Tootfinder

Causal Representation Learning with Observational Grouping for CXR Classification
Rajat Rasal, Avinash Kori, Ben Glocker
https://arxiv.org/abs/2506.20582 h…

Causal Representation Learning with Observational Grouping for CXR Classification
Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve gen…

S2Sent: Nested Selectivity Aware Sentence Representation Learning
Jianxiang Zang, Nijia Mo, Yonda Wei, Meiling Ning, Hui Liu
https://arxiv.org/abs/2508.18164 https://

S2Sent: Nested Selectivity Aware Sentence Representation Learning
The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of the encoder. However, within Transformer-based encoders, different blocks exhibit varying degrees of semantic perception ability. From the perspective of interpretability, the semantic perception potential of knowledge neurons is modulated by stimuli, thus ra…

Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programming
Jiajun Li, Ran Hou, Yu Ding, Yixuan Li, Shisi Guan, Jiahui Duan, Xiongwei Han, Tao Zhong, Vincent Chau, Weiwei Wu, Wanyuan Wang
https://arxiv.org/abs/2508.18742

Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programming
Model reduction, which aims to learn a simpler model of the original mixed integer linear programming (MILP), can solve large-scale MILP problems much faster. Most existing model reduction methods are based on variable reduction, which predicts a solution value for a subset of variables. From a dual perspective, constraint reduction that transforms a subset of inequality constraints into equalities can also reduce the complexity of MILP, but has been largely ignored. Therefore, this paper propo…

The block decomposition of the principal representation category of reductive algebraic groups with Frobenius maps
Xiaoyu Chen, Junbin Dong
https://arxiv.org/abs/2506.20378

The block decomposition of the principal representation category of reductive algebraic groups with Frobenius maps
Let ${\bf G}$ be a connected reductive algebraic group defined over the finite field $\mathbb{F}_q$ with $q$ elements. Let $\Bbbk$ be a field such that $\op{char} \Bbbk \ne \op{char} \mathbb{F}_q$. In this paper, we study the extensions of simple modules (over $\Bbbk$) in the principal representation category $\mathscr{O}(\bf G)$ which is defined in \cite{D1}. In particular, we get the block decomposition of $\mathscr{O}(\bf G)$, which is parameterized by the central characters of ${\bf G}$.

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
Kyra Wilson, Sourojit Ghosh, Aylin Caliskan
https://arxiv.org/abs/2508.17465

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
Text-to-image generators (T2Is) are liable to produce images that perpetuate social stereotypes, especially in regards to race or skin tone. We use a comprehensive set of 93 stigmatized identities to determine that three versions of Stable Diffusion (v1.5, v2.1, and XL) systematically associate stigmatized identities with certain skin tones in generated images. We find that SD XL produces skin tones that are 13.53% darker and 23.76% less red (both of which indicate higher likelihood of societal…

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
Shaoxiong Zhan, Hai Lin, Hongming Tan, Xiaodong Cai, Hai-Tao Zheng, Xin Su, Zifei Shan, Ruitong Liu, Hong-Gee Kim
https://arxiv.org/abs/2508.17858

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
As queries in retrieval-augmented generation (RAG) pipelines powered by large language models (LLMs) become increasingly complex and diverse, dense retrieval models have demonstrated strong performance in semantic matching. Nevertheless, they often struggle with fine-grained retrieval tasks, where precise keyword alignment and span-level localization are required, even in cases with high lexical overlap that would intuitively suggest easier retrieval. To systematically evaluate this limitation,…

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Chuxin Wang, Yixin Zha, Wenfei Yang, Tianzhu Zhang
https://arxiv.org/abs/2506.21541

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods still face two key issues that limit the potential of SSM: Destroying the adjacency of 3D points during SSM processing and failing to retain long-sequence memory as the input length increases in downstream tasks. To address these issues, we propose StruMamba3D,…

Condensed Representation of RDF and its Application on Graph Versioning
Jey Puget Gil, Emmanuel Coquery, John Samuel, Gilles Gesquiere
https://arxiv.org/abs/2506.21203

Condensed Representation of RDF and its Application on Graph Versioning
The study of the evolving phenomena in a domain helps to understand the relationships between entities at different points in time and predict future trends. These phenomena, often complex, can be represented using knowledge graphs, which have the capability to model heterogeneous data from multiple sources. Nowadays, a considerable amount of sources delivering periodic updates to knowledge graphs in various domains is openly available. The evolution of data is of interest to knowledge graph ma…

The monodromy representation of a hypergeometric system in $m$ variables of rank $p^m$
Jyoichi Kaneko, Keiji Matsumoto, Katsuyoshi Ohara, Tomohide Terasoma
https://arxiv.org/abs/2508.18769

The monodromy representation of a hypergeometric system in $m$ variables of rank $p^m$
We study the monodromy representation of the hypergeometric system $\mathcal{F}_{C}^{p,m}(a,B)$ in $m$ variables of rank $p^m$ with parameters $a$ and $B$. This system can be regarded as a multi-variable model of the generalized hypergeometric equation of rank $p$. We construct $m+1$ loops which generate the fundamental group of the complement of the singular locus of $\mathcal{F}_{C}^{p,m}(a,B)$, and we show that they satisfy certain relations as elements of the fundamental group. We produce c…

Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
Xinke Ma, Yongsheng Pan, Qingjie Zeng, Mengkang Lu, Bolysbek Murat Yerzhanuly, Bazargul Matkerim, Yong Xia
https://arxiv.org/abs/2506.19222

Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
Effective representation of Regions of Interest (ROI) and independent alignment of these ROIs can significantly enhance the performance of deformable medical image registration (DMIR). However, current learning-based DMIR methods have limitations. Unsupervised techniques disregard ROI representation and proceed directly with aligning pairs of images, while weakly-supervised methods heavily depend on label constraints to facilitate registration. To address these issues, we introduce a novel ROI-…

Wild Galois representations: elliptic curves with wild cyclic reduction
Nirvana Coppola
https://arxiv.org/abs/2506.20562 https://arxi…

Wild Galois representations: elliptic curves with wild cyclic reduction
In 1990, Kraus classified all possible inertia images of the $\ell$-adic Galois representation attached to an elliptic curve over a non-archimedean local field. In previous work, the author computed explicitly the Galois representation of elliptic curves having non-abelian inertia image, a phenomenon which only occurs when the residue characteristic of the field of definition is $2$ or $3$ and the curve attains good reduction over some non-abelian ramified extension. In this work, the computati…

Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform
Maxime Leiber, Yosra Marnissi, Axel Barrau, Sylvain Meignen, Laurent Massouli\'e
https://arxiv.org/abs/2506.21440

Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform
The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this limitation, we propose a unified differentiable formulation of the STFT that enables gradient-based optimization of its parameters. This approach addresses the limitations of traditional STFT parameter tuning methods, which often rely on computationally intensi…

Laboratory Frame Representation for General High-Frequency Gravitational Waveforms
Lars Fischer, Tom Krokotsch, Gudrid Moortgat-Pick
https://arxiv.org/abs/2506.20198

Laboratory Frame Representation for General High-Frequency Gravitational Waveforms
Next-generation gravitational wave (GW) experiments will explore higher frequency ranges, where GW wavelengths approach the size of the detector itself. In this regime, GWs may be detected not just through the well-known mechanical deformation by tidal forces but also via induced effective currents in electromagnetic background fields. However, the calculation of this signal requires the GW metric in laboratory coordinates of the detector, and an accurate transformation to all orders into this …

Reduction of Feynman Integrals in the Parametric Representation IV: Integrals with Irregular Integration Regions
Wen Chen
https://arxiv.org/abs/2508.18419 https://

Reduction of Feynman Integrals in the Parametric Representation IV: Integrals with Irregular Integration Regions
Parametric Feynman integrals with the regions of integration defined by some polynomials are considered in this paper. It is shown that integrals with irregular integration regions can be converted to standard parametric integrals, for which a reduction method is known. An application of this method to the analytic calculation of three-point energy correlators is presented. In principle, this method applies to more general event shapes and even jet observables.

from my link log —
Representing type lattices compactly.
https://bernsteinbear.com/blog/lattice-bitset/
saved 2025-03-12 https://…

DiT-SGCR: Directed Temporal Structural Representation with Global-Cluster Awareness for Ethereum Malicious Account Detection
Ye Tian, Liangliang Song, Peng Qian, Yanbin Wang, Jianguo Sun, Yifan Jia
https://arxiv.org/abs/2506.20123

DiT-SGCR: Directed Temporal Structural Representation with Global-Cluster Awareness for Ethereum Malicious Account Detection
The detection of malicious accounts on Ethereum - the preeminent DeFi platform - is critical for protecting digital assets and maintaining trust in decentralized finance. Recent advances highlight that temporal transaction evolution reveals more attack signatures than static graphs. However, current methods either fail to model continuous transaction dynamics or incur high computational costs that limit scalability to large-scale transaction networks. Furthermore, current methods fail to consid…

Symbolic dynamics, shadowing and representation of real numbers with some countably piecewise linear Markov maps
Zolt\'an Kalocsai
https://arxiv.org/abs/2508.17159 https://

Symbolic dynamics, shadowing and representation of real numbers with some countably piecewise linear Markov maps
We study piecewise linear Markov maps, with countable Markov partitions, inspired by a problem of the Miklós Schweitzer competition of the János Bolyai Mathematical Society in 2022. We introduce $\ell$-Markov partitions and apply ideas of symbolic dynamics to our systems, relating them to Markov shifts. We prove the shadowing property for the system from the competition. We also investigate the possible orbits of rational numbers, for a class of piecewise linear Markov maps which generalize o…

Differential contributions of low-frequency phase and power in crossmodal temporal prediction: A MEG study https://www.biorxiv.org/content/10.1101/2025.05.26.656128v1 on "tactile-to-visual influences on temporal prediction", "broad applicability of …

Differential contributions of low-frequency phase and power in crossmodal temporal prediction: A MEG study
Introduction Our representation of time is embedded within multisensory perception, based on sight, sound, or touch. However, despite being a crucial aspect of daily life, the neural dynamics of cross-modal temporal predictions remain elusive. The objective of this study was to investigate neural correlates of tactile-to-visual influences on temporal prediction using magnetoencephalography (MEG). We hypothesized to observe increased inter-trial phase consistency (ITPC) in the low-frequency delt…

Achieving Gender Representation in Lead-Author Publications in the ASTRO3D Centre of Excellence
Kim-Vy H. Tran, Stuart Wyithe, Michelle Ding
https://arxiv.org/abs/2506.20676

Achieving Gender Representation in Lead-Author Publications in the ASTRO3D Centre of Excellence
We examine the publication rates of 400 research-focused members in the ASTRO3D Centre of Excellence by gender, project, and year from January 2018 to January 2024 (six years). Of the 443 refereed publications led by ASTRO3D members, women were first-author on 38% which is nearly double that of the astronomy field in the same period (~20%). We record a high-water mark in 2022: 46% of ASTRO3D publications were led by females and 45% of research members identified as female. Using the nine resear…

Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
Yanwen Wang, Xinglin Zhao, Yijin Song, Xiaobo Liu, Yanrong Hao, Rui Cao, Xin Wen
https://arxiv.org/abs/2508.16597

Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
Functional connectivity (FC) derived from resting-state fMRI plays a critical role in personalized predictions such as age and cognitive performance. However, applying foundation models(FM) to fMRI data remains challenging due to its high dimensionality, computational complexity, and the difficulty in capturing complex spatiotemporal dynamics and indirect region-of-interest (ROI) interactions. To address these limitations, we propose a modular neuroimaging framework that integrates principles f…

MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition
Hyo Jin Jon, Longbin Jin, Hyuntaek Jung, Hyunseo Kim, Donghun Min, Eun Yi Kim
https://arxiv.org/abs/2506.19887

MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition
This paper presents our contributions to the Speech Emotion Recognition in Naturalistic Conditions (SERNC) Challenge, where we address categorical emotion recognition and emotional attribute prediction. To handle the complexities of natural speech, including intra- and inter-subject variability, we propose Multi-level Acoustic-Textual Emotion Representation (MATER), a novel hierarchical framework that integrates acoustic and textual features at the word, utterance, and embedding levels. By fusi…

More reliable character consistency
Factual representation with fine details
https://developers.googleblog.com/en/introducing-gemini-2-5-flash-image/

Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
Domenico De Cristofaro, Vincenzo Norman Vitale, Alessandro Vietti
https://arxiv.org/abs/2508.17914

Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
Automatic Speech Recognition has advanced with self-supervised learning, enabling feature extraction directly from raw audio. In Wav2Vec, a CNN first transforms audio into feature vectors before the transformer processes them. This study examines CNN-extracted information for monophthong vowels using the TIMIT corpus. We compare MFCCs, MFCCs with formants, and CNN activations by training SVM classifiers for front-back vowel identification, assessing their classification accuracy to evaluate pho…

Series representation in tensor products of Banach spaces
Jochen Wengenroth
https://arxiv.org/abs/2506.21344 https://arxiv.org/pdf/25…

Series representation in tensor products of Banach spaces
We show by a ridiculously simple argument that, for any norm on the tensor product of vector spaces, every element of the completion can be represented as a convergent series of elementary tensors.

Scalable implementations of mean-field and correlation methods based on Lie-algebraic similarity transformation of spin Hamiltonians in the Jordan-Wigner representation
Shadan Ghassemi Tabrizi, Thomas M. Henderson, Thomas D. K\"uhne, Gustavo E. Scuseria
https://arxiv.org/abs/2508.17498

Scalable implementations of mean-field and correlation methods based on Lie-algebraic similarity transformation of spin Hamiltonians in the Jordan-Wigner representation
Recent work has highlighted that the strong correlation inherent in spin Hamiltonians can be effectively reduced by mapping spins to fermions via the Jordan-Wigner transformation (JW). The Hartree-Fock method is straightforward in the fermionic domain and may provide a reasonable approximation to the ground state. Correlation with respect to the fermionic mean-field can be recovered based on Lie-algebraic similarity transformation (LAST) with two-body correlators. Specifically, a unitary LAST v…

On the representation number of grid graphs and cylindric grid graphs
Nawaf Shafi Alshammari, Sergey Kitaev, Artem Pyatkin
https://arxiv.org/abs/2507.16469

On the representation number of grid graphs and cylindric grid graphs
The representation number of a graph is the minimum number of copies of each vertex required to represent the graph as a word, such that the letters corresponding to vertices $x$ and $y$ alternate if and only if $xy$ is an edge in the graph. It is known that path graphs, circle graphs, and ladder graphs have representation number 2, while prism graphs have representation number 3. In this paper, we extend these results by showing that generalizations of the aforementioned graphs -- namely, th…

3DGH: 3D Head Generation with Composable Hair and Face
Chengan He, Junxuan Li, Tobias Kirschstein, Artem Sevastopolsky, Shunsuke Saito, Qingyang Tan, Javier Romero, Chen Cao, Holly Rushmeier, Giljoo Nam
https://arxiv.org/abs/2506.20875

3DGH: 3D Head Generation with Composable Hair and Face
We present 3DGH, an unconditional generative model for 3D human heads with composable hair and face components. Unlike previous work that entangles the modeling of hair and face, we propose to separate them using a novel data representation with template-based 3D Gaussian Splatting, in which deformable hair geometry is introduced to capture the geometric variations across different hairstyles. Based on this data representation, we design a 3D GAN-based architecture with dual generators and empl…

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
Hao Li, Lijun Li, Zhenghao Lu, Xianyi Wei, Rui Li, Jing Shao, Lei Sha
https://arxiv.org/abs/2507.18631

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever. However, recent studies have highlighted a critical challenge: even when fine-tuning with seemingly benign downstream datasets, the safety of aligned LLMs can be compromised, making them more susceptible to malicious instructions. In this paper, we show that fi…

A Nodal Discontinuous Galerkin Method with Low-Rank Velocity Space Representation for the Multi-Scale BGK Model
Andres Galindo-Olarte, Joseph Nakao, Mirjeta Pasha, Jing-Mei Qiu, William Taitano
https://arxiv.org/abs/2508.16564

A Nodal Discontinuous Galerkin Method with Low-Rank Velocity Space Representation for the Multi-Scale BGK Model
A novel hybrid algorithm is presented for the Boltzmann-BGK equation, in which a low-rank decomposition is applied solely in the velocity subspace, while a full-rank representation is maintained in the physical (position) space. This approach establishes a foundation for extending modern low-rank techniques to solve the Boltzmann equation in realistic settings, particularly where structured representations -- such as conformal geometries -- may not be feasible in practical engineering applicati…

T-ILR: a Neurosymbolic Integration for LTLf
Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Chiara Ghidini, Marco Montali, Massimiliano Ronzani
https://arxiv.org/abs/2508.15943

T-ILR: a Neurosymbolic Integration for LTLf
State-of-the-art approaches for integrating symbolic knowledge with deep learning architectures have demonstrated promising results in static domains. However, methods to handle temporal logic specifications remain underexplored. The only existing approach relies on an explicit representation of a finite-state automaton corresponding to the temporal specification. Instead, we aim at proposing a neurosymbolic framework designed to incorporate temporal logic specifications, expressed in Linear Te…

Robust Committee Voting, or The Other Side of Representation
Gregory Kehne, Ulrike Schmidt-Kraepelin, Krzysztof Sornat
https://arxiv.org/abs/2506.18643 htt…

Robust Committee Voting, or The Other Side of Representation
We study approval-based committee voting from a novel perspective. While extant work largely centers around proportional representation of the voters, we shift our focus to the candidates while preserving proportionality. Intuitively, candidates supported by similar voter groups should receive comparable representation. Since deterministic voting rules cannot achieve this ideal, we develop randomized voting rules that satisfy ex-ante neutrality, monotonicity, and continuity, while maintaining s…

CURL-SLAM: Continuous and Compact LiDAR Mapping
Kaicheng Zhang, Shida Xu, Yining Ding, Xianwen Kong, Sen Wang
https://arxiv.org/abs/2506.21077 https://

CURL-SLAM: Continuous and Compact LiDAR Mapping
This paper studies 3D LiDAR mapping with a focus on developing an updatable and localizable map representation that enables continuity, compactness and consistency in 3D maps. Traditional LiDAR Simultaneous Localization and Mapping (SLAM) systems often rely on 3D point cloud maps, which typically require extensive storage to preserve structural details in large-scale environments. In this paper, we propose a novel paradigm for LiDAR SLAM by leveraging the Continuous and Ultra-compact Representa…

The spectrum of global representations for families of bounded rank and VI-modules
Miguel Barrero, Tobias Barthel, Luca Pol, Neil Strickland, Jordan Williamson
https://arxiv.org/abs/2506.21525

The spectrum of global representations for families of bounded rank and VI-modules
A global representation is a compatible collection of representations of the outer automorphism groups of the finite groups belonging to a family $\mathscr{U}$. These arise in classical representation theory, in the study of representation stability, as well as in global homotopy theory. In this paper we begin a systematic study of the derived category $\mathsf{D}(\mathscr{U};k)$ of global representations over fields $k$ of characteristic zero, from the point-of-view of tensor-triangular geomet…

Resonating Kagome Dimer coverings in Rydberg atom arrays
Xicheng Wang, Erich J Mueller
https://arxiv.org/abs/2506.21255 https://arxiv…

Resonating Kagome Dimer coverings in Rydberg atom arrays
Motivated by experiments on Rydberg atom arrays, we explore the properties of uniform quantum superpositions of kagome dimer configurations and construct an efficient algorithm for experimentally producing them. We begin by considering the thin cylinder limit, where these states have simple descriptions. We then develop a matrix product representation of the states on arbitrary cylinders, which leads to a natural protocol to efficiently grow them. We explain how our approach can be adapted to o…

Hyperspherical Variational Autoencoders Using Efficient Spherical Cauchy Distribution
Lukas Sablica, Kurt Hornik
https://arxiv.org/abs/2506.21278 https://

Hyperspherical Variational Autoencoders Using Efficient Spherical Cauchy Distribution
We propose a novel variational autoencoder (VAE) architecture that employs a spherical Cauchy (spCauchy) latent distribution. Unlike traditional Gaussian latent spaces or the widely used von Mises-Fisher (vMF) distribution, spCauchy provides a more natural hyperspherical representation of latent variables, better capturing directional data while maintaining flexibility. Its heavy-tailed nature prevents over-regularization, ensuring efficient latent space utilization while offering a more expres…

Ranked choice voting (RCV)
is an increasingly popular electoral institution that has been posited by reformers and media outlets to produce transformative effects on electoral outcomes and representation.
This article finds no empirical support for the proposition that RCV changed fiscal outcomes or the ideological composition of city councils
— both on absolute terms and relative to mass opinion.
Furthermore, the roll-call based ideal points of legislators serving …

Generating Reliable Adverse event Profiles for Health through Automated Integrated Data (GRAPH-AID): A Semi-Automated Ontology Building Approach
Srikar Reddy Gadusu, Larry Callahan, Samir Lababidi, Arunasri Nishtala, Sophia Healey, Hande McGinty
https://arxiv.org/abs/2506.20851

Generating Reliable Adverse event Profiles for Health through Automated Integrated Data (GRAPH-AID): A Semi-Automated Ontology Building Approach
As data and knowledge expand rapidly, adopting systematic methodologies for ontology generation has become crucial. With the daily increases in data volumes and frequent content changes, the demand for databases to store and retrieve information for the creation of knowledge graphs has become increasingly urgent. The previously established Knowledge Acquisition and Representation Methodology (KNARM) outlines a systematic approach to address these challenges and create knowledge graphs. However,…

Jeremy Corbyn -working hard to ensure a victory for Farage, It is no use being right if you have no power to do anything about it.
We need, very urgently, some form of proportional representation, because it's fairer, and because it might be the only way to avoid a fascist government.

Replaced article(s) found for math.LO. https://arxiv.org/list/math.LO/new
[1/1]:
- Multi-representation associated to the numbering of a subbasis and formal inclusion relations
Emmanuel Rauzy

Nonabelian ferromagnets with three-body interactions
Alexios P. Polychronakos, Konstantinos Sfetsos
https://arxiv.org/abs/2506.19916 https://

Nonabelian ferromagnets with three-body interactions
We study the thermodynamics of nonabelian ferromagnets consisting of atoms in the fundamental representation of $SU(N)$ and interacting with two-body and three-body interactions. An intricate phase structure emerges, depending on the relative strength and sign of the two-body and three-body coupling constants. In the case where two-body interactions are ferromagnetic and three-body ones are antiferromagnetic, we uncover a rich cascade of phase transitions, the appearance of phases with two dist…

Massey products and the Iwasawa theory of fine Selmer groups
Anwesh Ray, R. Sujatha
https://arxiv.org/abs/2508.17156 https://arxiv.org/pdf/2508.17156

Massey products and the Iwasawa theory of fine Selmer groups
A central conjecture of Coates and Sujatha predicts that the fine Selmer group of any $p$-adic Galois representation is cotorsion over the relevant Iwasawa algebra with vanishing $μ$-invariant, generalizing Iwasawa's original conjecture for class groups. In this article, we recast this conjecture in terms of higher Galois cohomological operations called Massey products, stated purely in terms of the residual representation. This characterization implies that if the $μ$-invariant vanishes for …

Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
Hani Alomari, Anushka Sivakumar, Andrew Zhang, Chris Thomas
https://arxiv.org/abs/2506.21538

Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle to capture nuanced and diverse relationships that can exist across modalities. Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative, as they can capture richer and more diverse relationships. In this paper,…

The Pythagoras number of fields of transcendence degree $1$ over $\mathbb{Q}$
Olivier Benoist
https://arxiv.org/abs/2506.21380 https://

The Pythagoras number of fields of transcendence degree $1$ over $\mathbb{Q}$
We show that any sum of squares in a field of transcendence degree $1$ over $\mathbb{Q}$ is a sum of $5$ squares, answering a question of Pop and Pfister. We deduce this result from a representation theorem, in $k(C)$, for quadratic forms of rank $\geq 5$ with coefficients in $k$, where $C$ is a curve over a number field $k$.

An isovariant Blakers--Massey theorem
Inbar Klang, Sarah Yeakel
https://arxiv.org/abs/2506.21259 https://arxiv.org/pdf/2506.21259

An isovariant Blakers--Massey theorem
An isovariant map is an equivariant map between $G$-spaces which strictly preserves isotropy groups. In this paper, we lay the groundwork for the study of isovariant stable homotopy theory. We prove an isovariant Blakers--Massey theorem and its $n$-cubical generalization, define a suitable notion of suspension (by a trivial representation sphere) in the isovariant category, and prove an isovariant Freudenthal suspension theorem.

The projection spectral theorem, quasi-free states and point processes
Eugene Lytvynov
https://arxiv.org/abs/2508.19147 https://arxiv.org/pdf/2508.19147

The projection spectral theorem, quasi-free states and point processes
In this review paper, we demonstrate that several classes of point processes in a locally compact Polish space $X$ appear as the joint spectral measure of a rigorously defined particle density of a representation of the canonical anticommutation relations (CAR) or the canonical commutation relations (CCR) in a Fock space. For these representations of the CAR/CCR, the vacuum state on the corresponding $*$-algebra is quasi-free. The classes of point process that arise in such a way include determ…

Succinct Preferential Attachment Graphs
Ziad Ismaili Alaoui, Namrata, Sebastian Wild
https://arxiv.org/abs/2506.21436 https://arxiv.…

Succinct Preferential Attachment Graphs
Computing over compressed data combines the space saving of data compression with efficient support for queries directly on the compressed representation. Such data structures are widely applied in text indexing and have been successfully generalised to trees. For graphs, support for computing over compressed data remains patchy; typical results in the area of succinct data structures are restricted to a specific class of graphs and use the same, worst-case amount of space for any graph from th…

Information Ecosystem Reengineering via Public Sector Knowledge Representation
Mayukh Bagchi
https://arxiv.org/abs/2508.15916 https://arxiv.org/pdf/2508.15…

Information Ecosystem Reengineering via Public Sector Knowledge Representation
Information Ecosystem Reengineering (IER) -- the technological reconditioning of information sources, services, and systems within a complex information ecosystem -- is a foundational challenge in the digital transformation of public sector services and smart governance platforms. From a semantic knowledge management perspective, IER becomes especially entangled due to the potentially infinite number of possibilities in its conceptualization, namely, as a result of manifoldness in the multi-lev…

From Partial Exchangeability to Predictive Probability: A Bayesian Perspective on Classification
Marcio Alves Diniz
https://arxiv.org/abs/2508.16716 https://

From Partial Exchangeability to Predictive Probability: A Bayesian Perspective on Classification
We propose a novel Bayesian nonparametric classification model that combines a Gaussian process prior for the latent function with a Dirichlet process prior for the link function, extending the interpretative framework of de Finetti representation theorem and the construction of random distribution functions made by Ferguson (1973). This approach allows for flexible uncertainty modeling in both the latent score and the mapping to probabilities. We demonstrate the method performance using simula…

Replaced article(s) found for math.GR. https://arxiv.org/list/math.GR/new
[1/1]:
- On Dehornoy's representation for the Yang-Baxter equation
Carsten Dietzel, Edouard Feingesicht, Silvia Properzi

Finite temperature single-particle Green's function in the Lieb-Liniger model
Riccardo Senese, Fabian H. L. Essler
https://arxiv.org/abs/2508.17908 https://

Finite temperature single-particle Green's function in the Lieb-Liniger model
We develop a Monte Carlo sampling algorithm to numerically evaluate the Lehmann representation for the finite temperature single-particle Green's function in the repulsive Lieb-Liniger model. This allows us to determine the spectral function in the full range of temperatures and interactions, as well as in generalized Gibbs ensembles. We test our results against the known limit of infinite interaction strength and find excellent agreement.

From Representation to Mediation: A New Agenda for Conceptual Modeling Research in A Digital World
J. Recker, R. Lukyanenko, M. A. Jabbari, B. M. Samuel, A. Castellanos
https://arxiv.org/abs/2506.18743

From Representation to Mediation: A New Agenda for Conceptual Modeling Research in A Digital World
The role of information systems (IS) as representations of real-world systems is changing in an increasingly digitalized world, suggesting that conceptual modeling is losing its relevance to the IS field. We argue the opposite: Conceptual modeling research is more relevant to the IS field than ever, but it requires an update with current theory. We develop a new theoretical framework of conceptual modeling that delivers a fundamental shift in the assumptions that govern research in this area. T…

Multiplexed subspaces route neural activity across brain-wide networks (in mice)  https://www.nature.com/articles/s41467-025-58698-2 but no, subspace communication is not faster-than-light, sorry Star Trek fans.

Multiplexed subspaces route neural activity across brain-wide networks - Nature Communications
How the brain flexibly engages different networks of regions to perform different cognitive processes remains unknown. Here, the authors show changing the geometry of a neural representation to align with different subspaces within a brain region can engage different brainwide networks.

Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
Yahya Badran, Christine Preisach
https://arxiv.org/abs/2508.16269 https:/…

Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
Personalized recommendation is a key feature of intelligent tutoring systems, typically relying on accurate models of student knowledge. Knowledge Tracing (KT) models enable this by estimating a student's mastery based on their historical interactions. Many KT models rely on human-annotated knowledge concepts (KCs), which tag each exercise with one or more skills or concepts believed to be necessary for solving it. However, these KCs can be incomplete, error-prone, or overly general. In this …

Head-Related Transfer Function Individualization Using Anthropometric Features and Spatially Independent Latent Representation
Ryan Niu, Shoichi Koyama, Tomohiko Nakamura
https://arxiv.org/abs/2508.16176

Head-Related Transfer Function Individualization Using Anthropometric Features and Spatially Independent Latent Representation
A method for head-related transfer function (HRTF) individualization from the subject's anthropometric parameters is proposed. Due to the high cost of measurement, the number of subjects included in many HRTF datasets is limited, and the number of those that include anthropometric parameters is even smaller. Therefore, HRTF individualization based on deep neural networks (DNNs) is a challenging task. We propose a HRTF individualization method using the latent representation of HRTF magnitude ob…

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation
Li Sun, Jiefeng Wu, Feng Chen, Ruizhe Liu, Yanchao Yang
https://arxiv.org/abs/2508.18802 …

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation
Effective policy learning for robotic manipulation requires scene representations that selectively capture task-relevant environmental features. Current approaches typically employ task-agnostic representation extraction, failing to emulate the dynamic perceptual adaptation observed in human cognition. We present HyperTASR, a hypernetwork-driven framework that modulates scene representations based on both task objectives and the execution phase. Our architecture dynamically generates representa…

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
Sizhe Shan, Qiulin Li, Yutao Cui, Miles Yang, Yuehai Wang, Qun Yang, Jin Zhou, Zhao Zhong
https://arxiv.org/abs/2508.16930

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-audio generation, including multimodal data scarcity, modality imbalance and limited audio quality in existing methods, we propose HunyuanVideo-Foley, an end-to-end text-video-to-audio framework that synthesizes high-fidelity audio precisely aligned with visual dynamics and semantic context. Our approach incorporates …

Structured Quantum Baths with Memory: A QuTiP Framework for Spectral Diagnostics and Machine Learning Inference
Ridwan Sakidja
https://arxiv.org/abs/2508.17514 https://

Structured Quantum Baths with Memory: A QuTiP Framework for Spectral Diagnostics and Machine Learning Inference
We introduce a compact simulation framework for modeling open quantum systems coupled to structured, memory-retaining baths using QuTiP. Our method models the bath as a finite set of layered qubits with adjustable connections, interpreted either as a physical realization or as a conceptual representation, rather than as a continuum. This explicit modeling enables direct control over non-Markovian dynamics and allows spectral diagnostics via Fast Fourier Transform (FFT) of system observables. Us…

Additive systems for $\mathbb{Z}$ are undecidable
Andrei Zabolotskii
https://arxiv.org/abs/2508.17285 https://arxiv.org/pdf/2508.17285

Additive systems for $\mathbb{Z}$ are undecidable
What are the collections of sets ${A}_i\subset\mathbb{Z}$ such that any $n\in\mathbb{Z}$ has exactly one representation as $n=a_0+a_1+\dotsb$ with $a_i\in{A}_i$? The answer for $\mathbb{N}_0$ instead of $\mathbb{Z}$ is given by a theorem of de Bruijn. We describe a family of natural candidate collections for $\mathbb{Z}$, which we call canonical collections. Translating the problem into the language of dynamical systems, we show that the question of whether the sumset of a canonical collection …

Structure-Preserving Medical Image Generation from a Latent Graph Representation
Kevin Arias, Edwin Vargas, Kumar Vijay Mishra, Antonio Ortega, Henry Arguello
https://arxiv.org/abs/2508.15920

Structure-Preserving Medical Image Generation from a Latent Graph Representation
Supervised learning techniques have proven their efficacy in many applications with abundant data. However, applying these methods to medical imaging is challenging due to the scarcity of data, given the high acquisition costs and intricate data characteristics of those images, thereby limiting the full potential of deep neural networks. To address the lack of data, augmentation techniques leverage geometry, color, and the synthesis ability of generative models (GMs). Despite previous efforts, …

EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
Xiaoxiong Zhang, Xin Zhou, Zhiwei Zeng, Yongjie Wang, Dusit Niyato, Zhiqi Shen
https://arxiv.org/abs/2508.16170

EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
MultiModal Recommendation (MMR) systems have emerged as a promising solution for improving recommendation quality by leveraging rich item-side modality information, prompting a surge of diverse methods. Despite these advances, existing methods still face two critical limitations. First, they use raw modality features to construct item-item links for enriching the behavior graph, while giving limited attention to balancing collaborative and modality-aware semantics or mitigating modality noise i…

Proportional Representation in Rank Aggregation
Patrick Lederer
https://arxiv.org/abs/2508.16177 https://arxiv.org/pdf/2508.16177

Proportional Representation in Rank Aggregation
In rank aggregation, the task is to aggregate multiple weighted input rankings into a single output ranking. While numerous methods, so-called social welfare functions (SWFs), have been suggested for this problem, all of the classical SWFs tend to be majoritarian and are thus not acceptable when a proportional ranking is required. Motivated by this observation, we will design SWFs that guarantee that every input ranking is proportionally represented by the output ranking. Specifically, our cent…

Nonlinear Gravitational Memory in the Post-Minkowskian Expansion
Alessandro Georgoudis, Vasco Goncalves, Carlo Heissenberg, Julio Parra-Martinez
https://arxiv.org/abs/2506.20733

Nonlinear Gravitational Memory in the Post-Minkowskian Expansion
We present the first computation of the nonlinear gravitational memory waveform for the scattering of two compact objects in General Relativity at leading order in the post-Minkowskian expansion. We use the scattering-amplitudes-based representation of the gravitational waveform, which naturally expresses the nonlinear memory as the contribution of soft gravitons emitted by the gravitational waves themselves. We perform the calculation by applying a multipolar decomposition to the waveform and …

Crosslisted article(s) found for math-ph. https://arxiv.org/list/math-ph/new
[1/1]:
- On regularizations of the integral representation of Dirac delta function -- elementary approach
Grzegorz M. Koczan, Piotr Stachura

A Flavor of SO(10) Unification with a Spinor Higgs
Juanca Carrasco-Martinez, Lawrence J. Hall, Keisuke Harigaya, Kevin Langhoff
https://arxiv.org/abs/2506.20708

A Flavor of SO(10) Unification with a Spinor Higgs
We investigate Higgs Parity Unification-a realization of $SO(10)$ grand unification based on the Higgs Parity mechanism in which the Standard Model (SM) Higgs resides in a spinor representation. The theory has an intermediate left-right symmetric stage where the $SU(2)_R$ symmetry breaking scale is fixed by the vanishing of the SM Higgs quartic coupling. The strong $CP$ problem is solved by parity. Gauge coupling unification successfully predicts $α_s(M_Z)$ to within 1%. The spinor Higgs natur…

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
Ming Yang, Dongrun Li, Xin Wang, Xiaoyang Yu, Xiaoming Wu, Shibo He
https://arxiv.org/abs/2508.17954

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To addre…

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Angelos-Nikolaos Kanatas, Charilaos Papaioannou, Alexandros Potamianos
https://arxiv.org/abs/2506.17818

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Recent advances in music foundation models have improved audio representation learning, yet their effectiveness across diverse musical traditions remains limited. We introduce CultureMERT-95M, a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning and understanding. To achieve this, we propose a two-stage continual pre-training strategy that integrates learning rate re-warming and re-decaying, enabling stable adaptation even with limited co…

Enhancing Large Language Models through Structured Reasoning
Yubo Dong, Hehe Fan
https://arxiv.org/abs/2506.20241 https://arxiv.org/p…

Enhancing Large Language Models through Structured Reasoning
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical deduction and systematic planning, primarily due to their reliance on implicit statistical relationships without structured knowledge representation.Inspired by cognitive science and neurosymbolic AI, we introduce a novel approach to enhance LLMs through explicit str…

Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment
Fengshun Wang, Qiurui Wang, Peilin Zhao
https://arxiv.org/abs/2508.16291

Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment
Technical Element Score (TES) and Program Component Score (PCS) evaluations in figure skating demand precise assessment of athletic actions and artistic interpretation, respectively. Existing methods face three major challenges. Firstly, video and audio cues are regarded as common features for both TES and PCS predictions in previous works without considering the prior evaluation criterion of figure skating. Secondly, action elements in competitions are separated in time, TES should be derived …

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Dirac series of $\mathrm{GL}(n)$ over an Archimedean field
Yihao Ding, Hongfeng Zhang

CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition
Joerg Deigmoeller, Stephan Hasler, Nakul Agarwal, Daniel Tanneberg, Anna Belardinelli, Reza Ghoddoosian, Chao Wang, Felix Ocker, Fan Zhang, Behzad Dariush, Michael Gienger
https://ar…

CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition
We introduce CARMA, a system for situational grounding in human-robot group interactions. Effective collaboration in such group settings requires situational awareness based on a consistent representation of present persons and objects coupled with an episodic abstraction of events regarding actors and manipulated objects. This calls for a clear and consistent assignment of instances, ensuring that robots correctly recognize and track actors, objects, and their interactions over time. To achiev…

Quantum reflection time and the Goos-H\"anchen effect
D. Sokolovski, Y. Caudano
https://arxiv.org/abs/2508.17883 https://arxiv.org/pdf/2508.17883

Quantum reflection time and the Goos-Hänchen effect
We explore the analogy between following the motion of a reflected wave packet, and a quantum measurement of the spatial delay imposed on the particle by the scattering potential. It is shown that converting such delays into temporal durations can lead to \e{negative times}, and best be avoided. It is also demonstrated that a \e{soft} potential can be replaced by superposition of hard walls. This representation is used for calculating the Goos-Hänchen shift of a Gaussian beam incident on a pot…

The Asai--Flach Euler system in $p$-adic families
David Loeffler, Arshay Sheth
https://arxiv.org/abs/2506.19673 https://arxiv.org/pdf…

The Asai--Flach Euler system in $p$-adic families
We show that the Euler system for the Asai representation corresponding to a Hilbert modular eigenform over a real quadratic field, constructed by Lei, Loeffler and Zerbes (2018), can be interpolated $p$-adically as the Hilbert modular form varies in a Hida family. This work is used as an important input in recent work of Grossi, Loeffler and Zerbes (2025) on the proof of the Bloch--Kato conjecture in analytic rank zero for the Asai representation.

An ${\mathfrak S}_3$-cover of $K_4$ and integral polyhedral graphs
Taizo Sadahiro
https://arxiv.org/abs/2508.18593 https://arxiv.org/pdf/2508.18593

An ${\mathfrak S}_3$-cover of $K_4$ and integral polyhedral graphs
We show that the star graph defined as the Cayley graph of Sn+1 generated by the star transpositions is an Sn -cover of the complete graph Kn+1 , which is known to have fine spectral properties. In the case n = 3, the star graph also has fine geometric properties: it em- beds into the honeycomb lattice and has a spectrum computable via both representation theory and an explicit Fourier formula. Inter- mediate covers correspond to the cube and truncated tetrahedron, offering a new interpretation…

Exploring the Design Space of 3D MLLMs for CT Report Generation
Mohammed Baharoon, Jun Ma, Congyu Fang, Augustin Toma, Bo Wang
https://arxiv.org/abs/2506.21535

Exploring the Design Space of 3D MLLMs for CT Report Generation
Multimodal Large Language Models (MLLMs) have emerged as a promising way to automate Radiology Report Generation (RRG). In this work, we systematically investigate the design space of 3D MLLMs, including visual input representation, projectors, Large Language Models (LLMs), and fine-tuning techniques for 3D CT report generation. We also introduce two knowledge-based report augmentation methods that improve performance on the GREEN score by up to 10\%, achieving the 2nd place on the MICCAI 2024 …

Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision
KMA Solaiman, Bharat Bhargava
https://arxiv.org/abs/2506.20070 https://…

Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision
Existing multi-media retrieval models either rely on creating a common subspace with modality-specific representation models or require schema mapping among modalities to measure similarities among multi-media data. Our goal is to avoid the annotation overhead incurred from considering retrieval as a supervised classification task and re-use the pretrained encoders in large language models and vision tasks. We propose "FemmIR", a framework to retrieve multimodal results relevant to information …

Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
Hongbo Liu, Siyi Li, Zheng Yu
https://arxiv.org/abs/2508.18766 https://

Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
Drug-drug interactions (DDIs) are a major concern in clinical practice, as they can lead to reduced therapeutic efficacy or severe adverse effects. Traditional computational approaches often struggle to capture the complex relationships among drugs, targets, and biological entities. In this work, we propose HGNN-DDI, a heterogeneous graph neural network model designed to predict potential DDIs by integrating multiple drug-related data sources. HGNN-DDI leverages graph representation learning to…

Complete Minimal Form Factors for Irrelevant Deformations of Integrable Quantum Field Theory
Fabio Sailis, Olalla A. Castro-Alvaredo, Stefano Negro
https://arxiv.org/abs/2506.20517

Complete Minimal Form Factors for Irrelevant Deformations of Integrable Quantum Field Theory
In this paper, we present a method to compute the minimal form factors of diagonal integrable field theories perturbed by generalized $T \bar{T}$ perturbations. Building on existing results by the same authors, these MFFs are constructed in such a way as not to allow for any free parameters, an issue that plagued previous solutions. The MFFs are derived from a generalization of the standard integral representation which has been used since the birth of the form factor bootstrap program. Their a…

Geometry of effective field theory positivity cones
Quentin Bonnefoy, Vicente Cort\'es, Emanuele Gendy, Christophe Grojean, Karim Ritter von Merkl, Paula Naomi Pilatus
https://arxiv.org/abs/2508.18165

Geometry of effective field theory positivity cones
Positivity bounds are theoretical constraints on the Wilson coefficients of an effective field theory. These bounds emerge from the requirement that a given effective field theory must be the low-energy limit of a relativistic quantum theory that satisfies the fundamental principles of unitarity, locality, and causality. The task of deriving these bounds can be reformulated as the geometric problem of finding the extremal representation of a closed convex cone~$\mathcal C_W$. More precisely, in…

3D Software Synthesis Guided by Constraint-Expressive Intermediate Representation
Shuqing Li, Anson Y. Lam, Yun Peng, Wenxuan Wang, Michael R. Lyu
https://arxiv.org/abs/2507.18625

3D Software Synthesis Guided by Constraint-Expressive Intermediate Representation
Graphical user interface (UI) software has undergone a fundamental transformation from traditional two-dimensional (2D) desktop/web/mobile interfaces to spatial three-dimensional (3D) environments. While existing work has made remarkable success in automated 2D software generation, such as HTML/CSS and mobile app interface code synthesis, the generation of 3D software still remains under-explored. Current methods for 3D software generation usually generate the 3D environments as a whole and can…

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Yingji Zhang, Danilo S. Carvalho, Andr\'e Freitas
https://arxiv.org/abs/2506.20083

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models (LMs). In this survey, we offer a novel perspective on latent space geometry through the lens of compositional semantics, a direction we refer to as \textit{semantic representation learning}. This direction enables a bridge between symbolic and distri…

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Exact Structures and Purity
Kevin Schlegel
https://

Communication-Aware Map Compression for Online Path-Planning: A Rate-Distortion Approach
Ali Reza Pedram, Evangelos Psomiadis, Dipankar Maity, Panagiotis Tsiotras
https://arxiv.org/abs/2506.20579

Communication-Aware Map Compression for Online Path-Planning: A Rate-Distortion Approach
This paper addresses the problem of collaborative navigation in an unknown environment, where two robots, referred to in the sequel as the Seeker and the Supporter, traverse the space simultaneously. The Supporter assists the Seeker by transmitting a compressed representation of its local map under bandwidth constraints to support the Seeker's path-planning task. We introduce a bit-rate metric based on the expected binary codeword length to quantify communication cost. Using this metric, we for…

A digital twin of atomic ensemble quantum memories
Elizabeth Robertson, Benjamin Maa{\ss}, Konrad Tschernig, Janik Wolters
https://arxiv.org/abs/2506.20403

A digital twin of atomic ensemble quantum memories
Accurate performance estimation of experimentally demonstrated quantum memories is key to understand the nuances in their deployment in photonic quantum networks. While several software packages allow for accessible quantum simulation, they often do not account for the loss and noise in physical devices. We present a framework for modeling ensemble-based atomic quantum memories using the quantum channel formalism. We provide a Kraus matrix representation of several experimentally implemented st…

Sheffer sequences with zeros on a line
G. -S. Cheon, T. Forg\'acs, K. Tran
https://arxiv.org/abs/2508.18229 https://arxiv.org/pdf/2508.18229

Sheffer sequences with zeros on a line
We extend a result of Bump et al. to show that a large family of Sheffer sequences has their zeros - up to perhaps a finite number of exceptions - on a vertical line. We connect a particular such sequence to the Riemann zeta function via a product representation of a scaled Mellin transform, analogously to the product decomposition of a Mellin transform involving the generalized Laguerre polynomials into factors of the Gamma function and Meixner polynomials.

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robus...
Zhang, Zhang, Cheng, Wang, Wang, Zhang, Yang, Wu, Huang, Aviles-Rivero, Gao, Yang, Lally
…

USAD: Universal Speech and Audio Representation via Distillation
Heng-Jui Chang, Saurabhchand Bhati, James Glass, Alexander H. Liu
https://arxiv.org/abs/2506.18843

USAD: Universal Speech and Audio Representation via Distillation
Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a unified approach to audio representation learning that integrates diverse audio types - speech, sound, and music - into a single model. USAD employs efficient layer-to-layer distillation from domain-specific SSL models to train a student on a comprehensive audio …

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Kazhdan-Laumon Category O, Braverman-Kazhdan Schwartz space, and the semi-infinite flag variety
Calder Morton-Ferguson

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Zhigong Zhou, Ning Ding, Xiaochuan Fan, Yue Shang, Yiming Qiu, Jingwei Zhuo, Zhiwei Ge, Songlin Wang, Lin Liu, Sulong Xu, Han Zhang
https://arxiv.org/abs/2506.20330

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval performance. Though learning from cross-modality data has been studied extensively in tasks such as visual…

SPARK: Graph-Based Online Semantic Integration System for Robot Task Planning
Mimo Shirasaka, Yuya Ikeda, Tatsuya Matsushima, Yutaka Matsuo, Yusuke Iwasawa
https://arxiv.org/abs/2506.20394

SPARK: Graph-Based Online Semantic Integration System for Robot Task Planning
The ability to update information acquired through various means online during task execution is crucial for a general-purpose service robot. This information includes geometric and semantic data. While SLAM handles geometric updates on 2D maps or 3D point clouds, online updates of semantic information remain unexplored. We attribute the challenge to the online scene graph representation, for its utility and scalability. Building on previous works regarding offline scene graph representations, …

ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation
Jianwen Tan, Huiyao Zhang, Rui Xiong, Han Zhou, Hongfei Wang, Ye Li
https://arxiv.org/abs/2508.18050

ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation
Camouflaged Object Segmentation (COS) poses a significant challenge due to the intrinsic high similarity between targets and backgrounds, demanding models capable of profound holistic understanding beyond superficial cues. Prevailing methods, often limited by shallow feature representation, inadequate reasoning mechanisms, and weak cross-modal integration, struggle to achieve this depth of cognition, resulting in prevalent issues like incomplete target separation and imprecise segmentation. Ins…

C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
Shusen Ma, Yun-Bo Zhao, Yu Kang
https://arxiv.org/abs/2507.17454

C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
Multivariate time series forecasting has drawn increasing attention due to its practical importance. Existing approaches typically adopt either channel-mixing (CM) or channel-independence (CI) strategies. CM strategy can capture inter-variable dependencies but fails to discern variable-specific temporal patterns. CI strategy improves this aspect but fails to fully exploit cross-variable dependencies like CM. Hybrid strategies based on feature fusion offer limited generalization and interpretabi…

Computing the Level of a Fiber for Points on Modular Curves
Hailey Maxwell
https://arxiv.org/abs/2508.17463 https://arxiv.org/pdf/2508.17463

Computing the Level of a Fiber for Points on Modular Curves
The modular curves in the family $X_1(N)$ for natural numbers $N$ parametrize elliptic curves over the complex numbers with a distinguished point of order $N$. The purpose of this paper is to better understand how to calculate the degrees of points on $X_1(\ell^n)$ for a prime $\ell$ and arbitrary positive integer $n$. In analogy with the definition of the level of a Galois representation, we construct a new definition: the level of a fiber of a closed point on a modular curve. Using this defin…

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
Soumen Sinha, Shahryar Rahnamayan, Azam Asilian Bidgoli
https://arxiv.org/abs/2507.17025

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We pr…

Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
Junhao Wu, Yun Li, Junhao Li, Jingliang Bian, Xiaomao Fan, Wenbin Lei, Ruxin Wang
https://arxiv.org/abs/2508.16882

Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
Accurate segmentation of laryngo-pharyngeal tumors is crucial for precise diagnosis and effective treatment planning. However, traditional single-modality imaging methods often fall short of capturing the complex anatomical and pathological features of these tumors. In this study, we present an innovative multi-modality representation learning framework based on the `Align-Disentangle-Fusion' mechanism that seamlessly integrates 2D White Light Imaging (WLI) and Narrow Band Imaging (NBI) pairs t…

Crosslisted article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- On Strongly \( J^{\#} \)-Clean Rings
Peter Danchev, Gholamreza Karamali, Omid Hasanzadeh, Mehrdad Esfandiar

G$^{2}$D: Boosting Multimodal Learning with Gradient-Guided Distillation
Mohammed Rakib, Arunkumar Bagavathi
https://arxiv.org/abs/2506.21514 https://

G$^{2}$D: Boosting Multimodal Learning with Gradient-Guided Distillation
Multimodal learning aims to leverage information from diverse data modalities to achieve more comprehensive performance. However, conventional multimodal models often suffer from modality imbalance, where one or a few modalities dominate model optimization, leading to suboptimal feature representation and underutilization of weak modalities. To address this challenge, we introduce Gradient-Guided Distillation (G$^{2}$D), a knowledge distillation framework that optimizes the multimodal model wit…

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Hao Dai, Chong Tang, Jagmohan Chauhan
https://arxiv.org/abs/2507.17368

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-t…

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Webs for the Quantum Orthogonal Group
Elijah Bodish, Haihan Wu
https://

Crosslisted article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Weight-Shifting Operators of Hypergeometric Type for Maass Forms
Seung Ju Lee

Fourier Transform and the minimal representation of $E_7$
Wee Teck Gan, Nadya Gurevich
https://arxiv.org/abs/2507.16968 https://arxiv.org/pdf/2507.16968

Fourier Transform and the minimal representation of $E_7$
We consider the minimal representation of the adjoint split group $E_7$ over a p-adic field. The representation has a model in a space of functions on a 17 dimensional cone $Ω$, and elements of the unique parabolic subgroup Q with abelian radical act by simple geometric formulas. We write a formula for the action of an involutive element $s$, conjugating $Q$ to the opposite parabolic $\bar Q$. The resulting integral operator, called a Fourier transform on $Ω$, is related to generalized Fourie…