a discrete flow matching model, tailored for systems with discrete phase-space coordinates (e.g.

Xiaoli Xu, Zhiwen Zhou, Yong Zeng

Orthogonal frequency division multiplexing (OFDM), which has been the dominating waveform for contemporary wireless communications, is also regarded as a competitive candidate for future integrated sensing and communication (ISAC) systems. Existing works on OFDM-ISAC usually assume that the maximum sensing range should be limited by the cyclic prefix (CP) le

DongHeun Han, Byungmin Kim, RoUn Lee, KyeongMin Kim

Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended forc

Behrad Samari, Abolfazl Lavaei

Synthesizing safety controllers for general nonlinear systems is a highly challenging task, particularly when the system models are unknown, and input constraints are present. While some recent efforts have explored data-driven safety controller design for nonlinear systems, these approaches are primarily limited to specific classes of nonlinear dynamics (e.

Xin Li, Chengli Zhao, Xue Zhang, Xiaojun Duan

Differential equations are widely used to describe complex dynamical systems with evolving parameters in nature and engineering. Effectively learning a family of maps from the parameter function to the system dynamics is of great significance. In this study, we propose a novel learning framework of symbolic continuous-depth neural networks, termed Symbolic N

Tetsuya Nomoto, Akiko Kikkawa, Kazuki Nakazawa, Terufumi Yamaguchi

The nonlinear thermoelectric effect is a key factor for realising unconventional thermoelectric phenomena, such as heat rectification and power generation using thermal fluctuations. Recent theoretical advances have indicated that chiral materials can host a variety of exotic nonlinear thermoelectric transport arising from inversion-symmetry breaking. Howeve

Zhiliang Liu, Xin Zhao, Peng Cai, Bing Cong

Autonomous Underwater Vehicles (AUVs) play an essential role in modern ocean exploration, and their speed control systems are fundamental to their efficient operation. Like many other robotic systems, AUVs exhibit multivariable nonlinear dynamics and face various constraints, including state limitations, input constraints, and constraints on the increment in

Wen Luo, Feifan Song, Wei Li, Guangyue Peng

Large Language Models (LLMs) are increasingly required to generate text that is both factually accurate and diverse across various open-ended applications. However, current stochastic decoding methods struggle to balance such objectives. We introduce Dynamic Focus Decoding (DFD), a novel plug-and-play stochastic approach that resolves this trade-off without

Zhongyu Mai, Zewei Zhan, Hanyu Guo, Yulang Huang

Magnetic resonance imaging (MRI) motion artifacts can seriously affect clinical diagnostics, making it challenging to interpret images accurately. Existing methods for eliminating motion artifacts struggle to retain fine structural details and simultaneously lack the necessary vividness and sharpness. In this study, we present a novel dual-domain optimizatio

Nadarasar Bahavan, Sachith Seneviratne, Sanjay Saha, Ken Chen

Facial forgery methods such as deepfakes can be misused for identity manipulation and spreading misinformation. They have evolved alongside advancements in generative AI, leading to new and more sophisticated forgery techniques that diverge from existing ``known" methods. Conventional deepfake detection methods use the closed-set paradigm, thus limiting thei

Congwei Lu, Xulong Wang, Guancong Ma

Artificial classical wave systems such as wave crystals and metamaterials have demonstrated promising capabilities in simulating a wide range of quantum mechanical phenomena. Yet some gaps between quantum and classical worlds are generally considered fundamental and difficult to bridge. Dynamics obeying special unitary groups, e.g., electronic spins describe

Zheyuan Ma, Gaoxiang Liu, Alex Eastman, Kai Kaufman

Microcontroller systems are integral to our daily lives, powering mission-critical applications such as vehicles, medical devices, and industrial control systems. Therefore, it is essential to investigate and outline the challenges encountered in developing secure microcontroller systems. While previous research has focused solely on microcontroller firmware

Chenjun Ma, Chen Huang, Yilong You, Huazhan Liu

High harmonic generation (HHG) in solids could enable attosecond and ultraviolet light sources with high compactness, great controllability and rich functions. However, the HHG process is accompanied by a quite large wavevector mismatch that is uncompensated by any traditional phase-matching method, directly limiting its energy conversion efficiency. Here, w

Guanrong Li, Haolin Yang, Xinyu Liu, Zhen Wu

In the era of generative AI, recommender systems are moving from precise prediction to trustworthy generation. Large language models (LLMs) support this shift by inferring user interests and producing natural-language explanations. However, LLM-based recommendation suffers from a fundamental obstacle: popularity bias. Through pre-training on massive corpora,