Tootfinder

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…

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…

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…

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…

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-…

Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors
Patrick Iff, Paul Bruegger, Marcin Chrapek, Maciej Besta, Torsten Hoefler
https://arxiv.org/abs/2507.21989

Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors
Advances in embedding models for text, image, audio, and video drive progress across multiple domains, including retrieval-augmented generation, recommendation systems, vehicle/person reidentification, and face recognition. Many applications in these domains require an efficient method to retrieve items that are close to a given query in the embedding space while satisfying a filter condition based on the item's attributes, a problem known as Filtered Approximate Nearest Neighbor Search (FANNS)…

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform
Justin Curry, Brennan Lagasse, Ngoc B. Lam, Gregory Cox, David Rosenbluth, Alberto Speranzon
https://arxiv.org/abs/2507.22010

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform
In this work, we explore the structure of the embedding space of a transformer model trained for playing a particular reinforcement learning (RL) game. Specifically, we investigate how a transformer-based Proximal Policy Optimization (PPO) model embeds visual inputs in a simple environment where an agent must collect "coins" while avoiding dynamic obstacles consisting of "spotlights." By adapting Robinson et al.'s study of the volume growth transform for LLMs to the RL setting, we find that the…

Representations in vision and language converge in a shared, multidimensional space of perceived similarities
Katerina Marie Simkova, Adrien Doerig, Clayton Hickey, Ian Charest
https://arxiv.org/abs/2507.21871

Representations in vision and language converge in a shared, multidimensional space of perceived similarities
Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and language are well predicted by semantic feature spaces obtained from large language models (LLMs). This raises the possibility that sensory systems converge in their inherent ability to transform their inputs onto shared, embedding-like representational space. …

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

Linear codes arising from the point-hyperplane geometry -- Part II: the twisted embedding
Ilaria Cardinali, Luca Giuzzi
https://arxiv.org/abs/2507.16694 ht…

Linear codes arising from the point-hyperplane geometry -- Part II: the twisted embedding
Let $\barΓ$ be the point-hyperplane geometry of a projective space $\mathrm{PG(V)},$ where $V$ is a $(n+1)$-dimensional vector space over a finite field $\mathbb{F}_q$ of order $q.$ Suppose that $σ$ is an automorphism of $\mathbb{F}_q$ and consider the projective embedding $\varepsilon_σ$ of $\barΓ$ into the projective space $\mathrm{PG}(V\otimes V^*)$ mapping the point $([x],[ξ])\in \barΓ$ to the projective point represented by the pure tensor $x^σ\otimes ξ$, with $ξ(x)=0.$ In [I. Car…

Attributes Shape the Embedding Space of Face Recognition Models
Pierrick Leroy, Antonio Mastropietro, Marco Nurisso, Francesco Vaccarino
https://arxiv.org/abs/2507.11372

Attributes Shape the Embedding Space of Face Recognition Models
Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast). We propose a …

A remark on equivariant Riemannian isometric embeddings preserving symmetries
Dmitri Burago, Hongda Qiu
https://arxiv.org/abs/2507.23164 https://arxiv.org/…

A remark on equivariant Riemannian isometric embeddings preserving symmetries
This remark pertains to isometric embeddings endowed with certain geometric properties. We study two embeddings problems for the universal cover $M$ of an $n$-dimensional Riemannian torus $(\TT^n,g)$. The first concerns the existence of an isometric embedding of $M$ into a bounded subset of some Euclidean space $\RR^{D_1}$, and the second one seeks an isometric embdding of $M$ that is equivariant with respect to the deck transformation group of covering map. By using a known trick in a novel wa…

Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
Xinyuan Yan, Rita Sevastjanova, Sinie van der Ben, Mennatallah El-Assady, Bei Wang
https://arxiv.org/abs/2507.18607

Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the topological structures of LLM embedding spaces via mapper graphs enables us to understand their underlying structures. Specifically, a mapper graph summarizes the topological structure of the embedding space, where each node represents a topological neighborhood (containing a cluster of embeddings), and an edge connects…

This https://arxiv.org/abs/2406.10065 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

An Extended Validity Domain for Constraint Learning
We consider embedding a predictive machine-learning model within a prescriptive optimization problem. In this setting, called constraint learning, we study the concept of a validity domain, i.e., a constraint added to the feasible set, which keeps the optimization close to the training data, thus helping to ensure that the computed optimal solution exhibits less prediction error. In particular, we propose a new validity domain which uses a standard convex-hull idea but in an extended space. We …

Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
Ruiqi He, Zekun Fei, Jiaqi Li, Xinyuan Zhu, Biao Yi, Siyi Lv, Weijie Liu, Zheli Liu
https://arxiv.org/abs/2507.18518

Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
Vector Database (VDB) can efficiently index and search high-dimensional vector embeddings from unstructured data, crucially enabling fast semantic similarity search essential for modern AI applications like generative AI and recommendation systems. Since current VDB service providers predominantly use proprietary black-box models, users are forced to expose raw query text to them via API in exchange for the vector retrieval services. Consequently, if query text involves confidential records fro…

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…

The CompGIT package: a computational tool for Geometric Invariant Theory quotie
Robert Hanson, Jesus Martinez-Garcia
https://arxiv.org/abs/2506.19431 https…

The CompGIT package: a computational tool for Geometric Invariant Theory quotie
We describe CompGIT, a SageMath package to describe Geometric Invariant Theory (GIT) quotients of projective space by simple groups. The implementation is based on algorithms described by Gallardo--Martinez-Garcia--Moon--Swinarski. In principle the package is sufficient to describe any GIT quotient of a projective variety by a simple group -- in practice it requires that the user can construct an equivariant embedding of the polarised variety into projective space. The package describes the non…

Mixture of Encoders is a vector-native alternative that models both structured and unstructured data in a unified embedding space. Join Filip Makraduli as he introduces the method, demonstrates how it powers natural language search and real-time recommendations, and shares open-source tools and benchmarks for replacing complex hybrid stacks.
Learn more:

Koopman Operator Based Time-Delay Embeddings and State History Augmented LQR for Periodic Hybrid Systems: Bouncing Pendulum and Bipedal Walking
Chun-Ming Yang, Pranav A. Bhounsule
https://arxiv.org/abs/2507.14455

Koopman Operator Based Time-Delay Embeddings and State History Augmented LQR for Periodic Hybrid Systems: Bouncing Pendulum and Bipedal Walking
Time-delay embedding is a technique that uses snapshots of state history over time to build a linear state space model of a nonlinear smooth system. We demonstrate that periodic non-smooth or hybrid system can also be modeled as a linear state space system using this approach as long as its behavior is consistent in modes and timings. We extended time-delay embeddings to generate a linear model of two periodic hybrid systems: the bouncing pendulum and the simplest walker with control inputs. Th…

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…

On Geometrization of Classical Fields II (MES: dark matter, energy)
V. I. Noskov
https://arxiv.org/abs/2506.14313 https://arxiv.org/p…

On Geometrization of Classical Fields II (MES: dark matter, energy)
The study of arXiv:2502.01174 geometrization of classical fields in the 4d--Finsler space of MES (Model of Embedded Spaces) is continued. The model postulates a proper metric set of a distributed matter element and states that the space-time of the Universe is a physical Embedding of such sets. The Embedding geometry is a Finsler-like relativistic geometry with connectivity depending on the mechanical state of matter: torsion and non-metricity are absent. The Least Action Principle provides the…

This https://arxiv.org/abs/2406.10065 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

An Extended Validity Domain for Constraint Learning
We consider embedding a predictive machine-learning model within a prescriptive optimization problem. In this setting, called constraint learning, we study the concept of a validity domain, i.e., a constraint added to the feasible set, which keeps the optimization close to the training data, thus helping to ensure that the computed optimal solution exhibits less prediction error. In particular, we propose a new validity domain which uses a standard convex-hull idea but in an extended space. We …

A sequence of compact metric spaces and an isometric embedding into the Gromov-Hausdorff space
Takuma Byakuno
https://arxiv.org/abs/2507.07449 https://

A sequence of compact metric spaces and an isometric embedding into the Gromov-Hausdorff space
For a convergent series with positive terms, we prove that the $\ell^\infty$ product space of bounded subspaces of the Gromov-Hausdorff space can be isometrically embedded into the Gromov-Hausdorff space, where each subspace consists of compact metric spaces with the diameter less than or equal to the term.

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/5]:
- TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
Bingheng Wu, Jingze Shi, Yifan Wu, Nan Tang, Yuyu Luo

Symbolic Generation and Modular Embedding of High-Quality abc-Triples
Michael A. Idowu
https://arxiv.org/abs/2506.10039 https://arxiv…

Symbolic Generation and Modular Embedding of High-Quality abc-Triples
We present a symbolic identity for generating integer triples $(a, b, c)$ satisfying $a + b = c$, inspired by structural features of the \emph{abc conjecture}. The construction uses powers of $2$ and $3$ in combination with modular inversion in $\mathbb{Z}/3^p\mathbb{Z}$, leading to a parametric identity with residue constraints that yield abc-triples exhibiting low radical values. Through affine transformations, these symbolic triples are embedded into a broader space of high-quality examples,…

Observational Space Unveils Cosmic Expansion's Role in the Hubble Tension
Kang Jiao, Tong-Jie Zhang, Liang Gao
https://arxiv.org/abs/2506.16669 https:/…

Observational Space Unveils Cosmic Expansion's Role in the Hubble Tension
We introduce a geometric embedding method that directly constrains $H_0$ by exploiting the exact kinematic relation $\dot{z} = H_0(1+z) - H(z)$ in a unified observational framework. This approach reconstructs expansion history without requiring specific cosmological models, incorporating both existing Cosmic Chronometer data and forecasted Sandage-Loeb measurements. Through mathematical embedding of observational constraints, we achieve $\sim 1.6\%$ precision in $H_0$ determination, matching cu…

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim
https://arxiv.org/abs/2507.18632 https://

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing studies utilize CLIP's embedding space and text description to simulate target-like style features. Despite the previous achievements in zero-shot domain adaptation, we observe that these text-driven methods struggle to capture complex real-world variations and significantly increase adaptation time due to their alignmen…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[9/11]:
- Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space...
Yuri Kuratov, Mikhail Arkhipov, Aydar Bulatov, Mikhail Burtsev

Interpreting CFD Surrogates through Sparse Autoencoders
Yeping Hu, Shusen Liu
https://arxiv.org/abs/2507.16069 https://arxiv.org/pdf/2507.16069

Interpreting CFD Surrogates through Sparse Autoencoders
Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This work introduces a posthoc interpretability framework for graph-based surrogate models used in computational fluid dynamics (CFD) by leveraging sparse autoencoders (SAEs). By obtaining an overcomplete basis in the node embedding space of a pretrained surrogate, the method extracts…

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…

Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
Yimian Ding, Jingzehua Xu, Guanwen Xie, Shuai Zhang, Yi Li
https://arxiv.org/abs/2506.15082

Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL architectures, the proposed framework integrates an environment-aware network module that dynamically captures flow field data, effectively embedding this critical environmental information into the state space. This integration facilitates real-time environmental ad…

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
Julian Herreilers, Christiaan Jacobs, Thomas Niesler
https://arxiv.org/abs/2506.17690

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransformer, an encoder-only model, directly optimises the embedding space using normalised temperature-scaled cross entropy (NT-Xent) loss. We use this model to perform keyword spotting for radio broadcasts in Luganda and Bambara, the latter a severely under-resourced language. We compare our model to various existing AWE a…

Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
Y. Du
https://arxiv.org/abs/2507.05933 https:…

Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization robustness and neighborhood density metrics. Our approach is motivated by the observation that high-quality embeddings occupy geometrically stable regions in the embedding space and exhibit consistent neighborhood structures. We evaluate our method on 4 standar…

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
Matt Poyser, Toby P. Breckon
https://arxiv.org/abs/2506.14667

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image wit…

This https://arxiv.org/abs/2411.14464 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

JESTR: Joint Embedding Space Technique for Ranking Candidate Molecules for the Annotation of Untargeted Metabolomics Data
Motivation: A major challenge in metabolomics is annotation: assigning molecular structures to mass spectral fragmentation patterns. Despite recent advances in molecule-to-spectra and in spectra-to-molecular fingerprint prediction (FP), annotation rates remain low. Results: We introduce in this paper a novel paradigm (JESTR) for annotation. Unlike prior approaches that explicitly construct molecular fingerprints or spectra, JESTR leverages the insight that molecules and their corresponding spec…

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.

The Geometric P=W conjecture and Thurston's compactification
Ashwin Ayilliath-Kutteri, Mohammad Farajzadeh-Tehrani, Charles Frohman
https://arxiv.org/abs/2507.07211

The Geometric P=W conjecture and Thurston's compactification
In this paper, we derive an explicit formula for a well-known embedding of the set of isotopy classes of multicurves on a closed surface of genus $g$ into $\mathbb{N}^{9g - 9}$. More significantly, we relate this result and established facts about Thurston's compactification of Teichmüller space to the geometric P = W conjecture for $\tn{SL}(2,\C)$, which concerns projective compactifications of character varieties of closed surfaces. In particular, we construct a projective compactification o…

SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
Marc Brinner, Sina Zarriess
https://arxiv.org/abs/2507.13105

SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific abstracts to train a model that positions semantically related summaries closer together in the embedding space. This resulting objective ensures that the model captures the true semantic content of a text, in contrast to traditional citation-based approaches that do…

Fast Geometric Embedding for Node Influence Maximization
Alexander Kolpakov, Igor Rivin
https://arxiv.org/abs/2506.07435 https://arxi…

Fast Geometric Embedding for Node Influence Maximization
Computing classical centrality measures such as betweenness and closeness is computationally expensive on large-scale graphs. In this work, we introduce an efficient force layout algorithm that embeds a graph into a low-dimensional space, where the radial distance from the origin serves as a proxy for various centrality measures. We evaluate our method on multiple graph families and demonstrate strong correlations with degree, PageRank, and paths-based centralities. As an application, it turns …

Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
Rachna Saxena, Abhijeet Kumar, Suresh Shanmugam
https://arxiv.org/abs/2507.12378

Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
Traditional information extraction systems face challenges with text only language models as it does not consider infographics (visual elements of information) such as tables, charts, images etc. often used to convey complex information to readers. Multimodal LLM (MLLM) face challenges of finding needle in the haystack problem i.e., either longer context length or substantial number of documents as search space. Late interaction mechanism over visual language models has shown state of the art p…

On the Gromov--Hausdorff stability of metric viscosity solutions
Shimpei Makida
https://arxiv.org/abs/2507.06495 https://arxiv.org/pdf/2507.06495 https://arxiv.org/html/2507.06495
arXiv:2507.06495v1 Announce Type: new
Abstract: We establish the stability of metric viscosity solutions to first-order Hamilton--Jacobi equations under Gromov--Hausdorff convergence. Our proof combines a characterization of metric viscosity solutions via quadratic distance functions with a doubling variable method adapted to epsilon-isometries, which allows us to pass to the Gromov--Hausdorff limit without embedding the spaces into a common ambient space. As a byproduct, we give a PDE-based proof of the stability of the dual Kantorovich problems under measured-Gromov--Hausdorff convergence.
toXiv_bot_toot

The Intrinsic Riemannian Proximal Gradient Method for Convex Optimization
Ronny Bergmann, Hajg Jasa, Paula John, Max Pfeffer
https://arxiv.org/abs/2507.16055

The Intrinsic Riemannian Proximal Gradient Method for Convex Optimization
We consider a class of (possibly strongly) geodesically convex optimization problems on Hadamard manifolds, where the objective function splits into the sum of a smooth and a possibly nonsmooth function. We introduce an intrinsic convex Riemannian proximal gradient (CRPG) method that employs the manifold proximal map for the nonsmooth step, without operating in the embedding or tangent space. A sublinear convergence rate for convex problems and a linear convergence rate for strongly convex prob…

TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search
Harsha Kokel, Aamod Khatiwada, Tejaswini Pedapati, Haritha Ananthakrishnan, Oktie Hassanzadeh, Horst Samulowitz, Kavitha Srinivas
https://arxiv.org/abs/2507.11505

TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search
One of the major challenges in enterprise data analysis is the task of finding joinable tables that are conceptually related and provide meaningful insights. Traditionally, joinable tables have been discovered through a search for similar columns, where two columns are considered similar syntactically if there is a set overlap or they are considered similar semantically if either the column embeddings or value embeddings are closer in the embedding space. However, for enterprise data lakes, col…

Smooth manifolds in $G_{n,2}$ and $\mathbb{C} P^{N}$ defined by symplectic reductions of $T^n$-action
Victor M. Buchstaber, Svjetlana Terzi\'c
https://arxiv.org/abs/2507.04582

Smooth manifolds in $G_{n,2}$ and $\mathbb{C} P^{N}$ defined by symplectic reductions of $T^n$-action
Plücker coordinates define the $T^n$-equivariant embedding $p : G_{n,2}\to \mathbb{C} P^{N}$ of a complex Grassmann manifold $G_{n,2}$ into the complex projective space $\mathbb{C} P^{N}$, $N=\binom{n}{2}-1$ for the canonical $T^n$-action on $G_{n,2}$ and the $T^n$-action on $\mathbb{C} P^{N}$ given by the second symmetric power representation $T^n\to T^{N}$ and the standard $T^{N}$-action. Let $μ: G_{n,2}\to Δ_{n,2}\subset \mathbb{R} ^{n}$ and $\tildeμ: \mathbb{C} P^{N}\to Δ_{n,2}\subset …

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…