November 2025 arXiv papers — page 168

Chao Zhang

We study bipolaron formation and bipolaronic superconductivity on a square lattice, where electrons couple to both local Holstein phonons via on-site charge density and nonlocal bond Su-Schrieffer-Heeger phonons via modulation of hopping amplitudes. Using an unbiased Diagrammatic Monte Carlo method, we investigate how the interplay between these two types of

Long Yuan, Hongxing Rui

We propose an abstract discontinuous Galerkin neural network (DGNN) framework for analyzing the convergence of least-squares methods based on the residual minimization when feasible solutions are neural networks. Within this framework, we define a quadratic loss functional as in the least square method with $h-$refinement and introduce new discretization set

Athul M. Mathew, Haithem Hermassi, Thariq Khalid, Arshad Ali Khan

Gaze understanding unifies the detection of people, their gaze targets, and objects of interest into a single framework, offering critical insight into visual attention and intent estimation. Although prior research has modelled gaze cues in visual scenes, a unified system is still needed for gaze understanding using both visual and language prompts. This pa

Milena Radnović, Ruzzel Ragas

In the projective plane over a finite field of characteristic not equal to 2, we compute the probability that a randomly selected pair of distinct conics $(\mathscr{A},\mathscr{B})$, with $\mathscr{A}$ smooth or singular and $\mathscr{B}$ smooth, in a fixed pencil of conics will admit a triangle or a tetragon inscribed in $\mathscr{A}$ and circumscribed abou

Liya Zhu, Peizhuang Cong, Jingzhe Ding, Aowei Ji

Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, expertise-intensive knowledge in real-world professional scenarios. We introduce LPFQA, a long-tail knowledge benchmark derived from authentic professional forum discussions, covering

Kelun Lei, Hailong Yang, Huaitao Zhang, Xin You

Designing high-performance kernels requires expert-level tuning and a deep understanding of hardware characteristics. Recent advances in large language models (LLMs) have enabled automated kernel generation, yet most existing systems rely solely on correctness or execution time feedback, lacking the ability to reason about low-level performance bottlenecks.

Zhirui Zhang, Changhua Pei, Tianyi Gao, Zhe Xie

In the time-series domain, an increasing number of works combine text with temporal data to leverage the reasoning capabilities of large language models (LLMs) for various downstream time-series understanding tasks. This enables a single model to flexibly perform tasks that previously required specialized models for each domain. However, these methods typica

Shen Bian

We consider a two-species chemotaxis model in $\R^d(d \ge 3)$ featuring nonlinear porous medium-type diffusion and nonlocal attractive power-law interaction. Here, the nonlinear diffusion is chosen to be $1/m_1+1/m_2=(d+2)/d$ in such a way that the associated free energy is conformal invariant, and there are radially symmetric, non-increasing and non-compact

Naoki Kitazawa

Regions in the Euclidean plane surrounded by circles are fundamental geometric and combinatorial objects. Related studies have been done and we cannot explain them precisely, or roughly, well. We study such regions whose Poincar\'e-Reeb graphs are trees and investigate the trees obtained by a certain inductive rule from a disk in the plane. The Poincar\'e-Re

Nikolaus Vertovec, Frederik Baymler Mathiesen, Thom Badings, Luca Laurenti

Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as neural networks have shown great promise due to their expressiveness and applicability to a broad class of dynamics and safety constraints. However, verifying that a trained neural network is indeed a valid CBF is

Benjamin P. Riley, Prodromos Daoutidis, Qi Zhang

Two-stage stochastic mixed-integer linear programs with mixed-integer recourse arise in many practical applications but are computationally challenging due to their large size and the presence of integer decisions in both stages. The integer L-shaped method with alternating cuts is a widely used decomposition algorithm for these problems, relying on optimali

Shasha Liu, Hayssam Dahrouj, Abla Kammoun, Mohamed-Slim Alouini

Balancing throughput and fairness promises to be a key enabler for achieving large-scale digital inclusion in future vertical heterogeneous networks (VHetNets). In an attempt to address the global digital divide problem, this paper explores a multi-high-altitude platform system (HAPS)-ground integrated network, in which multiple HAPSs collaborate with ground

Zong Shang

Using the generic chaining method, we derive upper bounds for the \(L^q\) process of sub-Gaussian classes when \(1 \le q \le 2\), thereby resolving an open problem posed by Al-Ghattas, Chen, and Sanz-Alonso in arXiv:2502.16916. Combined with the results of arXiv:2502.16916, this yields upper bounds for the \(L^q\) process for all \(1 \le q < \infty\). We als

Shangfeng Huang, Ruisheng Wang, Xin Wang

As digital twins become central to the transformation of modern cities, accurate and structured 3D building models emerge as a key enabler of high-fidelity, updatable urban representations. These models underpin diverse applications including energy modeling, urban planning, autonomous navigation, and real-time reasoning. Despite recent advances in 3D urban

Chengcai Liu, Siwei Chen, Zejun Xiang, Shasha Zhang

At CRYPTO 2019, Gohr pioneered neural cryptanalysis by introducing differential-based neural distinguishers to attack Speck32/64, establishing a novel paradigm combining deep learning with differential cryptanalysis.Since then, constructing neural distinguishers has become a significant approach to achieving the deep learning-based cryptanalysis for block ci

Ehsan Asadi, Davood Keshavarzi, Alexander Koehler, Nima Tashakor

The share of electronically converted power from renewable sources, loads, and storage is continuously growing in the low- and medium-voltage grids. These sources and loads typically rectify the grid AC to DC, e.g., for a DC link, so that a DC grid could eliminate hardware and losses of these conversion stages. However, extended DC grids lack the stabilizing

Jinqi Xiao, Cheng Luo, Lingyi Huang, Cheng Yang

Transformers have become the backbone of modern AI, yet their high computational demands pose critical system challenges. While sparse training offers efficiency gains, existing methods fail to preserve critical structural relationships between weight matrices that interact multiplicatively in attention and feed-forward layers. This oversight leads to perfor

Mousomi Bhakta, Anup Biswas, Aniket Sen

We prove that any nonnegative viscosity solution of the inequality $$(-\Delta_p)^s u(x) \geq u^{t} |\nabla u|^{m}\quad \text{ in }\; \mathbb{R}^N,\; N\geq 2,$$ must be constant. This result holds for parameters $p\in (1, \infty), s\in (0, 1)$, $t, m\geq 0$, satisfying $$t (N-sp) + m(N-(sp-p+1)) < N(p-1),$$ with the additional condition that either $m\leq p-1

Amitava Choudhuri, Modhan Mohan Panja, Supriya Chatterjee, Benoy Talukdar

We emphasize that construction of travelling wave solutions for partial differential equations is a problem of considerable interest and thus introduce a simple algebraic method to generate such solutions for equations in the Burgers hierarchy. Our method based on a judicious use of the well known Cole-Hopf transformation is found to work satisfactorily for

Kentaro Sakai, Kentaro Tomita, Takeo Hoshi, Akito Nakano

We discuss the conceptual design of a spatially-resolved spectroscopy system of Thomson scattering with high wavelength resolution capable of measuring the shape of electron velocity distribution functions in magnetically confined plasmas. We design a spatially-resolved spectrometer with 2560 wavelength channels. The estimated number of scattered photons in

Fei Li, Junjie Cao

This study presents a comparative analysis of the Minimal Supersymmetric Standard Model (MSSM), the $Z_3$-symmetric Next-to-Minimal Supersymmetric Standard Model ($Z_3$-NMSSM), and the General Next-to-Minimal Supersymmetric Standard Model (GNMSSM), incorporating constraints from dark matter (DM) relic density, the LUX-ZEPLIN 2024 experiment (LZ 2024), Higgs

Dingkang Yang, Mingcheng Li, Xuecheng Wu, Zhaoyu Chen

Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal fused representations. Existing approaches typically adopt fixed primary modality strategies to maximize dominant modality advantages, yet fail to adapt to dynamic variations in m

Abdelkader Hidki, Amjad Sohail, Tesfay Gebremariam Tesfahannes, Mulugeta Tadesse Bedore

We investigate quantum coherence in a hybrid cavity magnomechanical system incorporating a squeezed-magnon drive. By analyzing the Gaussian quantum coherence of the cavity, magnonic, and mechanical subsystems, as well as the total system coherence, we identify the critical roles of phase control, coupling strength, drive power, and thermal noise. We show tha

Fikret H. Güngör

We present a systematic study of logical gadgets for 3-coloring under a single anchor constraint, where only one color representing logical falsehood is fixed to a vertex. We introduce a framework of what we call ladgets (logical gadgets), graph gadgets that implement Boolean functions. Then, we define a set of core gadgets, called primitives, which help ide

Minsuk Jang, Hyunseo Jeong, Minseok Son, Changick Kim

Context-based detection methods such as DetectGPT achieve strong generalization in identifying AI-generated text by evaluating content compatibility with a model's learned distribution. In contrast, existing image detectors rely on discriminative features from pretrained backbones such as CLIP, which implicitly capture generator-specific artifacts. However,

Lukas Flajsman, Lars Peeters, Armi Kosunen, Lide Yao

Er-substituted yttrium iron garnet (Er:YIG) holds the potential of combining the low magnetic damping of YIG with the telecom-band optical transitions of $\text{Er}^{3+}$ ions, making it a suitable material for hybrid optomagnonic devices and microwave-to-optical quantum transduction. We report the epitaxial growth of $\text{Er}_{x}\text{Y}_{3-x}\text{Fe}_{5

Gabriel Berk Pereira, Paul J. Goulart

We propose an acceleration scheme for first-order methods (FOMs) for convex quadratic programs (QPs) that is analogous to Anderson acceleration and the Generalized Minimal Residual algorithm for linear systems. We motivate our proposed method from the observation that FOMs applied to QPs typically consist of piecewise-affine operators. We describe our Krylov

N. V. Peskov

The process of preparing heterogeneous catalysts on porous supports includes a drying stage, in which the porous material, impregnated with an aqueous solution of the catalyst precursor, is dried, and the precursor is precipitated on the pore walls. The precipitate distribution throughout the support volume strongly influences the catalyst performance and du

Jiwoon Park

The $n$-component weakly coupled $|\varphi|^4$ model on the $\Z^d$ lattice ($d\ge 4$) exhibits a critical two-point correlation function with an exact polynomial decay in infinite volume, regardless of whether the interaction is short- or long-range. This paper presents a rigorous analysis of the system in both $\Z^d$ and a finite-volume torus. In a torus, w

Min Hee Park, Uhi Rinn Suh

In this paper, we find weak generating sets for a classical W-algebra $\mathcal{W}^k(\mathfrak{g},f)$ when $\mathfrak{g}=\mathfrak{sl}_N$ or $\mathfrak{sl}_{N_1|N_2}$. Furthermore, observing the relation between quantum and classical W-algebras, we further derive crucial information about the weak generating sets of quantum W-algebras at generic levels.

Seyma Yaman Kayadibi

This paper develops a mathematically rigorous, philosophically grounded framework for evaluating artificial memory systems, rooted in the metaphysical structure of Leibniz's Monadology. Building on a previously formalized metric, the Artificial Age Score (AAS), the study maps twenty core propositions from the Monadology to an information-theoretic architectu

Richard Mudd, Rina Friedberg, Ilya Gorbachev, Houssam Nassif

A 'Winner's Curse' arises in large-scale online experimentation platforms when the same experiments are used to both select treatments and evaluate their effects. In these settings, classical difference-in-means estimators of treatment effects are upwardly biased and conventional confidence intervals are rendered invalid. The bias scales with the magnitude o

A. Damas-Segovia, R. Beck, S. A. Mao, A. Basu

We seek to exploit the expanded observational range of the MeerKAT radio telescope with the new S-band receivers (2.0-2.8 GHz). To showcase its enhanced capabilities, we conducted new S-band observations of the galaxy NGC 2997 in full polarization. The S band is ideal for studying magnetic fields in spiral galaxies due to the weak Faraday depolarization. Per

Gur Elkin, Ofir Itzhak Shahar, Ohad Ben-Shahar

Square jigsaw puzzles are typically solved by visually matching piece images to recover the original layout. This work introduces PuzLM, an alternative perspective that recasts jigsaw reassembly as a discrete sequence-to-sequence (Seq2Seq) problem, inspired by natural language representations. We design an efficient puzzle quantization procedure that transfo

Xuan Yu, Tianyang Xu

Grassmannian manifold offers a powerful carrier for geometric representation learning by modelling high-dimensional data as low-dimensional subspaces. However, existing approaches predominantly rely on static single-subspace representations, neglecting the dynamic interplay between multiple subspaces critical for capturing complex geometric structures. To ad

Zhiyang Lyu, Yi Qi

We study the asymptotic behavior of extremal length along Teichm\"uller rays. Specifically, we determine the limit of extremal length along a Teichm\"uller ray and obtain an explicit expression for this limit, which complements a related formula established by Cormac Walsh. Building on this result and Kerckhoff's formula, we establish a formula for the limit

Stef Cuyckens, Xiaoling Yi, Robin Geens, Joren Dumoulin

Emerging continual learning applications necessitate next-generation neural processing unit (NPU) platforms to support both training and inference operations. The promising Microscaling (MX) standard enables narrow bit-widths for inference and large dynamic ranges for training. However, existing MX multiply-accumulate (MAC) designs face a critical trade-off:

Muhammad Faisal Khan

This thesis advances the spectral theory of structured matrix-sequences within the framework of Generalized Locally Toeplitz (GLT) $*$-algebras, focusing on the geometric mean of Hermitian positive definite (HPD) GLT sequences and its applications in mathematical physics. For two HPD sequences $\{A_n\}_n \sim_{\mathrm{GLT}} \kappa$ and $\{B_n\}_n \sim_{\math

Seiichi Yamamoto, Hiroki Ishizuka, Takumi Kawasetsu, Koh Hosoda

We present a tactile sensing method enabled by the mechanical compliance of soft robots; an externally attachable photoreflective module reads surface deformation of silicone skin to estimate contact force without embedding tactile transducers. Locating the sensor off the contact interface reduces damage risk, preserves softness, and simplifies fabrication a

Seunghyeok Shin, Dabin Kim, Hongki Lim

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from inflexibility -- they require conditioning signals during training, support only a fixed number of input views, and need complete re

Stephen Chung, Wenyu Du

We introduce the STATION, an open-world multi-agent environment for autonomous scientific discovery. The Station simulates a complete scientific ecosystem, where agents can engage in long scientific journeys that include reading papers from peers, formulating hypotheses, collaborating with peers, submitting experiments, and publishing results. Importantly, t

Sangwook Kim, Seunghyun Seo, Heesung Shin

In this article, we study (102,000)-avoiding inversion sequences with a fixed number of distinct elements. By introducing simple H-paths, we derive the trivariate generating function for these inversion sequences with respect to their length, number of distinct elements, and rank. As consequences, we obtain an explicit formula for the number of (102,000)-avo

Speed Zhu, Jianwei Cai, Guang Chen, Lulu Wu

Recent reasoning-first models (e.g., OpenAI o1, DeepSeek R1) have spurred a resurgence of interest in RLVR. Nevertheless, advances are dominated by mathematics (e.g., AIME), with competitive-programming code generation underexplored and data curation receiving less attention than RL algorithm design. We investigate how to construct RLVR datasets (i.e., RL pr

Yixuan Liu, Yingzhu Liu, Pengcheng You

Power system coherency refers to the phenomenon that machines in a power network exhibit similar frequency responses after disturbances, and is foundational for model reduction and control design. Despite abundant empirical observations, the understanding of coherence in complex power networks remains incomplete where the dynamics could be highly heterogeneo

Edwige Cyffers

This position paper argues that setting the privacy budget in differential privacy should not be viewed as an important limitation of differential privacy compared to alternative methods for privacy-preserving machine learning. The so-called problem of interpreting the privacy budget is often presented as a major hindrance to the wider adoption of differenti

Kevin Bönisch, Leandro Losaria

Since 2010, Kaggle has been a platform where data scientists from around the world come together to compete, collaborate, and push the boundaries of Data Science. Over these 15 years, it has grown from a purely competition-focused site into a broader ecosystem with forums, notebooks, models, datasets, and more. With the release of the Kaggle Meta Code and Ka

Noor Muhammad, Md. Nur Alam, Zhang Shiqing

Ebola virus disease is a severe hemorrhagic fever with rapid transmission through infected fluids and surfaces. We develop a fractional-order model using Caputo derivatives to capture memory effects in disease dynamics. An eight-compartment structure distinguishes symptomatic, asymptomatic, and post-mortem transmission pathways. We prove global well-posednes

Alberto Lastra, Cruz Prisuelos-Arribas, Victor Soto-Larrosa

The solution to systems of moment differential equations of the form $z\partial_my=(zA+B)y$ are provided, for a matrix $B$ with general good spectrum. Existence and convergence of Floquet-type solutions is studied. A generalized definition of $z^B$ is given, as a tool to solve the main problem whenever $A\equiv 0$. The theory is illustrated with examples whi

Azanzi Jiomekong, Jean Bikim, Patricia Negoue, Joyce Chin

Evaluating semantic tables interpretation (STI) systems, (particularly, those based on Large Language Models- LLMs) especially in domain-specific contexts such as the security domain, depends heavily on the dataset. However, in the security domain, tabular datasets for state-of-the-art are not publicly available. In this paper, we introduce Secu-Table datase

Bar Genossar, Sagi Dalyot, Roee Shraga, Avigdor Gal

Urban environments are continuously mapped and modeled by various data collection platforms, including satellites, unmanned aerial vehicles and street cameras. The growing availability of 3D geospatial data from multiple modalities has introduced new opportunities and challenges for integrating spatial knowledge at scale, particularly in high-impact domains

Haoqin Hong, Ding Fan, Fubin Dou, Zhi-Li Zhou

Recently, 3D Gaussian Splatting (3DGS), an explicit scene representation technique, has shown significant promise for dynamic novel-view synthesis from monocular video input. However, purely data-driven 3DGS often struggles to capture the diverse physics-driven motion patterns in dynamic scenes. To fill this gap, we propose Physics-Informed Deformable Gaussi

Xin Zuo, Chenyu Qu, Haibo Zhan, Jifeng Shen

Recent multispectral object detection methods have primarily focused on spatial-domain feature fusion based on CNNs or Transformers, while the potential of frequency-domain feature remains underexplored. In this work, we propose a novel Spatial and Frequency Feature Reconstruction method (SFFR) method, which leverages the spatial-frequency feature representa

Jihyeon Park, Jiyoon Myung, Seone Shin, Jungki Son

Designers often encounter friction when animating static SVG graphics, especially when the visual structure does not match the desired level of motion detail. Existing tools typically depend on predefined groupings or require technical expertise, which limits designers' ability to experiment and iterate independently. We present Decomate, a system that enabl

Junming Yuan, Ying Shi, Dong Wang, Lantian Li

Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. While effective in clean conditions, most existing approaches struggle with mixed keyword spotting--detecting multiple overlapping keywords within a single utterance--a capability es

Vamshika Sutar, Mahek Maheshwari, Archak Mittal

The automation of material handling in warehouses increasingly relies on robust, low cost perception systems for forklifts and Automated Guided Vehicles (AGVs). This work presents a vision based framework for pallet and pallet hole detection and mapping using a single standard camera. We utilized YOLOv8 and YOLOv11 architectures, enhanced through Optuna driv

Wenjie Hu, Sidun Liu, Peng Qiao, Zhenglun Sun

Recent advances in Transformer-based Neural Operators have enabled significant progress in data-driven solvers for Partial Differential Equations (PDEs). Most current research has focused on reducing the quadratic complexity of attention to address the resulting low training and inference efficiency. Among these works, Transolver stands out as a representati

Xuwei Tan, Yuanlong Wang, Thai-Hoang Pham, Ping Zhang

As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a trade-off between fairness and accuracy, inadvertently degrading performance for certain demographic groups. In high-stakes d

Yaoning Yu, Kai-Min Chang, Ye Yu, Kai Wei

Financial documents like earning reports or balance sheets often involve long tables and multi-page reports. Large language models have become a new tool to help numerical reasoning and understanding these documents. However, prompt quality can have a major effect on how well LLMs perform these financial reasoning tasks. Most current methods tune prompts on

O. A. Chuikin, Ya. S. Greenberg, O. V. Kibis

We study the dynamical and spectral characteristics of a quantum three-level ladder system, interacting with a continuous electromagnetic field in one-dimensional open waveguide. Common realization of such systems is a waveguide QED setup - a superconducting artificial atom (transmon), coupled to an open microwave transmission line. We derive an analytical s

Luyao Zhong, Xin Jin, Mingquan He, Rui Wang

The Wiedemann-Franz (WF) law, relating the electronic thermal conductivity ($\kappa_{\rm e}$) to the electrical conductivity, is vital in numerous applications such as in the design of thermoelectric materials and in the experimental determination of the lattice thermal conductivity ($\kappa_{\rm L}$). While the WF law is generally robust, violations are fre

Chao Liu, Yiqing Shi

This work extends the previous work by the first author [arXiv:2409.02516] and [Math. Ann. 393 (2025), 317-363], analyzing the long-term behavior of solutions to a broader class of quasilinear wave equations with parameter $1<\mathsf{a}\leq30$ and $\frac{1}{3}\leq\mathsf{b}\leq\frac{2}{3}$: \begin{equation*} \partial^2_t \varrho- \biggl( \frac{ \mathsf{m}^2

Wenxuan Wu, Shuai Wang, Xixin Wu, Helen Meng

Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of conversation, to extract target speech. Inspired by this observation, we propose ELEGANCE, a novel framework that incorpor

V. I. Yukalov, E. P. Yukalova

It is well known that the mathematically accurate description of ordering and related symmetry breaking in statistical systems requires to consider the thermodynamic limit. But the order does not appear from nowhere, and yet before the thermodynamic limit is reached, there should exist some kind of preordering that appears and grows in the process of increas

Jing-Wen Gao, Yunan He, Jian Liu

Topological data analysis (TDA), as a relatively recent approach, has demonstrated great potential in capturing the intrinsic and robust structural features of complex data. While persistent homology, as a core tool of TDA, focuses on characterizing geometric shapes and topological structures, the automorphism groups of Vietoris-Rips complexes can capture th

Peng He, Yao Liu, Yanglei Gan, Run Lin

Sequential recommendation (SR) aims to predict a user's next item preference by modeling historical interaction sequences. Recent advances often integrate frequency-domain modules to compensate for self-attention's low-pass nature by restoring the high-frequency signals critical for personalized recommendations. Nevertheless, existing frequency-aware solutio

Bing Wang, Ximing Li, Yanjun Wang, Changchun Li

Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of t

Xuanle Zhao, Shuxin Zeng, Xinyuan Cai, Xiang Cheng

While Vision Language Models (VLMs) have demonstrated remarkable capabilities in general visual understanding, their application in the chemical domain has been limited, with previous works predominantly focusing on text and thus overlooking critical visual information, such as molecular structures. Current approaches that directly adopt standard VLMs for ch

Zefeng He, Xiaoye Qu, Yafu Li, Siyuan Huang

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing video datasets, while the manual annotation of new, high-quality data remains prohibitively expensive. This work investi

Fei Li, Xiao-Wei Li

Counterdiabatic (CD) driving is a powerful technique for accelerating adiabatic quantum computing. However, it becomes self-limiting in complex optimizations like the Sherrington-Kirkpatrick model: long evolution times $T$ needed to traverse crossings force the CD strength to scale as $1/T$, causing it to vanish before convergence and wasting the quantum res

Jan Eliáš, Gianluca Cusatis

This article answers the question of whether homogenization of discrete fine-scale mechanical models, such as particle or lattice models, gives rise to an equivalent continuum that is of Cauchy-type or Cosserat-type. The study employs the machinery of asymptotic expansion homogenization to analyze discrete mechanical models with rotational degrees of freedom

Dragos-Patru Covei

This paper establishes the existence, uniqueness, and global $C^{1,\beta}$ regularity of positive classical solutions to a class of quasilinear Hamilton--Jacobi--Bellman (HJB) equations with Dirichlet boundary conditions on bounded convex domains. The core technical contribution is a constructive existence proof based on a weighted linear monotone iteration

Fernando Rodriguez Avellaneda, Paula Moraga

Accurate estimation of Aerosol Optical Depth (AOD) is crucial for understanding climate change and its impacts on public health, as aerosols are a measure of air quality conditions. AOD is usually retrieved from satellite imagery at coarse spatial and temporal resolutions. However, producing high-resolution AOD estimates in both space and time can better sup

Max Pettini, Ryan Cooke

This is a transcript of the joint talk we gave at the Sixth Gruber Cosmology Conference at Yale University on 3 October 2025. We describe the key role played by Big Bang Nucleosynthesis (BBN) in today's `Precision Cosmology', focusing in particular on the precise determination of the primordial abundance of deuterium. We describe the development of the ideas

David Ellerman

The usual formulas for the fair market valuation of a firm at time $t$ include the profits accruing to the shares at time $t$ from the use of wage or salaried labor in the future. But in employee-owned firms or partnerships, the future worker-members or partners are the residual claimants at those future times, so in those cases, the future residuals do not

Boyan Tang, Yilong Zeng, Xuanhao Ren, Peng Xiao

Accurate prediction of financial and electricity markets, especially under extreme conditions, remains a significant challenge due to their intrinsic nonlinearity, rapid fluctuations, and chaotic patterns. To address these limitations, we propose the Chaotic Oscillatory Transformer Network (COTN). COTN innovatively combines a Transformer architecture with a

Zijie Wang, Weiming Zhang, Wei Zhang, Xiao Tan

Centerline graphs, crucial for path planning in autonomous driving, are traditionally learned using deterministic methods. However, these methods often lack spatial reasoning and struggle with occluded or invisible centerlines. Generative approaches, despite their potential, remain underexplored in this domain. We introduce LaneDiffusion, a novel generative

Ruide Fu

The stack of local Langlands parameters for a torus is a Picard stack. In this article, we explicitly determine its Picard dual and show that the Fourier-Mukai transform gives rise to the integral categorical local Langlands correspondence for the torus. This is the categorification of the local Langlands correspondence and answers a conjecture of X. Zhu. Mo

Weikang Bian, Xiaoyu Shi, Zhaoyang Huang, Jianhong Bai

Recent advances in diffusion models enable high-quality video generation and editing, but precise relighting with consistent video contents, which is critical for shaping scene atmosphere and viewer attention, remains unexplored. Mainstream text-to-video (T2V) models lack fine-grained lighting control due to text's inherent limitation in describing lighting

Abdulahi Abiodun Badrudeen, Nakyung Lee, Adam Dubs, Sunwoo Kim

This paper proposes a blocker-aware multicarrier integrated sensing and communication (ISAC)-non orthogonal multiple access (NOMA) system, leveraging hybrid beamforming and dynamic power allocation to enhance spectrum efficiency in 6G networks. Recognizing the performance degradation caused by environmental blockers, the system introduces a joint waveform de

Yuhao Zhang, Qinghong Guo, Qixian Chen, Liuwei Zhang

Drug-target interaction (DTI) prediction is of great significance for drug discovery and drug repurposing. With the accumulation of a large volume of valuable data, data-driven methods have been increasingly harnessed to predict DTIs, reducing costs across various dimensions. Therefore, this paper proposes a $\textbf{L}$arge $\textbf{L}$anguage $\textbf{M}$o

Jian Zhang, Junyi Guo, Junyi Yuan, Huanda Lu

Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is often limited by incomplete or inconsistent textual descriptions, caused by historical data loss and the high cost of expert annotation. While large language models (LLMs) offer a promising solution by enriching textual descriptions, their outputs frequently

Jiayi Chen, Wei Zhao, Liangwang Ruan, Baoquan Chen

Collision detection is a core component of robotics applications such as simulation, control, and planning. Traditional algorithms like GJK+EPA compute witness points (i.e., the closest or deepest-penetration pairs between two objects) but are inherently non-differentiable, preventing gradient flow and limiting gradient-based optimization in contact-rich tas

Yanlin Wang, Di Yuan, Shani Dettman, Dawn Choo

Cochlear implants (CI) significantly improve spoken language in children with severe-to-profound sensorineural hearing loss (SNHL), yet outcomes remain more variable than in children with normal hearing. This variability cannot be reliably predicted for individual children using age at implantation or residual hearing. This study aims to compare the accuracy

Ardhendu Sekhar, Vasu Soni, Keshav Aske, Shivam Madnoorkar

Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational pathology framework that addresses these limitations through four complementary innovations: (1) Quantile-Gated Patch Sel

Mohammad Helal Uddin, Sai Krishna Ghanta, Liam Seymour, Sabur Baidya

Deep learning algorithms are becoming an essential component of many artificial intelligence (AI) driven applications, many of which run on resource-constrained and energy-constrained systems. For efficient deployment of these algorithms, although different techniques for the compression of neural network models are proposed, neural pruning is one of the fas

G. Catanzaro, A. Bhardwaj, V. Ripepi, E. Trentin

Context. While most chemical abundance studies of Cepheids rely on optical spectroscopy, near-infrared (NIR) observations offer advantages in terms of reduced extinction and access to new elemental tracers. Aims. We aim to validate NIR-based abundance determinations against optical results and to explore the diagnostic power of spectral lines inaccessible in

Siming Zhao, Qi Li

Organizations are increasingly exploring delegation of screening and negotiation tasks to AI systems, yet deployment in high-stakes B2B settings is constrained by governance: preventing unauthorized commitments, ensuring sufficient information before bargaining, and maintaining effective human oversight and auditability. Prior work on large language model ne

B. Ghosh, H. Harikumar, S. Rana

Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Targeted Manifold Manipulation-Nearest Neighbour (TMM-NN), which reconceptualises retrieval by assessing how readily each sample can be nudged into a designated region of the feature

Hanlin Sun, Jiayang Li

Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although more flexible and generalizable than conventional models, the practical use of these approaches remains limited by scalability due to the cost of calling one LLM for every traveler. Moreover, it has been found that LL

Yiwen Zhang, Keyan Ding, Yihang Wu, Xiang Zhuang

Retrieving molecular structures from tandem mass spectra is a crucial step in rapid compound identification. Existing retrieval methods, such as traditional mass spectral library matching, suffer from limited spectral library coverage, while recent cross-modal representation learning frameworks often encounter modality misalignment, resulting in suboptimal r

Pei Wang, Changjing Zhuge

This paper studies the restriction multiplicities of half-diagram modules for the partition algebra and their geometric interpretations. By specializing the Bowman-De Visscher-Orellana formula [BVC, Theorem 4.3] for restriction multiplicities of standard modules in the partition algebra, we compute these multiplicities and provide interpretations in terms of

Ruifei Zhang, Wei Zhang, Xiao Tan, Sibei Yang

Recent advancements in language-grounded autonomous driving have been significantly promoted by the sophisticated cognition and reasoning capabilities of large language models (LLMs). However, current LLM-based approaches encounter critical challenges: (1) Failure analysis reveals that frequent collisions and obstructions, stemming from limitations in visual

Lewin B. S. Marsh, Felix I. Parra, Valerian H. Hall-Chen, Juan Ruiz Ruiz

We derive the beam tracing and profile evolution for the propagation of any localised beam with arbitrary profile through an inhomogeneous cold plasma. We recover standard Gaussian beam-tracing, with an additional PDE describing the evolution of the beam's profile as it propagates through the plasma. We then solve for generic families of solutions to the PDE

Teng Shi, Chenglei Shen, Weijie Yu, Shen Nie

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic limitations: (1) unidirectional constraints, where causal attention restricts each token to attend only to its predecessors, hinde

Ruifei Zhang, Junlin Xie, Wei Zhang, Weikai Chen

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing excessive computational overhead, or use fixed schedules, failing to adapt to dynamic driving conditions. To address thes

Xuantang Xiong, Ni Mu, Runpeng Xie, Senhao Yang

Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for single tasks and rarely address generalization across different scenarios. Building on the insight that dynamics within the sa

Mingde Xu, Zhen Yang, Wenyi Hong, Lihang Pan

User interface (UI) development requires translating design mockups into functional code, a process that remains repetitive and labor-intensive. While recent Vision-Language Models (VLMs) automate UI-to-Code generation, they generate only static HTML/CSS/JavaScript layouts lacking interactivity. To address this, we propose WebVIA, the first agentic framework

Yunshan Zhong, Weiqi Yan, Yuxin Zhang

With the growing demand for high-quality image generation on resource-constrained devices, efficient diffusion models have received increasing attention. However, such models suffer from approximation errors introduced by efficiency techniques, which significantly degrade generation quality. Once deployed, these errors are difficult to correct, as modifying

Miao Li, Michael Klamkin, Pascal Van Hentenryck, Wenting Li

This paper studies optimization proxies, machine learning (ML) models trained to efficiently predict optimal solutions for AC Optimal Power Flow (ACOPF) problems. While promising, optimization proxy performance heavily depends on training data quality. To address this limitation, this paper introduces a novel active sampling framework for ACOPF optimization

Cong Li, Yuzhe Yang, Xuegui Zheng, Qifan Yang

With the advancement of large language models (LLMs), their context windows have rapidly expanded. To meet diverse demands from varying-length requests in online services, existing state-of-the-art systems tune the sequence parallelism (SP) allocation. However, current dynamic SP allocation lacks flexibility to (1) support stage-specific parallelism requirem