November 2025 arXiv papers — page 164

Adam Piaseczny, Eric Ruzomberka, Rohit Parasnis, Christopher G. Brinton

As Federated Learning (FL) becomes more widespread, there is growing interest in its decentralized variants. Decentralized FL leverages the benefits of fast and energy-efficient device-to-device communications to obviate the need for a central server. However, this opens the door to new security vulnerabilities as well. While FL security has been a popular r

Wenbo Huang, Jinghui Zhang, Zhenghao Chen, Guang Li

Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging because of the background distractions. Receptance Weighted Key Value (RWKV), which learns interaction between various d

ChunLiang Wu, Xiaochun Li

In the early stages of semiconductor equipment development, obtaining large quantities of raw optical images poses a significant challenge. This data scarcity hinder the advancement of AI-powered solutions in semiconductor manufacturing. To address this challenge, we introduce SinSEMI, a novel one-shot learning approach that generates diverse and highly real

Jake Ward, Paul Riechers, Adam Shai

Reasoning models leverage inference-time compute to significantly enhance the performance of language models on difficult logical tasks, and have become a dominating paradigm in frontier LLMs. Despite their wide adoption, the mechanisms underpinning the enhanced performance of these reasoning models are not well understood. In this work, we show that the maj

Hyunjae Kim, Jiwoong Sohn, Aidan Gilson, Nicholas Cochran-Caggiano

Large language models (LLMs) are transforming the landscape of medicine, yet two fundamental challenges persist: keeping up with rapidly evolving medical knowledge and providing verifiable, evidence-grounded reasoning. Retrieval-augmented generation (RAG) has been widely adopted to address these limitations by supplementing model outputs with retrieved evide

Jensen O'Sullivan, Daniel Tubbenhauer

We study the asymptotic size of decompositions of tensor powers of tilting modules for quantum groups (mostly at a complex root of unity). In type A1 we obtain a sharp result for the number of indecomposable summands, explained by a one dimensional half-line random walk with a periodic congruence constraint. In general type we prove a universal law: the domi

Arsalan Ali Malik, John Buchanan, Aydin Aysu

Field-Programmable Gate Arrays (FPGAs) have become essential in cloud computing due to their reconfigurability, energy efficiency, and ability to accelerate domain-specific workloads. As FPGA adoption grows, research into task scheduling and preemption techniques has intensified. However, the field lacks a standardized benchmarking framework for consistent a

Raya Majid Alsharfa, Mahmood Mohassel Feghhi, Majid Hameed Majeed

Wireless sensor networks (WSNs) face critical challenges in energy management and network lifetime optimization due to limited battery resources and communication overhead. This study introduces a novel hybrid clustering protocol that integrates the Water Strider Algorithm (WSA) with Fuzzy C-Means (FCM) clustering to achieve superior energy efficiency and ne

Qianfeng Yang, Xiang Chen, Pengpeng Li, Qiyuan Guan

Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing datasets often overlook two critical characteristics of real rainy 3D scenes: the viewpoint-dependent variation in the appearance of rain streaks caused by their projection onto 2D ima

Walter Hartung, Wei Chang, Yoo-Lim Cheon, Kyle Elliott

Plasma processing has been shown to help mitigate degradation of the performance of superconducting radio-frequency cavities, providing an alternative to removal of cryomodules from the accelerator for refurbishment. Studies of plasma processing for quarter-wave resonators (QWRs) and half-wave resonators (HWRs) are underway at the Facility for Rare Isotope B

Chun-Ming Huang, Li-Heng Chang, I-Hsin Chang, An-Sheng Lee

Deep learning has transformed seismic phase picking, but a systematic failure mode persists: for some S-wave arrivals that appear unambiguous to human analysts, the model produces only a distorted peak trapped below the detection threshold, even as the P-wave prediction on the same record appears flawless. By examining training dynamics and loss landscape ge

Michal Botur

In this paper we show that a new type of products hoops can be defined which, in the case of finite hoops, can describe an arbitrary hoop $\mathbf A$ as the product of its arbitrary filter $F$ and the corresponding homomorphic image $\mathbf A/F$. Moreover, this product satisfies a certain kind of associativity, and as a consequence we show that every finite

Shi Zhan

In this paper, we investigate Weng zeta functions associated with curves of genus 2 over finite fields. Building upon Weng's framework for non-abelian zeta functions, we establish that, as the rank n tends to infinity, the Riemann Hypothesis holds for these zeta functions. Our proof relies on the geometric properties of the moduli space of semi-stable bundle

Vasu Dev, Yijie Shen

Twistronics, the study of moir\'e superlattices of twisted bilayer 2D materials creating nontrivial physical effects, has recently revolutionized diverse subjects from materials to optoelectronics, nanophotonics, and beyond. Here, breaking the reliance on materials, we present twistronics in higher-dimensional free space, where the twisted lattice is not a l

Chung Peng Lee, Rachel Hong, Harry H. Jiang, Aster Plotnik

The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners' wishes. Ignoring the owner's indication of consent around data usage not only raises ethical concerns but also has recently

Jiangwen Dong, Zehui Lin, Wanyu Lin, Mingjin Zhang

Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as mixture-of-experts, typically operate at the task level; they are too coarse to effectively solve the heterogeneous probl

Shubham Agarwal, Subrata Mitra, Saud Iqbal

Text-to-image (T2I) models have gained significant popularity. Most of these are diffusion models with unique computational characteristics, distinct from both traditional small-scale ML models and large language models. They are highly compute-bound and use an iterative denoising process to generate images, leading to very high inference time. This creates

Evelyn Chee, Wynne Hsu, Mong Li Lee

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing diverse sensory inputs, akin to human perception. However, multi-modal continual learning presents additional challenges,

Jianyu Qi, Ding Zou, Wenrui Yan, Rui Ma

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms based on reinforcement learning (RL), focusing predominantly on mathematical datasets. However, existing post-training p

Yuda Qiu, Zitong Xiao, Yiwei Zuo, Zisheng Ye

We present AvatarTex, a high-fidelity facial texture reconstruction framework capable of generating both stylized and photorealistic textures from a single image. Existing methods struggle with stylized avatars due to the lack of diverse multi-style datasets and challenges in maintaining geometric consistency in non-standard textures. To address these limita

Thomas Cook, Kelly Patel, Sivapriya Vellaichamy, Udari Madhushani Sehwag

Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in text-to-SQL, where a learning agent receives natural language feedback to refine queries and distills the revealed knowledge for re

Patrick Huber, Ernie Chang, Wei Wen, Igor Fedorov

Efficient on-device language models around 1 billion parameters are essential for powering low-latency AI applications on mobile and wearable devices. However, achieving strong performance in this model class, while supporting long context windows and practical deployment remains a significant challenge. We introduce MobileLLM-Pro, a 1-billion-parameter lang

Shiwei Sang, Shao-Bo Lin, Xuehu Zhu

The widespread adoption of the \emph{maximum mean discrepancy} (MMD) in goodness-of-fit testing has spurred extensive research on its statistical performance. However, recent studies indicate that the inherent structure of MMD may constrain its ability to distinguish between distributions, leaving room for improvement. Regularization techniques have the pote

Han Liu, Hengyu Man, Xingtao Wang, Wenrui Li

Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces via convolutional neural networks (CNNs) or Swin Transformers, which tend to retain substantial spatial redundancy, the

Rui Song, Jiaying Lin, Rynson W. H. Lau

Video mirror detection has received significant research attention, yet existing methods suffer from limited performance and robustness. These approaches often over-rely on single, unreliable dynamic features, and are typically built on CNNs with limited receptive fields or Transformers with quadratic computational complexity. To address these limitations, w

Jinyong Yun, Hyungjin Kim, Seokho Ahn, Euijong Lee

Most on-device sensor calibration studies benchmark models only against three macroscopic requirements (i.e., accuracy, real-time, and resource efficiency), thereby hiding deployment bottlenecks such as instantaneous error and worst-case latency. We therefore decompose this triad into eight microscopic requirements and introduce Scare (Sensor Calibration mod

Yuheng Luo, Chuanzhe Zhang, Qingsong Liu, Hai Zhu

Opinion dynamics has recently been modeled from a game-theoretic perspective, where opinion updates are captured by individuals' cost functions representing their motivations. Conventional formulations aggregate multiple motivations into a single objective, implicitly assuming that these motivations are interchangeable. This paper challenges that assumpt

Liucheng Chen, Jiayi Yue, Jingwen Cheng, Jianli Bai

Among the complex many-body systems, the metal-insulator transition stands out as a cornerstone and a particularly fertile ground for scientific inquiry. The established models including Mott insulator, Anderson localization and Peierls transition, are still insufficient to capture the complex and intertwined phenomena observed in certain material systems. K

Qiuyang Fu, Mengyao Xue, Weiwei Zhu, N. D. R. Bhat

Pulsar searching with next-generation radio telescopes requires efficiently sifting through millions of candidates generated by search pipelines to identify the most promising ones. This challenge has motivated the utilization of Artificial Intelligence (AI)-based tools. In this work, we explore an optimized pulsar search pipeline that utilizes deep learning

Hao Sun, Xianghao Yu, Junting Chen

This paper proposes a novel structure-aware matrix completion framework assisted by radial basis function (RBF) interpolation for near-field radio map construction in extremely large multiple-input multiple-output (XL-MIMO) systems. Unlike the far-field scenario, near-field wavefronts exhibit strong dependencies on both angle and distance due to spherical wa

Sicheng Yang, Zhaohu Xing, Haipeng Zhou, Lei Zhu

Virtual staining offers a promising method for converting Hematoxylin and Eosin (H&E) images into Immunohistochemical (IHC) images, eliminating the need for costly chemical processes. However, existing methods often struggle to utilize spatial information effectively due to misalignment in tissue slices. To overcome this challenge, we leverage keypoints as r

Adi Danish Bin Muhammad Amin, Mohaiminul Islam Bhuiyan, Nur Shazwani Kamarudin, Zulfahmi Toh

The rapid evolution of the gaming industry, driven by technological advancements and a burgeoning community, necessitates a deeper understanding of user sentiments, especially as expressed on popular social media platforms like YouTube. This study presents a sentiment analysis on video games based on YouTube comments, aiming to understand user sentiments wit

Zhi-Peng Ma, Kai Wang, Yuan-Yuan Zuo, Yuan-Chuan Zou

Following the identification of the first confirmed individual neutrino source, Seyfert galaxies have emerged as the most prominent class of high-energy neutrino emitters. In this work, we perform a detailed investigation of the outflow--cloud interaction scenario for neutrino production in Seyfert nuclei. In this framework, fast AGN-driven winds collide wit

Atharva Naik, Bijay Kumar Agarwalla, Manas Kulkarni

We investigate the dynamics of number entropy in a chain of free fermions subjected to both defects and stochastic processes. For a special class of defects, namely conformal defects, we present analytical and numerical results for the temporal growth of number entropy, the time evolution of the number distribution, and the eigenvalue profile of the associat

Wen-Hao Yao, Xiaowen Li, Hui Dong, Shu-Yi Wei

Jets produced in association with a $Z^{0}$ or $W^{\pm}$ boson in hadronic collisions are automatically polarized due to the parity violation of weak interaction, making these processes ideal for understanding the spin transfer from polarized partons to polarized hadrons. Furthermore, leveraging this feature, we can also employ the weak-boson-tagged process

Simon K. Yung, Aritra Das, Jun Suzuki, Ping Koy Lam

Measurement incompatibility is a cornerstone of quantum mechanics. In the context of estimating multiple parameters of a quantum system, this manifests as a fundamental trade-off between the precisions with which different parameters can be estimated. Often, a parameter can be optimally measured, but at the cost of gaining no information about incompatible p

Mohaiminul Islam Bhuiyan, Nur Shazwani Kamarudin, Nur Hafieza Ismail

Worldwide, suicide is the second leading cause of death for adolescents with past suicide attempts to be an important predictor for increased future suicides. While some people with suicidal thoughts may try to suppress them, many signal their intentions in social media platforms. To address these issues, we propose a new type of hybrid deep learning scheme,

Steffen M. Recktenwald, Vincenzo Calabrese, Amy Q. Shen, Giovanniantonio Natale

We perform a combined experimental and theoretical investigation of the orientational dynamics of rod-like colloidal particles in dilute suspension as they are subjected to a time-dependent homogeneous planar elongational flow. Our experimental approach involves the flow of dilute suspensions of cellulose nanocrystals (CNC) within a cross-slot-type stagnatio

Yifan Wang, Yian Zhao, Fanqi Pu, Xiaochen Yang

Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm, which employs multiple branches to estimate geometric center, depth, dimensions, and rotation angle separately. Although this decoupling strategy simplifies the learning process, it inherently ignores the geometric coll

Damian Curran, Vanessa Sporne, Lea Frermann, Jeannie Paterson

How do we make a meaningful comparison of a large language model's knowledge of the law in one place compared to another? Quantifying these differences is critical to understanding if the quality of the legal information obtained by users of LLM-based chatbots varies depending on their location. However, obtaining meaningful comparative metrics is challengin

Sourav Ganguly, Arnob Ghosh

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision processes (RCMDPs), where the agent must maximize reward while ensuring cumulative utility exceeds a threshold under the worst-c

Dahye Cho, Hansol Hong, Hyeongjun Jin, Sangwook Lee

For all punctured Riemann surfaces arising as mirror curves of toric Calabi--Yau threefolds, we show that their symplectic cohomology is isomorphic to the compactly supported Hochschild cohomology of the noncommutative Landau--Ginzburg model defined on the NCCR of the associated toric Gorenstein singularities. This mirror correspondence is established by ana

Jing Shang, James Bannon, Benjamin Haibe-Kains, Robert Tibshirani

Random forests are a statistical learning technique that use bootstrap aggregation to average high-variance and low-bias trees. Improvements to random forests, such as applying Lasso regression to the tree predictions, have been proposed in order to reduce model bias. However, these changes can sometimes degrade performance (e.g., an increase in mean squared

Dian Jin, Yancheng Yuan, Xiaoming Tao

Pretrained equivariant graph neural networks based on spherical harmonics offer efficient and accurate alternatives to computationally expensive ab-initio methods, yet adapting them to new tasks and chemical environments still requires fine-tuning. Conventional parameter-efficient fine-tuning (PEFT) techniques, such as Adapters and LoRA, typically break symm

Takuma Aihara

We give several examples of tilting-discrete symmetric algebras; in particular, one explores which algebra has tilting-discrete trivial extension. We provide a counter example of the conjecture stating any {\tau} -tilting finite symmetric algebra is tiltingdiscrete. Also, we discuss the tilting-disconnectedness of symmetric algebras and give new examples of

Jose Marie Antonio Minoza, Rex Gregor Laylo, Christian F Villarin, Sebastian C. Ibanez

Machine learning inference occurs at a massive scale, yet its environmental impact remains poorly quantified, especially on low-resource hardware. We present ML-EcoLyzer, a cross-framework tool for measuring the carbon, energy, thermal, and water costs of inference across CPUs, consumer GPUs, and datacenter accelerators. The tool supports both classical and

Rakshak Adhikari

The dynamics of highly magnetized plasmas in extreme astrophysical environments are effectively modeled by Force-Free Electrodynamics (FFE), a framework essential for studying objects like neutron stars and accreting black holes. The inherently nonlinear nature of the FFE equations makes finding exact solutions a challenging task. This paper explores an inno

Tao Li, Kaiyuan Hou, Tuan Vinh, Monika Raj

Deep models are used for molecular property prediction, yet they are often difficult to interpret and may rely on spurious context rather than causal structure, which reduces reliability under distribution shift and harms predictive performance. We introduce CLaP (Causal Layerwise Peeling), a framework that separates causal signal from context in a layerwise

A. Hari Govindha, Sayak Banerjee, Saravanan Balusamy, Kirti Chandra Sahu

The evaporation of sessile droplets placed in close proximity is influenced by complex vapor-vapor interactions, producing a shielding effect that can significantly extend droplet lifetimes. This study presents a systematic experimental investigation of evaporation dynamics in multi-droplet configurations under ambient conditions, comparing completely pinned

Jens Flemming, Bernd Hofmann

Motivated by a seminal paper of professor M. Z. Nashed published in 1987 on classification of ill-posed linear operator equations and distinguishing two types of ill-posedness in Banach and Hilbert spaces, we present, illustrate and justify a new classification scheme in this context. This scheme classifies bounded linear operators mapping between infinite-d

Sudip Bera

The deep interconnection between linear algebra and graph theory allows one to interpret classical matrix invariants through combinatorial structures. To each square matrix A over a commutative ring K, one can associate a weighted directed graph D(A), where the algebraic behavior of A is reflected in the combinatorial properties of D(A). In particular, the d

Chadani Acharya

Public dashboards are now a common way for US government agencies to share high stakes information with residents. We audited six live systems at federal, state, and city levels: CDC respiratory illness, HUD homelessness PIT and HIC, California HCD Annual Progress Report, New York City Mayor's Management Report, Houston Permitting, and Chicago public health

Yulim So, Seokho Kang

Anomaly generation has been widely explored to address the scarcity of anomaly images in real-world data. However, existing methods typically suffer from at least one of the following limitations, hindering their practical deployment: (1) lack of visual realism in generated anomalies; (2) dependence on large amounts of real images; and (3) use of memory-inte

Heshan Fernando, Quan Xiao, Parikshit Ram, Yi Zhou

Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that multi-modal sensor training dynamics are often imbalanced: fast-to-learn sensing channels dominate optimization, while slower channels remain underutilized, degrading reliability

Su Jia, Peter Frazier, Nathan Kallus, Christina Lee Yu

We study the estimation of the ATE in randomized controlled trials under a dynamically evolving interference structure. This setting arises in applications such as ride-sharing, where drivers move over time, and social networks, where connections continuously form and dissolve. In particular, we focus on scenarios where outcomes exhibit spatio-temporal inter

Chen Zhang, Wen-Biao Han

We derive the approximate analytical solutions of the bound timelike geodesic orbits in the effective-one-body (EOB) frame with extreme-mass ratio limit. The analytical solutions are expressed in terms of the elliptic integrals using Mino time $\lambda$ as the independent variable. Since Mino time decouples the $r$ and $\theta$-motion, we also give explicit

Shibing Mo, Haoyang Ruan, Kai Wu, Jing Liu

Large Language Models (LLMs) have demonstrated remarkable generalization capabilities, but aligning their outputs with human preferences typically requires expensive supervised fine-tuning. Recent test-time methods leverage textual feedback to overcome this, but they often critique and revise a single candidate response, lacking a principled mechanism to sys

Richard Hou, Shengpu Tang, Wei Jin

Accurate predictions of conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) can enable effective personalized therapy. While cognitive tests and clinical data are routinely collected, they lack the predictive power of PET scans and CSF biomarker analysis, which are prohibitively expensive to obtain for every patient. To address this c

Ravindra Ganti, Steve Xu

We present XgenSilicon ML Compiler, a fully automated end-to-end compilation framework that transforms high-level machine learning models into optimized RISC-V assembly code for custom ASIC accelerators. By unifying the system's cost model across software and hardware, the compiler achieves significant improvements in Power, Performance, and Area (PPA) metri

Keunhyeung Park, Seunguk Yu, Youngbin Kim

Standard-to-dialect machine translation remains challenging due to a persistent dialect gap in large language models and evaluation distortions inherent in n-gram metrics, which favor source copying over authentic dialect translation. In this paper, we propose the dialect refinement (DIA-REFINE) framework, which guides LLMs toward faithful target dialect out

Sangun Choi, Yunho Oh

Embedding vector operations are a key component of modern deep neural network workloads. Unlike matrix operations with deterministic access patterns, embedding vector operations exhibit input data-dependent and non-deterministic memory accesses. Existing neural processing unit (NPU) simulators focus on matrix computations with simple double-buffered on-chip

Xingbo Du, Qiantong Dou, Lei Fan, Rui Zhang

Concept bottleneck models (CBMs) improve neural network interpretability by introducing an intermediate layer that maps human-understandable concepts to predictions. Recent work has explored the use of vision-language models (VLMs) to automate concept selection and annotation. However, existing VLM-based CBMs typically require full model retraining when new

Swetha Rani Kasimalla, Kuchan Park, Junho Hong, Young-Jin Kim

Enhancing the reliability of AI based fault diagnosis in inverter dominated microgrids requires diverse and statistically balanced datasets. However, the scarcity and imbalance of high fidelity fault data, especially for rare inverter malfunctions and extreme external line faults, limit dependable model training and validation. This paper introduces a unifie

Wenqi Cao, Aming Li

Conventional topology learning methods for dynamical networks become inapplicable to processes exhibiting low-rank characteristics. To address this, we propose the low rank dynamical network model which ensures identifiability. By employing causal Wiener filtering, we establish a necessary and sufficient condition that links the sparsity pattern of the filte

Joel Kemp, Andre Farinha, David Howard, Krishna Manaswi Digumarti

Soft Robotics presents a rich canvas for free-form and continuum devices capable of exerting forces in any direction and transforming between arbitrary configurations. However, there is no current way to tractably and directly exploit the design freedom due to the curse of dimensionality. Parameterisable sets of designs offer a pathway towards tractable, mod

Ben Harper, Azar C. Nakhl, Thomas Quella, Martin Sevior

Classical simulations of quantum systems are notoriously difficult computational problems, with conventional state vector and tensor network methods restricted to quantum systems that feature only a small number of qudits. The recently introduced Clifford Augmented Matrix Product State (CAMPS) method offer scalability and efficiency by combining both tensor

Qing Guo, Chengxiang Zhang

We establish the existence of infinitely many nonnegative, segregated solutions for the sublinearly coupled Schr\"odinger system \begin{equation*} \left\{\begin{aligned}-\Delta u+K_1(x)u&=\mu u^{p-1}+ (\sigma_1+1)\beta u^{\sigma_1}v^{\sigma_2+1}, &x\in\mathbb{R}^N&, -\Delta v+K_2(x)v&=\nu v^{p-1}+(\sigma_2+1)\beta u^{\sigma_1+1}v^{\sigma_2}, &x\in\mathbb{R}^

A. Waszewski, J. S. Morgan, M. C. M. Cheung, R. Ekers

We have conducted a comprehensive comparison of interplanetary scintillation (IPS) observations taken by the Murchison Widefield Array (MWA) with several heliospheric transient event catalogues, over a time period of 7 months during solar minimum. From this analysis we have found that of the 84% of catalogued events that have MWA IPS data available, 68% of t

Mathieu Yahiaoui, Mario Kieburg

To classify one-dimensional disordered quantum systems with chiral symmetry, we analyse the winding number of the determinant of a parametrized non-Hermitian random matrix field over the unit circle modelling the off-diagonal block of a disordered chiral Hamiltonian. The associated partition function is computed explicitly for a broad class of additive two-m

Saeedeh Javadi, Sara Mirabi, Manan Gangar, Bahadorreza Ofoghi

In high-stakes information domains such as healthcare, where large language models (LLMs) can produce hallucinations or misinformation, retrieval-augmented generation (RAG) has been proposed as a mitigation strategy, grounding model outputs in external, domain-specific documents. Yet, this approach can introduce errors when source documents contain outdated

Chaehee Song, Sanmin Kim, Hyeonjun Jeong, Juyeb Shin

Vision-based 3D occupancy prediction has made significant advancements, but its reliance on cameras alone struggles in challenging environments. This limitation has driven the adoption of sensor fusion, among which camera-radar fusion stands out as a promising solution due to their complementary strengths. However, the sparsity and noise of the radar data li

Lingran Song, Yucheng Zhou, Jianbing Shen

Despite significant progress in pixel-level medical image analysis, existing medical image segmentation models rarely explore medical segmentation and diagnosis tasks jointly. However, it is crucial for patients that models can provide explainable diagnoses along with medical segmentation results. In this paper, we introduce a medical vision-language task na

Zhao-Yang Wu, Zi-Yue Bai, Li-Ming Wang

The properties of light vector mesons near 2.2 GeV remain poorly understood, impeding progress in mapping the higher-lying hadronic spectrum. Utilizing the newly released BESIII data on the Born cross sections for the process of $e^+ e^- \rightarrow b_1(1235) \pi$, we conduct a combined analysis incorporating theoretical predictions for the mass spectrum and

Franklin Lee, Tengfei Ma

Drug-drug interactions (DDIs) remain a major source of preventable harm, and many clinically important mechanisms are still unknown. Existing models either rely on pharmacologic knowledge graphs (KGs), which fail on unseen drugs, or on electronic health records (EHRs), which are noisy, temporal, and site-dependent. We introduce, to our knowledge, the first s

Tapti Palit, Seyedhamed Ghavamnia, Michalis Polychronakis

Precise and sound call graph construction is crucial for many software security mechanisms. Unfortunately, traditional static pointer analysis techniques used to generate application call graphs suffer from imprecision. These techniques are agnostic to the application's architecture and are designed for broad applicability. To mitigate this precision problem

Yishuai Wang, Wenze Pan, Meng Zhang, Yanwu Xie

Superconducting diodes, which enable dissipationless supercurrent flow in one direction while blocking it in the reverse direction, are emerging as pivotal components for superconducting electronics. The development of editable superconducting diodes could unlock transformative applications, including dynamically reconfigurable quantum circuits that adapt to

Jiawei Huang, Aimin Wang, Geng Sun, Jiahui Li

Low-altitude wireless networks (LAWNs) have emerged as a viable solution for maritime communications. In these maritime LAWNs, unmanned aerial vehicles (UAVs) serve as practical low-altitude platforms for wireless communications due to their flexibility and ease of deployment. However, the open and clear UAV communication channels make maritime LAWNs vulnera

Depanshu Sani, Mehar Khurana, Saket Anand

Animal Re-ID has recently gained substantial attention in the AI research community due to its high impact on biodiversity monitoring and unique research challenges arising from environmental factors. The subtle distinguishing patterns, handling new species and the inherent open-set nature make the problem even harder. To address these complexities, foundati

Gen Yang, Zhipeng Deng, Junfeng Man

The primary objective of Continual Anomaly Detection (CAD) is to learn the normal patterns of new tasks under dynamic data distribution assumptions while mitigating catastrophic forgetting. Existing embedding-based CAD approaches continuously update a memory bank with new embeddings to adapt to sequential tasks. However, these methods require constructing cl

Xia Wang, Donglei Yang

A graph $G$ is $m$-joined if there is an edge between every two disjoint $m$-sets of vertices. In this paper, we prove that for any $\varepsilon>0$ and sufficiently large $m, n\in \mathbb{N}$ with $m \le n^{1-\varepsilon}$, every $n$-vertex $m$-joined graph $G$ contains a minor with density $\Omega\!\left(\tfrac{n}{\sqrt{m}}\right)$, which is best possible u

Fangu Chen

Elkies proved the infinitude of supersingular primes for elliptic curves over real number fields. We generalize Elkies' result to some abelian fourfolds in Mumford's families, and more generally, to certain families of Kuga-Satake abelian varieties. The proof relies on the study of local deformation spaces at closed points of the integral model of a Hodge-ty

Ruijia Wu, Ping Chen, Fei Shen, Shaoan Zhao

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting their ability to handle complex, compositional, and long-form descriptions. In particular, they fail to capture two ess

Yong Wu, Shuyuan Wu, Xinwei Sun, Xuening Zhu

We study estimation of the average treatment effect (ATE) from a single network in observational settings with interference. The weak cross-unit dependence is modeled via an endogenous peer-effect (network autoregressive) term that induces distance-decaying network dependence, relaxing the common finite-order interference to infinite interference. We propose

Jiantang Huang

Basketball broadcast footage is traditionally captured at 30-60 fps, limiting viewers' ability to appreciate rapid plays such as dunks and crossovers. We present a real-time slow-motion synthesis system that produces high-quality basketball-specific interpolated frames by fine-tuning the recent Real-Time Intermediate Flow Estimation (RIFE) network on the Spo

Kyung-Yoon Yoon, Yeong-Jun Cho

In this study, we propose NOVO (NO text, Visual-Only prompts), a novel framework that bridges vision-language models (VLMs) and segmentation models through visual-only prompts. Unlike prior approaches that feed text-derived SEG token embeddings into segmentation models, NOVO instead generates a coarse mask and point prompts from the VLM output. These visual

Norbert Hegyvari, Janos Pach, Thang Pham

Raimi's theorem guarantees the existence of a partition of $\mathbb{N}$ into two parts with an unavoidable intersection property: for any finite coloring of $\mathbb{N}$, some color class intersects both parts infinitely many times, after an appropriate shift (translation). We establish a polynomial extension of this result, proving that such intersections p

Bin Rao, Chengyue Wang, Haicheng Liao, Qianfang Wang

Long-tail motion forecasting is a core challenge for autonomous driving, where rare yet safety-critical events-such as abrupt maneuvers and dense multi-agent interactions-dominate real-world risk. Existing approaches struggle in these scenarios because they rely on either non-interpretable clustering or model-dependent error heuristics, providing neither a d

Siqi Hui, Sanping Zhou, Ye deng, Wenli Huang

Cross-domain few-shot learning (CD-FSL) aims to recognize novel classes with only a few labeled examples under significant domain shifts. While recent approaches leverage a limited amount of labeled target-domain data to improve performance, the severe imbalance between abundant source data and scarce target data remains a critical challenge for effective re

Xu-hui Han, Pin-pin Zhang, Yu-jie Xiao, Ruo-song Zhang

The Sino-French SVOM (Space Variable Objects Monitor) mission is a space-based astronomy mission complemented with ground-based dedicated instrumentation. It aims to explore and study high-energy cosmic phenomena, such as gamma-ray bursts (GRBs). This unprecedented combination of space-based and ground-based instruments will provide leading multi-wavelength

Kimya Yadollahpour, Hossein Khodavirdi, Ankit Srivastava

In this paper, we elucidate the concept of local acoustic metamaterials. These are composites which exhibit equi-frequency contours (EFC) which correspond to those expected of homogeneous local acoustic media. We show that EFCs for local acoustic media are conics in 2-dimension and quadrics in 3-dimension. In 2-D, the sure signature of negative properties is

Xingchi Li, Xiaochi Liu, Guanxun Li

The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One promising approach to address this issue is the watermark technique, which embeds subtle statistical signals into LLM-generate

Jie Zhang, Ya-Lei Jin, Hua Wang, Jin-Xuan Yang

In 1986, Brualdi and Solheid firstly proposed the problem of determining the maximum spectral radius of graphs in the set $\mathcal{H}_{n,m}$ consisting of all simple connected graphs with $n$ vertices and $m$ edges, which is a very tough problem and far from resolved. The $A_{\alpha}$-spectral radius of a simple graph of order $n$, denoted by $\rho_\alpha(G

Mohammadreza M. Kalan, Yuyang Deng, Eitan J. Neugut, Samory Kpotufe

We consider the problem of transfer learning in Neyman-Pearson classification, where the objective is to minimize the error w.r.t. a distribution $\mu_1$, subject to the constraint that the error w.r.t. a distribution $\mu_0$ remains below a prescribed threshold. While transfer learning has been extensively studied in traditional classification, transfer lea

Kevin Du, Yash Nair, Lucas Janson

Uncertainty quantification (UQ) for adaptively collected data, such as that coming from adaptive experiments, bandits, or reinforcement learning, is necessary for critical elements of data collection such as ensuring safety and conducting after-study inference. The data's adaptivity creates significant challenges for frequentist UQ, yet Bayesian UQ remains t

Fahadul Islam, Sunil Dhar

This investigation is a rigorous theoretical study of the Single Differential Cross Section (SDCS) for the ionization of hydrogen in the 3s state by electron impact computed by means of the First-Born Approximation. The transition matrix has been found by means of the integral process of Bethe-Lewis. The effect of the Coulomb attractive force and the continu

Tim Van Hoose

We prove a modified scattering and sharp $L^\infty$ decay result for both the Hartree and Schr\"odinger-Bopp-Podolsky equations in dimensions $2$ and $3$ using the testing by wavepackets approach due to Ifrim and Tataru. We show that modified scattering and sharp pointwise decay occur for these equations at a regularity much lower than previous results due t

Gözde Üstün, Simon J. Devitt

In this work, we compare two schemes for generating arbitrary qudit graph states using spin qudits in silicon. The first scheme proposes the creation of qudit linear graph states from a single emitter - a silicon spin qudit. By employing fusion - a destructive and non-deterministic measurement technique - these linear graphs can then be combined to form more

Lulu Yu, Keping Bi, Jiafeng Guo, Shihao Liu

Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly. Click data has been widely used as a low-cost alternative, and with recent advances in large language models (LLMs), LLM-based relevance annotation has emerged as another promising annotation. This paper investigates whether LL

Kaiyuan Zhai, Jiacheng Cui, Zhehao Zhang, Junyu Xue

Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both costly and impractical. Yet, this task remains highly challenging due to the scarcity and heterogeneity of data across different buildings, climate zones, and seasonal patterns. In par

Qinghong Guo, Yu Wang, Ji Cao, Tongya Zheng

Road network representation learning (RNRL) has attracted increasing attention from both researchers and practitioners as various spatiotemporal tasks are emerging. Recent advanced methods leverage Graph Neural Networks (GNNs) and contrastive learning to characterize the spatial structure of road segments in a self-supervised paradigm. However, spatial heter