Tootfinder

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.

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…

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…

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…

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…

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-…

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…

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 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…

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…

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 …

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:

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…

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…

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,…

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

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 …

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…

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…

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

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…

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 …