Tootfinder

An explicit algorithm for the Higman Embedding Theorem
V. H. Mikaelian
https://arxiv.org/abs/2507.04347 https://arxiv.org/pdf/2507.04…

An explicit algorithm for the Higman Embedding Theorem
We propose an algorithm which for any recursive group $G$, given by its effectively enumerable generators and recursively enumerable relations, outputs an explicit embedding of $G$ into a finitely presented group directly written by its generators and defining relations. This is the explicit analogue of the remarkable Higman Embedding Theorem stating that a finitely generated group $G$ is embeddable into a finitely presented group if and only if $G$ is recursive. The constructed finitely presen…

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Xiaodong Wu, Tianyi Tang, Xiangman Li, Jianbing Ni, Yong Yu
https://arxiv.org/abs/2507.03646

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely unexplored, raising critical questions about their effectiveness against adversarial attacks. To address this gap, we examine the robustness of model-specific watermarking, where watermark embedding is integrated with text-to-image generation in models like lat…

Graph-Embedding Empowered Entity Retrieval
Emma J. Gerritse, Faegheh Hasibi, Arjen P. de Vries
https://arxiv.org/abs/2506.03895 https://

Graph-Embedding Empowered Entity Retrieval
In this research, we investigate methods for entity retrieval using graph embeddings. While various methods have been proposed over the years, most utilize a single graph embedding and entity linking approach. This hinders our understanding of how different graph embedding and entity linking methods impact entity retrieval. To address this gap, we investigate the effects of three different categories of graph embedding techniques and five different entity linking methods. We perform a reranking…

Local Fr'echet Regression via RKHS embedding and Its Applications to Data Analysis on Manifolds
Yuki Iida, Hiroshi Shiraishi, Hiroaki Ogata
https://arxiv.org/abs/2507.03288

Local Fr'echet Regression via RKHS embedding and Its Applications to Data Analysis on Manifolds
Local Fr'echet Regression (LFR) is a nonparametric regression method for settings in which the explanatory variable lies in a Euclidean space and the response variable lies in a metric space. It is used to estimate smooth trajectories in general metric spaces from noisy observations of random objects taking values in such spaces. Since metric spaces form a broad class of spaces that often lack algebraic structures such as addition or scalar multiplication characteristics typical of vector space…

Fast variational knowledge graph embedding
Pulak Ranjan Giri, Mori Kurokawa, Kazuhiro Saito
https://arxiv.org/abs/2507.02472 https://…

Fast variational knowledge graph embedding
Embedding of a knowledge graph(KG) entities and relations in the form of vectors is an important aspect for the manipulation of the KG database for several downstream tasks, such as link prediction, knowledge graph completion, and recommendation. Because of the growing size of the knowledge graph databases, it has become a daunting task for the classical computer to train a model efficiently. Quantum computer can help speedup the embedding process of the KGs by encoding the entities into a vari…

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
A. Bochkov
https://arxiv.org/abs/2507.04886 https://…

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning vectors." This paper challenges that view. We construct Transformer models where the embedding layer is entirely frozen, with vectors derived not from data, but from the visual structure of Unicode glyphs. These non-semantic, precomputed visual embeddings are fi…

Visualization for interactively adjusting the de-bias effect of word embedding
Arisa Sugino, Takayuki Itoh
https://arxiv.org/abs/2506.02447 https://…

Visualization for interactively adjusting the de-bias effect of word embedding
Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the dataset used for pre-training contains bias. On the other hand, indiscriminate removal of bias from word embeddings may result in the loss of information, even if the bias is undesirable to us. As a result, a risk of model performance degradation due to bias re…

This https://arxiv.org/abs/2409.14644 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models
The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code clustering. However, existing methods for source code embedding, including those based on LLMs, often rely on costly supervised training or fine-tuning for domain adaptation. This paper proposes a novel approach to embedding source code by combining large la…

Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs
Francesco Di Salvo, Hanh Huyen My Nguyen, Christian Ledig
https://arxiv.org/abs/2507.02671

Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs
Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Learning (FL) enables decentralized training but suffers from high communication costs and is often restricted to a single downstream task, reducing flexibility. We propose a data-sharing method via Differentially Private (DP) generative models. By adopting foundation models, we extract compact, informative embeddings, re…

Dimension-Preserving Saturated Embeddings of Finite Posets into the Spectra of Noetherian UFDs
David Baron, S. Loepp
https://arxiv.org/abs/2507.03574 https…

Dimension-Preserving Saturated Embeddings of Finite Posets into the Spectra of Noetherian UFDs
Given a finite poset $X$, we find necessary and sufficient conditions for there to exist a local Noetherian UFD $A$ and a saturated embedding of posets $ϕ: X \longrightarrow \mbox{Spec}(A)$ such that $\dim(X)=\dim(A)$. The conditions imposed on $X$ in our characterization are remarkably mild, demonstrating that there is a large class of finite posets that can be embedded into the spectrum of a local Noetherian UFD of the same dimension as $X$ in a way that preserves saturated chains. We also s…

Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization
Giuseppe Ruggeri, Renzo Andri, Daniele Jahier Pagliari, Lukas Cavigelli
https://arxiv.org/abs/2507.01676

Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization
Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck is found in the embedding layers, which perform many random memory accesses to retrieve small embedding vectors from tables of various sizes. We propose the design of tailored data flows to speedup embedding look-ups. Namely, we propose four strategies to look up an embedding table effectively on one core, and a framew…

Energy-conserving Kansa methods for Hamiltonian wave equations
Xiaobin Li, Meng Chen, Zhengjie Sun, Leevan Ling, Siqing Li
https://arxiv.org/abs/2507.04361

Energy-conserving Kansa methods for Hamiltonian wave equations
We introduce a fast, constrained meshfree solver designed specifically to inherit energy conservation (EC) in second-order time-dependent Hamiltonian wave equations. For discretization, we adopt the Kansa method, also known as the kernel-based collocation method, combined with time-stepping. This approach ensures that the critical structural feature of energy conservation is maintained over time by embedding a quadratic constraint into the definition of the numerical solution. To address the co…

The Local Structure Theorem for Graph Minors with Finite Index
Christophe Paul, Evangelos Protopapas, Dimitrios M. Thilikos, Sebastian Wiederrecht
https://arxiv.org/abs/2507.02769

The Local Structure Theorem for Graph Minors with Finite Index
The Local Structure Theorem (LST) for graph minors roughly states that every $H$-minor free graph $G$ that contains a sufficiently large wall $W$, there is a set of few vertices $A$ such that, upon removing $A$, the resulting graph $G':=G - A$ admits an "almost embedding" $δ$ into a surface $Σ$ in which $H$ does not embed. By almost embedding, we mean that there exists a hypergraph $\mathcal{H}$ whose vertex set is a subset of the vertex set of $G$ and an embedding of $\mathcal{H}$ in $Σ$ su…

Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
Weiqing Xiao, Hao Huang, Chonghao Zhong, Yujie Lin, Nan Wang, Xiaoxue Chen, Zhaoxi Chen, Saining Zhang, Shuocheng Yang, Pierre Merriaux, Lei Lei, Hao Zhao
https://arxiv.org/abs/2506.03134

Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
We present SA-Radar (Simulate Any Radar), a radar simulation approach that enables controllable and efficient generation of radar cubes conditioned on customizable radar attributes. Unlike prior generative or physics-based simulators, SA-Radar integrates both paradigms through a waveform-parameterized attribute embedding. We design ICFAR-Net, a 3D U-Net conditioned on radar attributes encoded via waveform parameters, which captures signal variations induced by different radar configurations. Th…

Toroidal embedding of Chevalley groups over $\mathbb{Z}$
Shang Li
https://arxiv.org/abs/2506.02638 https://arxiv.org/pdf/2506.02638…

Toroidal embedding of Chevalley groups over $\mathbb{Z}$
The classification of equivariant toroidal embeddings of a reductive group over an algebraically closed field is combinatorial and does not depend on the characteristic of the base field. This suggests that there should exist ``universal'' toroidal embeddings for a Chevalley group scheme over $\mathbb{Z}$ which specialize to classical toroidal embeddings via base change. In this paper, we establish the existence of ``universal'' equivariant toroidal embeddings for split reductive group schemes …

README: Robust Error-Aware Digital Signature Framework via Deep Watermarking Model
Hyunwook Choi, Sangyun Won, Daeyeon Hwang, Junhyeok Choi
https://arxiv.org/abs/2507.04495

README: Robust Error-Aware Digital Signature Framework via Deep Watermarking Model
Deep learning-based watermarking has emerged as a promising solution for robust image authentication and protection. However, existing models are limited by low embedding capacity and vulnerability to bit-level errors, making them unsuitable for cryptographic applications such as digital signatures, which require over 2048 bits of error-free data. In this paper, we propose README (Robust Error-Aware Digital Signature via Deep WaterMarking ModEl), a novel framework that enables robust, verifiabl…

Dynamic mapping from static labels: remote sensing dynamic sample generation with temporal-spectral embedding
Shuai Yuan, Shuang Chen, Tianwu Lin, Jie Wang, Peng Gong
https://arxiv.org/abs/2506.02574

Dynamic mapping from static labels: remote sensing dynamic sample generation with temporal-spectral embedding
Accurate remote sensing geographic mapping depends heavily on representative and timely sample data. However, rapid changes in land surface dynamics necessitate frequent updates, quickly rendering previously collected samples obsolete and imposing significant labor demands for continuous manual updates. In this study, we aim to address this problem by dynamic sample generation using existing single-date static labeled samples. We introduce TasGen, a two-stage automated framework to automaticall…

Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval
Yubai Wei, Jiale Han, Yi Yang
https://arxiv.org/abs/2506.00363 …

Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness diminishes when applied to private datasets (e.g., company-specific proprietary data), which often contain specialized terminology and lingo. In this work, we introduce BMEmbed, a novel method for adapting general-purpose text embedding models to private data…

The presentable stable envelope of an exact category
Christoph Winges, Marius Nielsen
https://arxiv.org/abs/2506.02598 https://arxiv.…

The presentable stable envelope of an exact category
We prove an analogue of the Gabriel--Quillen embedding theorem for exact $\infty$-categories, giving rise to a presentable version of Klemenc's stable envelope of an exact $\infty$-category. Moreover, we construct a symmetric monoidal structure on the $\infty$-category of small exact $\infty$-categories and discuss the multiplicative properties of the Gabriel--Quillen embedding. For $E$ an Adams-type homotopy associative ring spectrum, this allows us to identify the symmetric monoidal $\infty$-…

This https://arxiv.org/abs/2506.01297 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MobCLIP: Learning General-purpose Geospatial Representation at Scale
Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence. Current embedding methods often lack versatility, limiting their utility across diverse tasks in both human and natural domains. We present MobCLIP, the first nationwide general-purpose location encoder, integrating an unprecedented diversity of data modalities through effective and scalable multimodal fusion. Adopting a novel CLIP-based architecture, our framework aligns 100M+…

Plan-Based Scalable Online Virtual Network Embedding
Oleg Kolosov, David Breitgand, Dean H. Lorenz, Gala Yadgar
https://arxiv.org/abs/2507.00237 https://…

Plan-Based Scalable Online Virtual Network Embedding
Network virtualization allows hosting applications with diverse computation and communication requirements on shared edge infrastructure. Given a set of requests for deploying virtualized applications, the edge provider has to deploy a maximum number of them to the underlying physical network, subject to capacity constraints. This challenge is known as the virtual network embedding (VNE) problem: it models applications as virtual networks, where virtual nodes represent functions and virtual lin…

Laterally Excited Bulk Acoustic Wave (LBAW) X-Cut Lithium Niobate Resonators
Walter Gubinelli, Ryan Tetro, Pietro Simeoni, Luca Colombo, Matteo Rinaldi
https://arxiv.org/abs/2506.04433

Laterally Excited Bulk Acoustic Wave (LBAW) X-Cut Lithium Niobate Resonators
In this work, Laterally excited Bulk Acoustic Wave (LBAW) resonators on X-cut Lithium Niobate (LiNbO3) and, for the first time their higher-order overtones (LOBAW) are demonstrated by embedding interdigitated electrodes recessed into the piezoelectric thin film, allowing to exploit both S0 and SH0 vibrational modes. This recessed electrode architecture decouples the dispersion relation from film thickness, enabling lithographic tuning of resonance frequency and on-chip multi-frequency scaling o…

3-manifolds with more than one abelian embedding
Jonathan A. Hillman
https://arxiv.org/abs/2506.01186 https://arxiv.org/pdf/2506.0118…

3-manifolds with more than one abelian embedding
We construct 3-manifolds which have at least two inequivalent embeddings such that both complementary regions have abelian fundamental group.

This https://arxiv.org/abs/2505.13394 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Multireference Embedding and Fragmentation Methods for Classical and Quantum Computers: from Model Systems to Realistic Applications
One of the primary challenges in quantum chemistry is the accurate modeling of strong electron correlation. While multireference methods effectively capture such correlation, their steep scaling with system size prohibits their application to large molecules and extended materials. Quantum embedding offers a promising solution by partitioning complex systems into manageable subsystems. In this review, we highlight recent advances in multireference density matrix embedding and localized active s…

On the subsystems 0f certain almost Markov shifts
Wolfgang Krieger
https://arxiv.org/abs/2507.02717 https://arxiv.org/pdf/2507.02717

On the subsystems 0f certain almost Markov shifts
For an aperiodic subshift of finite type Y and for a subshift X with topological entropy less than the topological entropy of Y, it was proved in Krieger: On the subsystems of topological Markov chains, Ergodic theory and dynamical systems 1982, 2, 195-202, that the necessary condition on the periodic points of X and Y for the existence of an embedding of X int Y is also sufficient for the existence of an embedding of X into Y. In this note we extend this theorem to a certain class of almost Ma…

Estimating the Euclidean distortion of an orbit space
Ben Blum-Smith, Harm Derksen, Dustin G. Mixon, Yousef Qaddura, Brantley Vose
https://arxiv.org/abs/2506.04425

Estimating the Euclidean distortion of an orbit space
Given a finite-dimensional inner product space $V$ and a group $G$ of isometries, we consider the problem of embedding the orbit space $V/G$ into a Hilbert space in a way that preserves the quotient metric as well as possible. This inquiry is motivated by applications to invariant machine learning. We introduce several new theoretical tools before using them to tackle various fundamental instances of this problem.

GENPLUGIN: A Plug-and-Play Framework for Long-Tail Generative Recommendation with Exposure Bias Mitigation
Kun Yang, Siyao Zheng, Tianyi Li, Xiaodong Li, Hui Li
https://arxiv.org/abs/2507.03568

GENPLUGIN: A Plug-and-Play Framework for Long-Tail Generative Recommendation with Exposure Bias Mitigation
Generative recommendation (GenRec) offers LLM integration, reduced embedding costs, and eliminates per-candidate scoring, attracting great attention. Despite its promising performance, this study reveals that it suffers from generation exposure bias and poor long-tail item generalization, two critical limitations overlooked by prior works on GenRec. To address these, we propose GENPLUGIN, a plug-and-play framework featuring a dual-encoder, shared-decoder architecture. During pre-training, it al…

This https://arxiv.org/abs/2411.07103 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

On a connection between total positivity and Bernoulli stopping problems
Consider the optimal stopping problem of maximising the expected payoff in a game where a nonnegative reward is granted upon stopping on a success in a sequence of independent Bernoulli trials. These Bernoulli stopping problems are characterised by a recurrence relation connecting the stopping and continuation payoffs. This recurrence is used to establish optimality of the myopic strategy under unimodal continuation payoffs. Further, by embedding the success epochs of the trials into a Markov c…

Tunable spin-phonon polarons in a chiral molecular qubit framework
Aimei Zhou, Ruihao Bi, Zhenghan Zhang, Luming Yang, Xudong Tian, Denan Li, Mingshu Tan, Weibin Ni, Haozhou Sun, Jinkun Guo, Xinxing Zhao, Zhifu Shi, Wei Tong, Zhitao Zhang, Jin-Hu Dou, Feng Jin, Shi Liu, Mircea Dinca, Tijana Rajh, Jian Li, Wenjie Dou, Lei Sun
https://

Tunable spin-phonon polarons in a chiral molecular qubit framework
Chiral structures that produce asymmetric spin-phonon coupling can theoretically generate spin-phonon polarons -- quasiparticles exhibiting non-degenerate spin states with phonon displacements. However, direct experimental evidence has been lacking. Using a chiral molecular qubit framework embedding stable semiquinone-like radicals, we report spin dynamic signatures that clearly indicate the formation of spin-phonon polarons for the first time. Our non-adiabatic model reveals that these quasipa…

AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences
Minoru Kishi, Ryosuke Sakai, Shinnosuke Takamichi, Yusuke Kanamori, Yuki Okamoto
https://arxiv.org/abs/2507.00475

AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences
We propose a novel objective evaluation metric for synthesized audio in text-to-audio (TTA), aiming to improve the performance of TTA models. In TTA, subjective evaluation of the synthesized sound is an important, but its implementation requires monetary costs. Therefore, objective evaluation such as mel-cepstral distortion are used, but the correlation between these objective metrics and subjective evaluation values is weak. Our proposed objective evaluation metric, AudioBERTScore, calculates …

Updated constraints on Regge-Teitelboim gravity
S. R. Pinto, C. J. A. P. Martins
https://arxiv.org/abs/2506.22006 https://arxiv.org/p…

Updated constraints on Regge-Teitelboim gravity
In the Regge-Teitelboim model, gravity is described by embedding the space-time manifold in a (usually flat) fixed higher-dimensional background, where the embedding coordinates, rather than the metric tensor, are the dynamical degrees of freedom. Stern \& Xu extended the Regge-Teitelboim framework to encompass scenarios where the background embedding space is not flat, noting that when the background is a five-dimensional de Sitter space, the Robertson-Walker manifold undergoes a transition fr…

Dynamically derived morphology from the recurrence patterns of close binary stars using Kepler data
Anisha R. V. Kashyap, D. Pawar, R. Misra, G. Ambika, Sandip V George
https://arxiv.org/abs/2506.04111

Dynamically derived morphology from the recurrence patterns of close binary stars using Kepler data
In this work, we propose a novel method to classify close binary stars, derived from the dynamical structure inherent in their light curves. We apply the technique to light curves of binaries from the revised Kepler Eclipsing binary catalog, selecting close binaries which have the standard morphology parameter, $c$, $\gt 0.5$ corresponding to semi-detached, over-contact and ellipsoidal systems. Using the method of time delay embedding, we recreate the non-linear dynamics underlying the data and…

Physics-Informed Neural Network Approach to Quark-Antiquark Color Flux Tube
Wei Kou, Xiaoxuan Lin, Bing'ang Guo, Xurong Chen
https://arxiv.org/abs/2506.03513

Physics-Informed Neural Network Approach to Quark-Antiquark Color Flux Tube
We introduce a physics-informed neural network (PINNs) framework for modelling the spatial distribution of chromodynamic fields induced by quark-antiquark pairs, based on lattice Monte Carlo simulations. In contrast to conventional neural networks, PINNs incorporate physical laws--expressed here as differential equations governing type-II superconductivity--directly into the training objective. By embedding these equations into the loss function, we guide the network to learn physically consist…

Embedding a Praeger-Xu graph into a surface
Zhaochen Ding, Zheng Guo, Luyi Liu
https://arxiv.org/abs/2507.01716 https://arxiv.org/pdf…

Embedding a Praeger-Xu graph into a surface
Rotary maps (orientably regular maps) are highly symmetric graph embeddings on orientable surfaces. This paper classifies all rotary maps whose underlying graphs are Praeger-Xu graphs, denoted $\operatorname{C}(p,r,s)$, for any odd prime $p$ that does not divide $r$. Our main result establishes a one-to-one correspondence between the isomorphism classes of these maps and the multiplicity-free representations of the dihedral group $\operatorname{D}_{2r}$ over the finite field $\mathbb{F}_p$. Thi…

This https://arxiv.org/abs/2503.18156 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Adoption of Watermarking Measures for AI-Generated Content and Implications under the EU AI Act
AI-generated images have become so good in recent years that individuals often cannot distinguish them any more from "real" images. This development, combined with the rapid spread of AI-generated content online, creates a series of societal risks, particularly with the emergence of "deep fakes" that impersonate real individuals. Watermarking, a technique that involves embedding information within images and other content to indicate their AI-generated nature, has emerged as a primary mechanism…

This https://arxiv.org/abs/2407.01203 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

An elementary proof of a criterion for subfunctors of Ext to be closed
Let $\mathcal{A}$ be an abelian category and let $F$ be a subbifunctor of the additive bifunctor $\text{Ext}_{\mathcal{A}}^{1}(-,-)\colon \mathcal{A}^{\text{op}}\times \mathcal{A}\to \mathsf{Ab}$. Buan proved in [4] that $F$ is closed if, and only if, $F$ has the $3\times 3$-lemma property, a certain diagrammatic property satisfied by the class of $F$-exact sequences. The proof of this result relies on the theory of exact categories and on the Freyd--Mitchell embedding theorem, a very well-know…

This https://arxiv.org/abs/2505.13476 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Unified Structural Embedding of Orbifold Sigma Models
This paper introduces a unified structural embedding framework for orbifold sigma models that systematically incorporates twisted sectors, singularities, and smooth regions into a single algebraic object. Traditional approaches to orbifold theories often treat sectors separately, requiring ad hoc regularizations near singularities and failing to capture inter-sector interactions under renormalization group flow. The framework presented herein resolves these limitations through the construction …

Features-based embedding or Feature-grounding
Piotr Makarevich
https://arxiv.org/abs/2506.22442 https://arxiv.org/pdf/2506.22442

Features-based embedding or Feature-grounding
In everyday reasoning, when we think about a particular object, we associate it with a unique set of expected properties such as weight, size, or more abstract attributes like density or horsepower. These expectations are shaped by our prior knowledge and the conceptual categories we have formed through experience. This paper investigates how such knowledge-based structured thinking can be reproduced in deep learning models using features based embeddings. Specially, it introduces an specific a…

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
Matteo Attimonelli, Alessandro De Bellis, Claudio Pomo, Dietmar Jannach, Eugenio Di Sciascio, Tommaso Di Noia
https://arxiv.org/abs/2507.05006

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
Pre-trained language models (PLMs) are widely used to derive semantic representations from item metadata in recommendation and search. In sequential recommendation, PLMs enhance ID-based embeddings through textual metadata, while in product search, they align item characteristics with user intent. Recent studies suggest task and domain-specific fine-tuning are needed to improve representational power. This paper challenges this assumption, showing that Generalist Text Embedding Models (GTEs), p…

Unified Network-Based Representation of BIM Models for Embedding Semantic, Spatial, and Topological Data
Jin Han, Xin-Zheng Lu, Jia-Rui Lin
https://arxiv.org/abs/2505.22670

Unified Network-Based Representation of BIM Models for Embedding Semantic, Spatial, and Topological Data
Building Information Modeling (BIM) has revolutionized the construction industry by providing a comprehensive digital representation of building structures throughout their lifecycle. However, existing research lacks effective methods for capturing the complex spatial and topological relationships between components in BIM models, which are essential for understanding design patterns and enhancing decision-making. This study proposes a unified network-based representation method that integrates…

Privacy-Aware, Public-Aligned: Embedding Risk Detection and Public Values into Scalable Clinical Text De-Identification for Trusted Research Environments
Arlene Casey, Stuart Dunbar, Franz Gruber, Samuel McInerney, Mat\'u\v{s} Falis, Pamela Linksted, Katie Wilde, Kathy Harrison, Alison Hamilton, Christian Cole
https://arxiv.…

Privacy-Aware, Public-Aligned: Embedding Risk Detection and Public Values into Scalable Clinical Text De-Identification for Trusted Research Environments
Clinical free-text data offers immense potential to improve population health research such as richer phenotyping, symptom tracking, and contextual understanding of patient care. However, these data present significant privacy risks due to the presence of directly or indirectly identifying information embedded in unstructured narratives. While numerous de-identification tools have been developed, few have been tested on real-world, heterogeneous datasets at scale or assessed for governance read…

Quasioptic, Calibrated, Full 2-port Measurements of Cryogenic Devices under Vacuum in the 220-330 GHz Band
Maxim Masyukov, Aleksi Tamminen, Irina Nefedova, Andrey Generalov, Samu-Ville P\"alli, Roman Grigorev, Pouyan Rezapoor, Rui Silva, Juha Mallat, Juha Ala-Laurinaho, Zachary Taylor
https://arxiv.org/abs/2506.03824…

Quasioptic, Calibrated, Full 2-port Measurements of Cryogenic Devices under Vacuum in the 220-330 GHz Band
A quasi-optical (QO) test bench was designed, simulated, and calibrated for characterizing S-parameters of devices in the 220-330 GHz (WR-3.4) frequency range, from room temperature down to 4.8 K. The devices were measured through vacuum windows via focused beam radiation. A de-embedding method employing line-reflect-match (LRM) calibration was established to account for the effects of optical components and vacuum windows. The setup provides all four S-parameters with the reference plane locat…

The Hasse principle for homogeneous polynomials with random coefficients over thin sets II
Daniel Flores, Kiseok Yeon
https://arxiv.org/abs/2506.01291 http…

The Hasse principle for homogeneous polynomials with random coefficients over thin sets II
Let $d$ and $n$ be natural numbers. Let $ν_{d,n}: \mathbb{R}^n\rightarrow \mathbb{R}^{N}$ denote the Veronese embedding with $N=N_{n,d}:=\binom{n+d-1}{d}$, defined by listing all the monomials of degree $d$ in $n$ variables using the lexicographical ordering. Let $\langle \boldsymbol{a}, ν_{d,n}(\boldsymbol{x})\rangle\in \mathbb{Z}[\boldsymbol{x}]$ be a homogeneous polynomial in $n$ variables of degree $d$ with integer coefficients $\boldsymbol{a}$, where $\langle\cdot,\cdot\rangle$ denotes t…

Energy-Embedded Neural Solvers for One-Dimensional Quantum Systems
Yi-Qiang Wu, Xuan Liu, Hanlin Li, Fuqiang Wang
https://arxiv.org/abs/2505.24194 https://…

Energy-Embedded Neural Solvers for One-Dimensional Quantum Systems
Physics-informed neural networks (PINN) have been widely used in computational physics to solve partial differential equations (PDEs). In this study, we propose an energy-embedding-based physics-informed neural network method for solving the one-dimensional time-independent Schrödinger equation to obtain ground- and excited-state wave functions, as well as energy eigenvalues by incorporating an embedding layer to generate process-driven data. The method demonstrates high accuracy for several w…

A unifying approach to self-organizing systems interacting via conservation laws
Frank Barrows, Guanming Zhang, Satyam Anand, Zizi Chen, Jonathan Lin, Amman Desai, Stefano Martiniani, Francesco Caravelli
https://arxiv.org/abs/2507.02575

A unifying approach to self-organizing systems interacting via conservation laws
We present a unified framework for embedding and analyzing dynamical systems using generalized projection operators rooted in local conservation laws. By representing physical, biological, and engineered systems as graphs with incidence and cycle matrices, we derive dual projection operators that decompose network fluxes and potentials. This formalism aligns with principles of non-equilibrium thermodynamics and captures a broad class of systems governed by flux-forcing relationships and local c…

Random Hyperbolic Graphs with Arbitrary Mesoscale Structures
Stefano Guarino, Davide Torre, Enrico Mastrostefano
https://arxiv.org/abs/2506.02686 https://

Random Hyperbolic Graphs with Arbitrary Mesoscale Structures
Real-world networks exhibit universal structural properties such as sparsity, small-worldness, heterogeneous degree distributions, high clustering, and community structures. Geometric network models, particularly Random Hyperbolic Graphs (RHGs), effectively capture many of these features by embedding nodes in a latent similarity space. However, networks are often characterized by specific connectivity patterns between groups of nodes -- i.e. communities -- that are not geometric, in the sense t…

Systemic Constraints of Undecidability
Seth Bulin
https://arxiv.org/abs/2507.01036 https://arxiv.org/pdf/2507.01036

Systemic Constraints of Undecidability
This paper presents a theory of systemic undecidability, reframing incomputability as a structural property of systems rather than a localized feature of specific functions or problems. We define a notion of causal embedding and prove a closure principle: any subsystem that participates functionally in the computation of an undecidable system inherits its undecidability. This result positions undecidability as a pervasive constraint on prediction, modeling, and epistemic access in both natural …

Embedding theorems for Bergman-Zygmund spaces induced by doubling weights
Atte Pennanen
https://arxiv.org/abs/2505.23211 https://arxi…

Embedding theorems for Bergman-Zygmund spaces induced by doubling weights
Let $0

This https://arxiv.org/abs/2505.14806 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Place Cells as Position Embeddings of Multi-Time Random Walk Transition Kernels for Path Planning
The hippocampus orchestrates spatial navigation through collective place cell encodings that form cognitive maps. We reconceptualize the population of place cells as position embeddings approximating multi-scale symmetric random walk transition kernels: the inner product $\langle h(x, t), h(y, t) \rangle = q(y|x, t)$ represents normalized transition probabilities, where $h(x, t)$ is the embedding at location $ x $, and $q(y|x, t)$ is the normalized symmetric transition probability ove…

Embedding $\mathrm{SL}(2,\mathbb{C})/\mathbb{Z}_2$ in Complex Riemannian Geometry
John. W. Moffat, Ethan. J. Thompson
https://arxiv.org/abs/2506.19158 http…

Embedding $\mathrm{SL}(2,\mathbb{C})/\mathbb{Z}_2$ in Complex Riemannian Geometry
We present a unified framework demonstrating how the spinor complex Lorentz group SL(2,C)/Z\_2 is realized as a canonical subgroup within a four-dimensional complex Riemannian manifold. Building on the complex, holomorphic metric extension and contour-integration regularization of classical singularities, we show that promoting the metric to a complex-valued tensor on a complex 4-fold enlarges the frame bundle to SO(4,C). Its spin double cover factorizes as a product of two independent SL(2,C) …

This https://arxiv.org/abs/2409.16662 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A new class of anisotropic double phase problems: exponents depending on solutions and their gradients
In this work, we introduce two novel classes of quasilinear elliptic equations, each driven by the double phase operator with variable exponents. The first class features a new double phase equation where exponents depend on the gradient of the solution. We delve into proving various properties of the corresponding Musielak-Orlicz Sobolev spaces, including the $Δ_2$ property, uniform convexity, density and compact embedding. Additionally, we explore the characteristics of the new double phase …

This https://arxiv.org/abs/2506.01186 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

3-manifolds with more than one abelian embedding
We construct 3-manifolds which have at least two inequivalent embeddings such that both complementary regions have abelian fundamental group.

SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer
Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish, Swarup Ranjan Behera, Abu Osama Siddiqui, Sarthak Jain, Priyabrata Mallick, Jaya Sai Kiran Patibandla, Pailla Balakrishna Reddy, Arun Balaji Buduru, Rajesh Sharma
https://

SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer
As video-sharing platforms have grown over the past decade, child viewership has surged, increasing the need for precise detection of harmful content like violence or explicit scenes. Malicious users exploit moderation systems by embedding unsafe content in minimal frames to evade detection. While prior research has focused on visual cues and advanced such fine-grained detection, audio features remain underexplored. In this study, we embed audio cues with visual for fine-grained child harmful c…

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
Dipam Goswami, Liying Wang, Bart{\l}omiej Twardowski, Joost van de Weijer
https://arxiv.org/abs/2506.00037

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training data is static, thus limiting its applications to dynamic scenarios where new training data emerges over time. IR methods generally encode a huge corpus of documents to low-dimensional embeddings and store them in a database index. During retrieval, a semant…

Quantum Assisted Ghost Gutzwiller Ansatz
P. V. Sriluckshmy, Fran\c{c}ois Jamet, Fedor \v{S}imkovic IV
https://arxiv.org/abs/2506.21431 https://

Quantum Assisted Ghost Gutzwiller Ansatz
The ghost Gutzwiller ansatz (gGut) embedding technique was shown to achieve comparable accuracy to the gold standard dynamical mean-field theory method in simulating real material properties, yet at a much lower computational cost. Despite that, gGut is limited by the algorithmic bottleneck of computing the density matrix of the underlying effective embedding model, a quantity which must be converged within a self-consistent embedding loop. We develop a hybrid quantum-classical gGut technique w…

This https://arxiv.org/abs/2505.22652 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

PyRigi -- a general-purpose Python package for the rigidity and flexibility of bar-and-joint frameworks
We present PyRigi, a novel Python package designed to study the rigidity properties of graphs and frameworks. Among many other capabilities, PyRigi can determine whether a graph admits only finitely many ways, up to isometries, of being drawn in the plane once the edge lengths are fixed, whether it has a unique embedding, or whether it satisfied such properties even after the removal of any of its edges. By implementing algorithms from the scientific literature, PyRigi enables the exploration o…

Last week, we continued our #ISE2025 lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models.
Benefits of NLMs:
- Capturing Long-Range Dependencies
- Computational and Statistical Tractability
- Improved Generalisation
- Higher Accuracy
@…

On the Stability of the Euler Characteristic Transform for a Perturbed Embedding
Jasmine George, Oscar Lledo Osborn, Elizabeth Munch, Messiah Ridgley II, Elena Xinyi Wang
https://arxiv.org/abs/2506.19991

On the Stability of the Euler Characteristic Transform for a Perturbed Embedding
The Euler Characteristic Transform (ECT) is a robust method for shape classification. It takes an embedded shape and, for each direction, computes a piecewise constant function representing the Euler Characteristic of the shape's sublevel sets, which are defined by the height function in that direction. It has applications in TDA inverse problems, such as shape reconstruction, and is also employed with machine learning methodologies. In this paper, we define a distance between the ECTs of two d…

News Sentiment Embeddings for Stock Price Forecasting
Ayaan Qayyum
https://arxiv.org/abs/2507.01970 https://arxiv.org/pdf/2507.01970

News Sentiment Embeddings for Stock Price Forecasting
This paper will discuss how headline data can be used to predict stock prices. The stock price in question is the SPDR S&P 500 ETF Trust, also known as SPY that tracks the performance of the largest 500 publicly traded corporations in the United States. A key focus is to use news headlines from the Wall Street Journal (WSJ) to predict the movement of stock prices on a daily timescale with OpenAI-based text embedding models used to create vector encodings of each headline with principal componen…

Automated Symmetric Constructions in Discrete Geometry
Bernardo Subercaseaux, Ethan Mackey, Long Qian, Marijn J. H. Heule
https://arxiv.org/abs/2506.00224 …

Automated Symmetric Constructions in Discrete Geometry
We present a computational methodology for obtaining rotationally symmetric sets of points satisfying discrete geometric constraints, and demonstrate its applicability by discovering new solutions to some well-known problems in combinatorial geometry. Our approach takes the usage of SAT solvers in discrete geometry further by directly embedding rotational symmetry into the combinatorial encoding of geometric configurations. Then, to realize concrete point sets corresponding to abstract designs …

This https://arxiv.org/abs/2410.16428 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions
Modern speaker verification systems primarily rely on speaker embeddings and cosine similarity. While effective, these methods struggle with multi-talker speech due to the unidentifiability of embedding vectors. We propose Neural Scoring (NS), a novel end-to-end framework that directly estimates verification posterior probabilities without relying on test-side embeddings, making it more powerful and robust to complex conditions, e.g., with multiple talkers. To address the challenge of training …

Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
Madox C. McGrae-Menge, Jacob R. Pierce, Frederico Fiuza, E. Paulo Alves
https://arxiv.org/abs/2506.14048

Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
Machine learning is offering powerful new tools for the development and discovery of reduced models of nonlinear, multiscale plasma dynamics from the data of first-principles kinetic simulations. However, ensuring the physical consistency of such models requires embedding fundamental symmetries of plasma dynamics. In this work, we explore a symmetry-embedding strategy based on data augmentation, where symmetry-preserving transformations (e.g., Lorentz and Galilean boosts) are applied to simulat…

A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study
Agnideep Aich, Sameera Hewage, Md Monzur Murshed, Ashit Baran Aich, Amanda Mayeaux, Asim K. Dey, Kumer P. Das, Bruce Wade
https://arxiv.org/abs/2505.24006

A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study
In this paper, we introduce the A2 Copula Spatial Bayesian Neural Network (A2-SBNN), a predictive spatial model designed to map coordinates to continuous fields while capturing both typical spatial patterns and extreme dependencies. By embedding the dual-tail novel Archimedean copula viz. A2 directly into the network's weight initialization, A2-SBNN naturally models complex spatial relationships, including rare co-movements in the data. The model is trained through a calibration-driven process …

This https://arxiv.org/abs/2505.16933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a representative large language diffusion model, LLaDA-V incorporates a vision encoder and MLP connector that projects visual features into the language embedding space, enabling effective multimodal alignme…

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Fengze Li, Yue Wang, Yangle Liu, Ming Huang, Dou Hong, Jieming Ma
https://arxiv.org/abs/2506.20167

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Multivariate time series forecasting requires models to simultaneously capture variable-wise structural dependencies and generalize across diverse tasks. While structural encoders are effective in modeling feature interactions, they lack the capacity to support semantic-level reasoning or task adaptation. Conversely, large language models (LLMs) possess strong generalization capabilities but remain incompatible with raw time series inputs. This gap limits the development of unified, transferabl…

Embedding-based Retrieval in Multimodal Content Moderation
Hanzhong Liang, Jinghao Shi, Xiang Shen, Zixuan Wang, Vera Wen, Ardalan Mehrani, Zhiqian Chen, Yifan Wu, Zhixin Zhang
https://arxiv.org/abs/2507.01066

Embedding-based Retrieval in Multimodal Content Moderation
Video understanding plays a fundamental role for content moderation on short video platforms, enabling the detection of inappropriate content. While classification remains the dominant approach for content moderation, it often struggles in scenarios requiring rapid and cost-efficient responses, such as trend adaptation and urgent escalations. To address this issue, we introduce an Embedding-Based Retrieval (EBR) method designed to complement traditional classification approaches. We first lever…

A Formula for Connected Bosonic \(n\)-Point Functions for the BKP Hierarchy
Xuhui Zhang, Jian Zhou
https://arxiv.org/abs/2506.00451 https://

A Formula for Connected Bosonic \(n\)-Point Functions for the BKP Hierarchy
We present a formula for the connected \(n\)-point functions of a tau-funtion of the BKP hierarchy by embedding BKP hierarchy into KP hierarchy. This formula is different from the one given by Wang and Yang. We prove that these two formulae are equivalent.

An AST-guided LLM Approach for SVRF Code Synthesis
Abanoub E. Abdelmalak, Mohamed A. Elsayed, David Abercrombie, Ilhami Torunoglu
https://arxiv.org/abs/2507.00352

An AST-guided LLM Approach for SVRF Code Synthesis
Standard Verification Rule Format (SVRF) is essential for semiconductor applications like Design Rule Check (DRC), Layout Versus Schematic (LVS), and Optical Proximity Correction (OPC) and it faces challenges as advancing nodes create complex design rules that renders traditional SVRF development ineffective and highlight an expertise gap. This paper introduces a novel methodology integrating Abstract Syntax Tree (AST) embedding and Retrieval-Augmented Generation (RAG) for enhanced SVRF code sy…

On the proofs of Leighton's Graph Covering Theorem and a notion dual to commensurability
Nicholas Touikan
https://arxiv.org/abs/2507.01839 https://

On the proofs of Leighton's Graph Covering Theorem and a notion dual to commensurability
Leighton's Graph Covering Theorem states that if two finite graphs have the same universal covering tree, then they also have a common finite degree cover. Bass and Kulkarni gave an alternative proof of this fact using tree lattices. We give an example of two graphs that admit a common finite cover which can not be obtained using tree lattice techniques. The argument naturally leads to the question of when a commensuration can be induced by an embedding into a common finite index overgroup. We …

Replaced article(s) found for cs.SI. https://arxiv.org/list/cs.SI/new
[1/1]:
- Principal Graph Encoder Embedding and Principal Community Detection
Cencheng Shen, Yuexiao Dong, Carey E. Priebe, Jonathan Larson, Ha Trinh, Youngser Park

NAVER LABS Europe Submission to the Instruction-following Track
Beomseok Lee, Marcely Zanon Boito, Laurent Besacier, Ioan Calapodescu
https://arxiv.org/abs/2506.01808

NAVER LABS Europe Submission to the Instruction-following Track
In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encod…

Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
Zhaoyang Li, Haodong Zhou, Longjie Luo, Xiaoxiao Li, Yongxin Chen, Lin Li, Qingyang Hong
https://arxiv.org/abs/2506.02621

Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
This paper presents the system developed for Task 1 of the Multi-modal Information-based Speech Processing (MISP) 2025 Challenge. We introduce CASA-Net, an embedding fusion method designed for end-to-end audio-visual speaker diarization (AVSD) systems. CASA-Net incorporates a cross-attention (CA) module to effectively capture cross-modal interactions in audio-visual signals and employs a self-attention (SA) module to learn contextual relationships among audio-visual frames. To further enhance p…

Generative flow-based warm start of the variational quantum eigensolver
Hang Zou, Martin Rahm, Anton Frisk Kockum, Simon Olsson
https://arxiv.org/abs/2507.01726

Generative flow-based warm start of the variational quantum eigensolver
Hybrid quantum-classical algorithms like the variational quantum eigensolver (VQE) show promise for quantum simulations on near-term quantum devices, but are often limited by complex objective functions and expensive optimization procedures. Here, we propose Flow-VQE, a generative framework leveraging conditional normalizing flows with parameterized quantum circuits to efficiently generate high-quality variational parameters. By embedding a generative model into the VQE optimization loop throug…

Linear codes arising from the point-hyperplane geometry-Part I: the Segre embedding
Ilaria Cardinali, Luca Giuzzi
https://arxiv.org/abs/2506.21309 https://…

Linear codes arising from the point-hyperplane geometry-Part I: the Segre embedding
Let $V$ be a vector space over the finite field $\mathbb{F}_q$ with $q$ elements and $Λ$ be the image of the Segre geometry $\mathrm{PG}(V)\otimes\mathrm{PG}(V^*)$ in $\mathrm{PG}(V\otimes V^*)$. Consider the subvariety $Λ_{1}$ of $Λ$ represented by the pure tensors $x\otimes ξ$ with $x\in V$ and $ξ\in V^*$ such that $ξ(x)=0$. Regarding $Λ_1$ as a projective system of $\mathrm{PG}(V\otimes V^*)$, we study the linear code $\mathcal{C}(Λ_1)$ arising from it. The code $\mathcal{C}(Λ_1)$ i…

Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space
Guangyuan Weng, Minsuk Kim, Yong-Yeol Ahn, Esteban Moro
https://arxiv.org/abs/2506.24061

Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space
Human mobility in cities is shaped not only by visible structures such as highways, rivers, and parks but also by invisible barriers rooted in socioeconomic segregation, uneven access to amenities, and administrative divisions. Yet identifying and quantifying these barriers at scale and their relative importance on people's movements remains a major challenge. Neural embedding models, originally developed for language, offer a powerful way to capture the complexity of human mobility from large-…

This https://arxiv.org/abs/2410.13230 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Starbucks-v2: Improved Training for 2D Matryoshka Embeddings
2D Matryoshka training enables a single embedding model to generate sub-network representations across different layers and embedding dimensions, offering adaptability to diverse computational and task constraints. However, its effectiveness remains well below that of individually trained models of equivalent sizes. To address this, we propose Starbucks, a new training strategy for Matryoshka-style embedding models that combines structured fine-tuning with masked autoencoder (MAE) pre-training.…

This https://arxiv.org/abs/2303.17475 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning distributed representations with efficient SoftMax normalization
Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function of the term ${\rm SoftMax}(XY^T)$. The complexity required to calculate this term, however, runs quadratically with the problem size, making it a computationally heavy solution. In this article, we propose a linear-time heuristic approximation to compute the …

Replaced article(s) found for math.GT. https://arxiv.org/list/math.GT/new
[1/1]:
- Criteria for toroidal embedding of one-vertex ribbon graphs
Tim Berezin

This https://arxiv.org/abs/2209.01847 has been replaced.
link: https://scholar.google.com/scholar?q=a

Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment
Entity alignment aims to discover unique equivalent entity pairs with the same meaning across different knowledge graphs (KGs). Existing models have focused on projecting KGs into a latent embedding space so that inherent semantics between entities can be captured for entity alignment. However, the adverse impacts of alignment conflicts have been largely overlooked during training, thereby limiting the entity alignment performance. To address this issue, we propose a novel Conflict-aware Pseudo…

This https://arxiv.org/abs/2303.14503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

On winding numbers of $K_5$ minus an edge in the plane
Let $K$ be the graph on vertices $\{1, 2, 3, 4, 5\}$, and having all edges except $(4, 5)$. A continuous map $f:K\to \R^2$ is called an \emph{almost embedding} if $f$-images of non-adjacent edges are disjoint. Take the winding numbers of the $f$-image of the oriented cycle $(1, 2, 3)$ around $f(4)$ and around $f(5)$. We prove that the difference of these numbers equals $\pm 1$. This is surprising, because in other similar situations analogous statement is wrong.

On multiplicities in length spectra of semi-arithmetic hyperbolic surfaces
Mikhail Belolipetsky, Gregory Cosac, Cayo D\'oria, Gisele Teixeira Paula
https://arxiv.org/abs/2507.00211

On multiplicities in length spectra of semi-arithmetic hyperbolic surfaces
We show that semi-arithmetic surfaces of arithmetic dimension two which admit a modular embedding have exponential growth of mean multiplicities in their length spectrum. Prior to this work large mean multiplicities were rigorously confirmed only for the length spectra of arithmetic surfaces. We also discuss the relation of the degeneracies in the length spectrum and quantization of the Hamiltonian mechanical system on the surface.

Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
Petra Baran\v{c}\'ikov\'a, Ond\v{r}ej Bojar
https://arxiv.org/abs/2506.20203

Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several Semantic Textual Similarity (STS) benchmarks to assess the ability of the embeddings to capture linguistic phenomena such as semantic similarity, temporal aspects, and stylistic variations. In the extrinsic evaluation, we fine-tune each embedding model using COM…

SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
Julien Guinot, Alain Riou, Elio Quinton, Gy\"orgy Fazekas
https://arxiv.org/abs/2506.17815

SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches face large memory requirement limitations due to relying on large batch sizes to effectively utilize negative samples. Further, multimodal joint embedding spaces suffer from a modality gap wherein embeddings from different modalities lie in different manifolds of the embedding space. To address these challenges, we pro…

DV365: Extremely Long User History Modeling at Instagram
Wenhan Lyu, Devashish Tyagi, Yihang Yang, Ziwei Li, Ajay Somani, Karthikeyan Shanmugasundaram, Nikola Andrejevic, Ferdi Adeputra, Curtis Zeng, Arun K. Singh, Maxime Ransan, Sagar Jain
https://arxiv.org/abs/2506.00450

DV365: Extremely Long User History Modeling at Instagram
Long user history is highly valuable signal for recommendation systems, but effectively incorporating it often comes with high cost in terms of data center power consumption and GPU. In this work, we chose offline embedding over end-to-end sequence length optimization methods to enable extremely long user sequence modeling as a cost-effective solution, and propose a new user embedding learning strategy, multi-slicing and summarization, that generates highly generalizable user representation of …

This https://arxiv.org/abs/2410.08902 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Residual finiteness of some automorphism groups of high dimensional manifolds
We show that for a smooth, closed 2-connected manifold $M$ of dimension $d \geq 6$, the topological mapping class group $π_0 \mathrm{Homeo}(M)$ is residually finite, in contrast to the situation for the smooth mapping class group $π_0 \mathrm{Diff}(M)$. Combined with a result of Sullivan, this implies that $π_0 \mathrm{Homeo}(M)$ is an arithmetic group. The proof uses embedding calculus, and is of independent interest: we show that the $T_k$-mapping class group, $π_0 T_k \mathrm{Diff}(M)$, …

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
Mohna Chakraborty, Adithya Kulkarni, Qi Li
https://arxiv.org/abs/2507.00330

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection, particularly in cold-start settings with no labeled data. Existing studies overlook the dependency between instances and verbalizers, where instance-label probabilities depend on verbalizer token proximity in the embedding space. To address this, we propose COLDSEL…

Efficient Blockchain-based Steganography via Backcalculating Generative Adversarial Network
Zhuo Chen, Jialing He, Jiacheng Wang, Zehui Xiong, Tao Xiang, Liehuang Zhu, Dusit Niyato
https://arxiv.org/abs/2506.16023

Efficient Blockchain-based Steganography via Backcalculating Generative Adversarial Network
Blockchain-based steganography enables data hiding via encoding the covert data into a specific blockchain transaction field. However, previous works focus on the specific field-embedding methods while lacking a consideration on required field-generation embedding. In this paper, we propose a generic blockchain-based steganography framework (GBSF). The sender generates the required fields such as amount and fees, where the additional covert data is embedded to enhance the channel capacity. Base…

This https://arxiv.org/abs/2504.10545 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
Recent advances in recommender systems have underscored the complementary strengths of generative modeling and pretrained language models. We propose HSTU-BLaIR, a hybrid framework that augments the Hierarchical Sequential Transduction Unit (HSTU)-based generative recommender with BLaIR, a lightweight contrastive text embedding model. This integration enriches item representations with semantic signals from textual metadata while preserving HSTU's powerful sequence modeling capabilities. We e…

DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
Xueyuan Chen, Dongchao Yang, Wenxuan Wu, Minglin Wu, Jing Xu, Xixin Wu, Zhiyong Wu, Helen Meng
https://arxiv.org/abs/2506.00350

DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility and poor speaker similarity. In this study, we introduce a novel diffusion-based DSR system that leverages a latent diffusion model to enhance the quality of speech reconstruction. Our model comprises: (i) a speech content encoder for phoneme embedding restor…

A topologically extendible mapping class that is not smoothly extendible
Shital Lawande, Kuldeep Saha
https://arxiv.org/abs/2505.23999 https://

A topologically extendible mapping class that is not smoothly extendible
We give an example of a smooth characteristic embedding of a torus in $\s^2 \times \s^2 \# \s^1 \times \s^3$ such that there exists no diffeomorphism of the ambient $4$-manifold that induces the Dehn twist along a meridian of the torus, but there exists a homeomorphism of the ambient $4$-manifold, isotopic to identity, that induces the Dehn twist. As an application of our methods, we provide examples of two proper smooth embeddings of an annulus in $\s^2 \times \s^2 \# \s^1 \times \s^3 \setminu…

Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
Max Conti, Manuel Faysse, Gautier Viaud, Antoine Bosselut, C\'eline Hudelot, Pierre Colombo
https://arxiv.org/abs/2505.24782

Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations. In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-t…

This https://arxiv.org/abs/2411.06426 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks mainly rely on scenario camouflage, prompt obfuscation, prompt optimization, and prompt iterative optimization to conceal malicious prompts. In particular, sequential prompt chains in a single query can lead LLMs to …

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Zhibo Fan, Hongtao Lin, Haoyu Chen, Bowen Deng, Hedi Xia, Yuke Yan, James Li
https://arxiv.org/abs/2506.23060

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range of diverse user interests. Effectively covering the diverse and long-tail user interests within this stage poses a significant challenge: traditional two-tower models struggle in this regard due to limited user-item feature interaction and often bias towards t…

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Chenchen Yuan, Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci
https://arxiv.org/abs/2506.14625

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability,…

LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
Yingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma, Tat-Seng Chua
https://arxiv.org/abs/2506.21579

LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items. Traditional sequential recommenders predominantly rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns. However, these embeddings depend solely on past interactions, lacking transferable knowledge to generalize to unseen domains. Recent advances in large language models (LLMs) have mo…

NEAR$^2$: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
Shenbin Qian, Diptesh Kanojia, Samarth Agrawal, Hadeel Saadany, Swapnil Bhosale, Constantin Orasan, Zhe Wu
https://arxiv.org/abs/2506.19743

NEAR$^2$: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching user intent with relevant products while managing the computational demands of real-time search across massive inventories. In this paper, we propose a Nested Embedding Approach to product Retrieval and Ranking, called NEAR$^2$, which can achieve up to $12$ tim…

This https://arxiv.org/abs/2505.11582 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents
Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed and predictive accuracy. This is often achieved through neural methods that aim to learn language semantics. However, our results suggest that these are not always the best solution. Our task was to classify rigidly-structured medical documents according to t…

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
Arjun Rao, Hanieh Alipour, Nick Pendar
https://arxiv.org/abs/2506.00049

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
This paper presents a comparison of embedding models in tri-modal hybrid retrieval for Retrieval-Augmented Generation (RAG) systems. We investigate the fusion of dense semantic, sparse lexical, and graph-based embeddings, focusing on the performance of the MiniLM-v6 and BGE-Large architectures. Contrary to conventional assumptions, our results show that the compact MiniLM-v6 outperforms the larger BGE-Large when integrated with LLM-based re-ranking within our tri-modal hybrid framework. Experim…

This https://arxiv.org/abs/2412.19302 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

RecLM: Recommendation Instruction Tuning
Modern recommender systems aim to deeply understand users' complex preferences through their past interactions. While deep collaborative filtering approaches using Graph Neural Networks (GNNs) excel at capturing user-item relationships, their effectiveness is limited when handling sparse data or zero-shot scenarios, primarily due to constraints in ID-based embedding functions. To address these challenges, we propose a model-agnostic recommendation instruction-tuning paradigm that seamlessly int…

Rule-Assisted Attribute Embedding
Sibo Zhao, Michael Bewong, Selasi Kwashie, Junwei Hu, Zaiwen Feng
https://arxiv.org/abs/2506.08314 https://

Rule-Assisted Attribute Embedding
Recommendation systems often overlook the rich attribute information embedded in property graphs, limiting their effectiveness. Existing graph convolutional network (GCN) models either ignore attributes or rely on simplistic triples, failing to capture deeper semantic structures. We propose RAE (Rule- Assisted Approach for Attribute Embedding), a novel method that improves recommendations by mining semantic rules from property graphs to guide attribute embedding. RAE per…