Tootfinder

MSRS: Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
Xinyan Jiang, Lin Zhang, Jiayi Zhang, Qingsong Yang, Guimin Hu, Di Wang, Lijie Hu
https://arxiv.org/abs/2508.10599

MSRS: Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
Activation steering offers a promising approach to controlling the behavior of Large Language Models by directly manipulating their internal activations. However, most existing methods struggle to jointly steer multiple attributes, often resulting in interference and undesirable trade-offs. To address this challenge, we propose Multi-Subspace Representation Steering (MSRS), a novel framework for effective multi-attribute steering via subspace representation fine-tuning. MSRS reduces inter-attri…

LayerLock: Non-collapsing Representation Learning with Progressive Freezing
Goker Erdogan, Nikhil Parthasarathy, Catalin Ionescu, Drew Hudson, Alexander Lerchner, Andrew Zisserman, Mehdi Sajjadi, Joao Carreira
https://arxiv.org/abs/2509.10156

LayerLock: Non-collapsing Representation Learning with Progressive Freezing
We introduce LayerLock, a simple yet effective approach for self-supervised visual representation learning, that gradually transitions from pixel to latent prediction through progressive layer freezing. First, we make the observation that during training of video masked-autoencoding (MAE) models, ViT layers converge in the order of their depth: shallower layers converge early, deeper layers converge late. We then show that this observation can be exploited to accelerate standard MAE by progress…

How the US democracy is designed to avoid representation
Right now in the US, a system which proclaims to give each citizen representation, my interests are not represented very well by most of my so-called representatives at any level of government. This is true for a majority of Americans across the political spectrum, and it happens by design. The "founding fathers" were explicit about wanting a system of government that would appear Democratic but which would keep power in the hands of rich white landowners, and they successfully designed exactly that. But how does disenfranchisement work in this system?
First, a two-party system locked in by first-post-the-post winner-takes-all elections immediately destroys representation for everyone who didn't vote for the winner, including those who didn't vote or weren't eligible to vote. Single-day non-holiday elections and prisoner disenfranchisement go a long way towards ensuring working-class people get no say, but much larger is the winner-takes all system. In fact, even people who vote for the winning candidate don't get effective representation if they're really just voting against the opponent as the greater of two evils. In a 51/49 election with 50% turnout, you've immediately ensured that ~75% of eligible voters don't get represented, and with lesser-of-two-evils voting, you create an even wider gap to wedge corporate interests into. Politicians need money to saturate their lesser-of-two-evils message far more than they need to convince any individual voter to support their policies. It's even okay if they get caught lying, cheating, or worse (cough Epstein cough) as long as the other side is also doing those things and you can freeze out new parties.
Second, by design the Senate ensures uneven representation, allowing control of the least-populous half of states to control or at least shut down the legislative process. A rough count suggests 284.6 million live in the 25 most-populous states, while only 54.8 million live in the rest. Currently, counting states with divided representation as two half-states with half as much population, 157.8 million people are represented by 53 Republican sensors, while 180.5 million people get only 45 seats of Democratic representation. This isn't an anti-Democrat bias, it's a bias towards less-populous states, whose residents get more than their share it political power.
I haven't even talked about gerrymandering yet, or family/faith-based "party loyalty," etc. Overall, the effect is that the number of people whose elected representatives meaningfully represent their interests on any given issue is vanishingly small (like, 10% of people tops), unless you happen to be rich enough to purchase lobbying power or direct access.
If we look at polls, we can see how lack of representation lets congress & the president enact many policies that go against what a majority of the population wants. Things like abortion restrictions, the current ICE raids, and Medicare cuts are deeply unpopular, but they benefit the political class and those who can buy access. These are possible because the system ensures at every step of the way that ordinary people do NOT get the one thing the system promises them: representation in the halls of power.
Okay, but is this a feature of all democracies, inherent in the nature of a majority-decides system? Not exactly...
1/2
#uspol #democracy

Sparse Coding Representation of 2-way Data
Boya Ma, Abram Magner, Maxwell McNeil, Petko Bogdanov
https://arxiv.org/abs/2509.10033 https://arxiv.org/pdf/250…

Sparse Coding Representation of 2-way Data
Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial dictionaries. Data-agnostic analytical dictionaries, such as the discrete Fourier transform, wavelets and graph Fourier, have seen wide adoption due to efficient implementations and good practical performance. On the other hand, dictionaries learned from data offer spar…

Efficient Image Denoising Using Global and Local Circulant Representation
Zhaoming Kong, Jiahuan Zhang, Xiaowei Yang
https://arxiv.org/abs/2508.10307 https://

Efficient Image Denoising Using Global and Local Circulant Representation
The advancement of imaging devices and countless image data generated everyday impose an increasingly high demand on efficient and effective image denoising. In this paper, we present a computationally simple denoising algorithm, termed Haar-tSVD, aiming to explore the nonlocal self-similarity prior and leverage the connection between principal component analysis (PCA) and the Haar transform under circulant representation. We show that global and local patch correlations can be effectively capt…

GundamQ: Multi-Scale Spatio-Temporal Representation Learning for Robust Robot Path Planning
Yutong Shen, Ruizhe Xia, Bokai Yan, Shunqi zhang, Pengrui Xiang, Sicheng He, Yixin Xu
https://arxiv.org/abs/2509.10305

GundamQ: Multi-Scale Spatio-Temporal Representation Learning for Robust Robot Path Planning
In dynamic and uncertain environments, robotic path planning demands accurate spatiotemporal environment understanding combined with robust decision-making under partial observability. However, current deep reinforcement learning-based path planning methods face two fundamental limitations: (1) insufficient modeling of multi-scale temporal dependencies, resulting in suboptimal adaptability in dynamic scenarios, and (2) inefficient exploration-exploitation balance, leading to degraded path quali…

Access graph: a novel graph representation of public transport networks for accessibility analysis
Tina \v{S}filigoj, Aljo\v{s}a Peperko, Oded Cats
https://arxiv.org/abs/2507.08361

Access graph: a novel graph representation of public transport networks for accessibility analysis
Accessibility, defined as travel impedance between spatially dispersed opportunities for activity, is one of the main determinants of public transport (PT) use. In-depth understanding of its properties is crucial for optimal public transport systems planning and design. Although the concept has been around for decades and there is a large body of literature on accessibility operationalisation and measurement, a unified approach is lacking. To this end, we introduce a novel graph representation …

The affine Brylinski filtration and $\mathscr{W}$-algebras
Suresh Govindarajan, Sachin S. Sharma, Sankaran Viswanath
https://arxiv.org/abs/2508.10365 https://

The affine Brylinski filtration and $\mathscr{W}$-algebras
The Brylinski-Kostant filtration on a representation of a finite-dimensional semisimple Lie algebra has interpretations in terms of the algebra, geometry and combinatorics of the representation. Its extension to affine Lie algebras was first studied by Slofstra. Recent work of the present authors constructed a Poincaré-Birkhoff-Witt type basis for the dominant weight spaces of the basic representation of affine Lie algebras of type $A$, which is compatible with the affine Brylinski filtration.…

Bertrand's Representation of the Optimal Detector
Vladimir Lenok
https://arxiv.org/abs/2509.10198 https://arxiv.org/pdf/2509.10198

Bertrand's Representation of the Optimal Detector
It is shown how the optimal detector of Gaussian signals can be represented in terms of Bertrand's class of time-frequency distributions. In this representation, the detector is a correlation between the corresponding time-frequency distributions. Since Bertrand's class is related to the power-law chirp signals, the new representation can be useful for their detection. The new approach is shown to be more effective then other time-frequency methods for the case of phase-insensitive detection. T…

The decline of representation in our representative democracy (pbump)
https://www.pbump.net/o/the-decline-of-representation-in-our-representative-democracy/
http://www.memeorandum.com/250813/p70#a250813p70

Hypercomplex Prompt-aware Multimodal Recommendation
Zheyu Chen, Jinfeng Xu, Hewei Wang, Shuo Yang, Zitong Wan, Haibo Hu
https://arxiv.org/abs/2508.10753 https://

Hypercomplex Prompt-aware Multimodal Recommendation
Modern recommender systems face critical challenges in handling information overload while addressing the inherent limitations of multimodal representation learning. Existing methods suffer from three fundamental limitations: (1) restricted ability to represent rich multimodal features through a single representation, (2) existing linear modality fusion strategies ignore the deep nonlinear correlations between modalities, and (3) static optimization methods failing to dynamically mitigate the o…

Writer Stephanie Wambugu on speaking across generations
#creativity
https://

Writer Stephanie Wambugu on speaking across generations – The Creative Independent
Writer Stephanie Wambugu discusses the conflict of art-world representation, acting as a vessel of human emotion, and resisting trend forecasting.

Improving gravitational wave search sensitivity with TIER: Trigger Inference using Extended strain Representation
Digvijay Wadekar, Arush Pimpalkar, Mark Ho-Yeuk Cheung, Benjamin Wandelt, Emanuele Berti, Ajit Kumar Mehta, Tejaswi Venumadhav, Javier Roulet, Tousif Islam, Barak Zackay, Jonathan Mushkin, Matias Zaldarriaga
https://…

Improving gravitational wave search sensitivity with TIER: Trigger Inference using Extended strain Representation
We introduce a machine learning (ML) framework called $\texttt{TIER}$ for improving the sensitivity of gravitational wave search pipelines. Typically, search pipelines only use a small region of strain data in the vicinity of a candidate signal to construct the detection statistic. However, extended strain data ($\sim 10$ s) in the candidate's vicinity can also carry valuable complementary information. We show that this information can be efficiently captured by ML classifier models trained on …

Axis-level Symmetry Detection with Group-Equivariant Representation
Wongyun Yu, Ahyun Seo, Minsu Cho
https://arxiv.org/abs/2508.10740 https://arxiv.org/pdf…

Axis-level Symmetry Detection with Group-Equivariant Representation
Symmetry is a fundamental concept that has been extensively studied, yet detecting it in complex scenes remains a significant challenge in computer vision. Recent heatmap-based approaches can localize potential regions of symmetry axes but often lack precision in identifying individual axes. In this work, we propose a novel framework for axis-level detection of the two most common symmetry types-reflection and rotation-by representing them as explicit geometric primitives, i.e. lines and points…

Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation
In-Chang Baek, Seoyoung Lee, Sung-Hyun Kim, Geumhwan Hwang, KyungJoong Kim
https://arxiv.org/abs/2508.09860

Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation
Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation. This direction is especially relevant in procedural content generation via reinforcement learning (PCGRL), which is intended to serve as a tool for human designers. However, existing systems often fall short of exhibiting human-centered behavior, limiting the practical utility of AI-…

On the fully analytical cumulative distribution of product of correlated Gaussian random Variables with zero means
Erdinc Akyildirim, Alper Hekimoglu
https://arxiv.org/abs/2509.09866

On the fully analytical cumulative distribution of product of correlated Gaussian random Variables with zero means
We derive a fully analytical, one-line closed-form expression for the cumulative distribution function (CDF) of the product of two correlated zero-mean normal random variables, avoiding any series representation. This result complements the well-known compact density formula with an equally compact and computationally practical CDF representation. Our main formula expresses the CDF in terms of Humbert's confluent hypergeometric function $Φ_1$ and modified Bessel functions $K_ν$, offering both…

Existence of Richter-Peleg Representation for General Preferences
Leandro Gorno, Paulo Klinger Monteiro
https://arxiv.org/abs/2508.08980 https://arxiv.org/…

Existence of Richter-Peleg Representation for General Preferences
This paper provides a general characterization of preferences that admit a Richter-Peleg representation without imposing completeness or transitivity. We establish that a binary relation on a nonempty set admits a Richter-Peleg representation if and only if it is "strongly acyclic" and its transitive closure is "separable". Strong acyclicity rules out problematic cycles among indifference classes, while separability limits the structural complexity of the relation. Our main result has two signi…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/3]:
- Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
Pegah Khayatan, Mustafa Shukor, Jayneel Parekh, Arnaud Dapogny, Matthieu Cord

A pseudo-inverse of a line graph
Sevvandi Kandanaarachchi, Philip Kilby, Cheng Soon Ong
https://arxiv.org/abs/2508.09412 https://arxiv.org/pdf/2508.09412…

A pseudo-inverse of a line graph
Line graphs are an alternative representation of graphs where each vertex of the original (root) graph becomes an edge. However not all graphs have a corresponding root graph, hence the transformation from graphs to line graphs is not invertible. We investigate the case when there is a small perturbation in the space of line graphs, and try to recover the corresponding root graph, essentially defining the inverse of the line graph operation. We propose a linear integer program that edits the sm…

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- CRDT Emulation, Simulation, and Representation Independence
Nathan Liittschwager, Jonathan Castello, Stelios Tsampas, Lindsey Kuper

Bayesian Interpretation of Husimi Function and Wehrl Entropy
Chen Xu, Yiqi Yu, Peng Zhang
https://arxiv.org/abs/2507.08600 https://ar…

Bayesian Interpretation of Husimi Function and Wehrl Entropy
Husimi function (Q-function) of a quantum state is the distribution function of the density operator in the coherent state representation. It is widely used in theoretical research, such as in quantum optics. The Wehrl entropy is the Shannon entropy of the Husimi function, and is non-zero even for pure states. This entropy has been extensively studied in mathematical physics. Recent research also suggests a significant connection between the Wehrl entropy and many-body quantum entanglement in s…

Random Sperner lemma and random Brouwer fixed point theorem
Qiang Tu, Xiaohuan Mu, Tiexin Guo, Goong Chen
https://arxiv.org/abs/2507.08521 https://

Random Sperner lemma and random Brouwer fixed point theorem
In this paper, we systematically develop the theory of $L^{0}$-simplicial subdivisions of $L^{0}$-simplexes by grasping the inherent connection between $L^{0}$-simplexes and usual simplexes. We establish a key representation theorem of a proper $L^0$-labeling function by usual proper labeling functions. Based on the representation theorem, we can establish a general random Sperner lemma. Next, as an application of the random Sperner lemma, we give a complete proof of the known random Brouwer fi…

"My approach is to look at the character’s world. Often, we get so locked into memorizing lines and practicing how we’re going to say those lines, when in reality the lines are just a symbol or representation of the person. I spend a lot of time getting into the character’s life. Every character has a point of view, so what informs this character’s point of view?"
—Malcolm-Jamal Warner
#acting

Integral representation for a product of two Jacobi functions of the second kind
Howard S. Cohl, Loyal Durand
https://arxiv.org/abs/2508.08085 https://arxi…

Integral representation for a product of two Jacobi functions of the second kind
By starting with Durand's double integral representation for a product of two Jacobi functions of the second kind, we derive an integral representation for a product of two Jacobi functions of the second kind in kernel form. We also derive a Bateman-type sum for a product of two Jacobi functions of the second kind. From this integral representation we derive integral representations for the Jacobi function of the first kind in both the hyperbolic and trigonometric contexts. From the integral re…

Lower bounds on heights of odd degree points of hyperelliptic curves
Jef Laga, Jack A. Thorne
https://arxiv.org/abs/2507.08652 https://

Lower bounds on heights of odd degree points of hyperelliptic curves
We develop a reduction theory for the representation of $\mathrm{SL}_n$ on pairs of symmetric $n\times n$ matrices. We apply this theory to the pencils of quadrics arising from divisors on hyperelliptic curves. We use these results to show that, in a density $1$ family, an odd degree point $P$ of degree at most $2g-1$ on the hyperelliptic curve $z^2 = f_0x^{2g+2} + f_1 x^{2g+1} y + \cdots + f_{2g+2}y^{2g+2}$ cannot have small Weil height.

EqualMotion: Accessible Motion Capture for the Creative Industries
Clarice Hilton, Kat Hawkins, Phill Tew, Freddie Collins, Seb Madgwick, Dominic Potts, Tom Mitchell
https://arxiv.org/abs/2507.08744

EqualMotion: Accessible Motion Capture for the Creative Industries
Motion capture technologies are increasingly used in creative and performance contexts but often exclude disabled practitioners due to normative assumptions in body modeling, calibration, and avatar representation. EqualMotion introduces a body-agnostic, wearable motion capture system designed through a disability-centred co-design approach. By enabling personalised calibration, integrating mobility aids, and adopting an inclusive visual language, EqualMotion supports diverse body types and mov…

Higgs branch of 5d $\mathcal{N}=1$ symplectic gauge theories and dressed instanton operators
Amihay Hanany, Elias Van den Driessche
https://arxiv.org/abs/2507.08669

Higgs branch of 5d $\mathcal{N}=1$ symplectic gauge theories and dressed instanton operators
We expand in instanton charge sectors the representation content of the infinite coupling chiral ring of the Higgs branch of 5d $\mathcal{N}=1$ $Sp(k)$ theories with $N_f$ flavours. The entire chiral ring can be expressed as the product of bare instantons, one for each topological sector, times a common dressing factor depending on the mesons and the instanton-anti instanton bound state. The dressing factor, which is independent of the instanton number, encodes the chiral ring of the theory at …

Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
Zitao Wang, Nian Si, Molei Liu
https://arxiv.org/abs/2509.09371 https://

Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
We propose REpresentation-Aware Distributionally Robust Estimation (READ), a novel framework for Wasserstein distributionally robust learning that accounts for predictive representations when guarding against distributional shifts. Unlike classical approaches that treat all feature perturbations equally, READ embeds a multidimensional alignment parameter into the transport cost, allowing the model to differentially discourage perturbations along directions associated with informative representa…

Integral Cayley graphs over a nonabelian group of order $8n$
Bei Ye, Xiaogang Liu
https://arxiv.org/abs/2508.10653 https://arxiv.org/pdf/2508.10653

Integral Cayley graphs over a nonabelian group of order $8n$
A graph is called an integral graph when all eigenvalues of its adjacency matrix are integers. We study which Cayley graphs over a nonabelian group $$ T_{8n}=\left\langle a,b\mid a^{2n}=b^8=e,a^n=b^4,b^{-1}ab=a^{-1} \right \rangle $$ are integral graphs. Based on the group representation theory, we first give the irreducible matrix representations and characters of $T_{8n}$. Then we give necessary and sufficient conditions for which Cayley graphs over $T_{8n}$ are integral graphs. As applicatio…

Double-functorial representation of regular structures
Jos\'e Siqueira
https://arxiv.org/abs/2508.06637 https://arxiv.org/pdf/2508.06637

Double-functorial representation of regular structures
It is well-known that bicategories of spans capture the Beck-Chevalley relationship underlying the adjunctions suitable for the semantics of existential quantification. By viewing hyperdoctrines from a double-categorical lens, this paper shows that we can also characterise the Frobenius property: (generalised) regular hyperdoctrines correspond to those lax symmetric monoidal double pseudofunctors from spans to quintets whose monoidal laxators provide companion commuter cells (in the sense of Pa…

DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Xiaoxue Luo, Jinwei Huang, Runyan Yang, Yingying Gao, Junlan Feng, Chao Deng, Shilei Zhang
https://arxiv.org/abs/2509.09201

DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio, however, often contains mixed speech and background sounds, and downstream tasks require selective access to these components. Therefore, we rethink the audio codec as a universal disentangled representation learner to enable controllable feature selection across different audio tasks. To this end, we introduce DeCod…

Tightening the mixed integer linear formulation for the piecewise linear approximation in general dimensions
Quentin Ploussard, Xiang Li, Matija Pavi\v{c}evi\'c
https://arxiv.org/abs/2508.09395

Tightening the mixed integer linear formulation for the piecewise linear approximation in general dimensions
This paper addresses the problem of tightening the mixed-integer linear programming (MILP) formulation for continuous piecewise linear (CPWL) approximations of data sets in arbitrary dimensions. The MILP formulation leverages the difference-of-convex (DC) representation of CPWL functions. We introduce the concept of well-behaved CPWL interpolations and demonstrate that any CPWL interpolation of a data set has a well-behaved version. This result is critical to tighten the MILP problem. We presen…

A Generalized Stability Analysis Method with Dynamic Phasors for LV AC Microgrids
B\"ulent Da\u{g}
https://arxiv.org/abs/2507.08383 https://

A Generalized Stability Analysis Method with Dynamic Phasors for LV AC Microgrids
Representation of inductive coupling lines with conventional static phasors is the main reason of inadequacy of the existing phasors based simplified stability analysis methods for microgrids with inductive coupling lines. In the literature, dynamic phasors have been proposed for the dynamic modelling of inductive lines to conserve the simplified structure of the analysis method. In this study a generalized stability analysis method for LV AC microgrids, composed of droop controlled inverters, …

Optimal Representation for Right-to-Left Parallel Scalar Point Multiplication
Kittiphon Phalakarn, Kittiphop Phalakarn, Vorapong Suppakitpaisarn
https://arxiv.org/abs/2508.07310

Optimal Representation for Right-to-Left Parallel Scalar Point Multiplication
This paper introduces an optimal representation for a right-to-left parallel elliptic curve scalar point multiplication. The right-to-left approach is easier to parallelize than the conventional left-to-right approach. However, unlike the left-to-right approach, there is still no work considering number representations for the right-to-left parallel calculation. By simplifying the implementation by Robert, we devise a mathematical model to capture the computation time of the calculation. Then, …

Harmonic maps and framed $\mathrm{PSL}_2(\mathbb{C})$-representations
Subhojoy Gupta, Gobinda Sau
https://arxiv.org/abs/2508.10335 https://arxiv.org/pdf/25…

Harmonic maps and framed $\mathrm{PSL}_2(\mathbb{C})$-representations
We show that given an element $X$ of the enhanced Teichmüller space $\mathcal{T}^\pm(\mathbb{S}, \mathbb{M})$ and a type-preserving framed $\mathrm{PSL}_2(\mathbb{C})$-representation $\hatρ = (ρ,β)$, there is a $ρ$-equivariant harmonic map $f:\mathbb{H}^2 \to \mathbb{H}^3$ that is asymptotic to the framing $β$. Here, the domain is the universal cover of the punctured Riemann surface obtained from a conformal completion of $X$. Moreover, such a harmonic map is unique if one prescribes, in …

Representation Theory of $UT_3(\mathbb{F}_3)$ and its Applications to Equivariant Decomposition in Neural Architectures
Bich Van Nguyen, Nguyen Cao Manh Thang
https://arxiv.org/abs/2507.08397

Representation Theory of $UT_3(\mathbb{F}_3)$ and its Applications to Equivariant Decomposition in Neural Architectures
In this paper we prove theorems characterizing the decomposition of equivariant feature spaces, filters and a structural preservation theorem for invariant subspace chains in group equivariant convolutional neural networks(G-CNN). Furthermore, we give explicit matrix forms for irreducible representations of $UT_3(\F_3)$-the unitriangular matrix groups over the field with three elements. These results provide a foundation for designing new G-CNN architectures via representations of $UT_3(\F_3)$ …

Proportional Representation Is the Solution to Gerrymandering
https://jacobin.com/2025/09/proportional-representation-voting-democrats-gerrymandering/

Nonlinear filtering based on density approximation and deep BSDE prediction
Kasper B{\aa}gmark, Adam Andersson, Stig Larsson
https://arxiv.org/abs/2508.10630 https://

Nonlinear filtering based on density approximation and deep BSDE prediction
A novel approximate Bayesian filter based on backward stochastic differential equations is introduced. It uses a nonlinear Feynman--Kac representation of the filtering problem and the approximation of an unnormalized filtering density using the well-known deep BSDE method and neural networks. The method is trained offline, which means that it can be applied online with new observations. A mixed a priori-a posteriori error bound is proved under an elliptic condition. The theoretical convergence …

Hippocampal plasticity and navigational skills in blindness https://www.intechopen.com/online-first/1228782 "We discuss how cross-modal plasticity repurposes the visual cortex for navigation, the role of sensory substitution devices in facilitating spatial learning, and behavioral …

Hippocampal Plasticity and Navigational Skills in Blindness

Navigation is a fundamental cognitive ability that relies on the hippocampus, a brain region that is known for its role in spatial representation and memory. In individuals with congenital blindness, the absence of visual input leads to significant neuroplastic adaptations that support alternative navigation strategies. This review examines the structural and functional modifications of the hippocampus in individuals who are blind and explores the broader neural mechanisms underlying…

PCHands: PCA-based Hand Pose Synergy Representation on Manipulators with N-DoF
En Yen Puang, Federico Ceola, Giulia Pasquale, Lorenzo Natale
https://arxiv.org/abs/2508.07945 htt…

PCHands: PCA-based Hand Pose Synergy Representation on Manipulators with N-DoF
We consider the problem of learning a common representation for dexterous manipulation across manipulators of different morphologies. To this end, we propose PCHands, a novel approach for extracting hand postural synergies from a large set of manipulators. We define a simplified and unified description format based on anchor positions for manipulators ranging from 2-finger grippers to 5-finger anthropomorphic hands. This enables learning a variable-length latent representation of the manipulato…

Shape-to-Music: A Musical Representation for Structural Topologies of Mechanical Metamaterials
Sofia Cassara, Buminhan Sansa, Saltuk Yildiz, Waris Khan, Pinar Acar
https://arxiv.org/abs/2509.09020

Shape-to-Music: A Musical Representation for Structural Topologies of Mechanical Metamaterials
Mechanical metamaterials are increasingly attracting interest in engineering applications due to their unique mechanical properties and lightweight nature. This study develops a novel sound-based representation to characterize the topologies of mechanical metamaterials, including spinodal designs and porous cellular structures. Two distinct frameworks are introduced: an image-based approach, where material topologies are divided into grids and their relative densities are mapped to evolving mel…

Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation
Soo-Whan Chung, Min-Seok Choi
https://arxiv.org/abs/2508.08953 https://…

Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation
This paper introduces a novel approach to speech restoration by integrating a context-related conditioning strategy. Specifically, we employ the diffusion-based generative restoration model, UNIVERSE++, as a backbone to evaluate the effectiveness of contextual representations. We incorporate acoustic context embeddings extracted from the CLAP model, which capture the environmental attributes of input audio. Additionally, we propose an Acoustic Context (ACX) representation that refines CLAP embe…

Revealing Higher-Order Interactions in Complex Networks: A U.S. Diplomacy Case Study
Arthur Rondeau, Didier Wernli, Roland Bouffanais
https://arxiv.org/abs/2509.10333 https://…

Revealing Higher-Order Interactions in Complex Networks: A U.S. Diplomacy Case Study
Although diplomatic communication has long been examined in the social sciences, its network structure remains underexplored. Using the U.S. diplomatic cables released by WikiLeaks in 2010 as a case study, we adopt a network-science perspective. We represent diplomatic interactions as a hypergraph and develop a general, random-walk-based pipeline to evaluate this representation against traditional pairwise graphs. We further evaluate the pipeline on legislative co-sponsorship and organizational…

Replaced article(s) found for q-bio.NC. https://arxiv.org/list/q-bio.NC/new
[1/1]:
- Representation biases: will we achieve complete understanding by analyzing representations?
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Yuxuan Li, Katherine Hermann

Emergent Hydrodynamics in an Exclusion Process with Long-Range Interactions
Ali Zahra, Jerome Dubail, Gunter M. Sch\"utz
https://arxiv.org/abs/2508.09879 https://

Emergent Hydrodynamics in an Exclusion Process with Long-Range Interactions
We study the symmetric Dyson exclusion process (SDEP) - a lattice gas with exclusion and long-range, Coulomb-type interactions that emerge both as the maximal-activity limit of the symmetric exclusion process and as a discrete version of Dyson's Brownian motion on the unitary group. Exploiting an exact ground-state (Doob) transform, we map the stochastic generator of the SDEP onto the spin-$1/2$ XX quantum chain, which in turn admits a free-fermion representation. At macroscopic scales we conje…

Proportional representation is the solution to gerrymandering (Matthew Yglesias/Slow Boring)
https://www.slowboring.com/p/proportional-representation-is-the
http://www.memeorandum.com/250811/p39#a250811p39

Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
Kalana Wijegunarathna, Kristin Stock, Christopher B. Jones
https://arxiv.org/abs/2508.06584

Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
The development, integration, and maintenance of geospatial databases rely heavily on efficient and accurate matching procedures of Geospatial Entity Resolution (ER). While resolution of points-of-interest (POIs) has been widely addressed, resolution of entities with diverse geometries has been largely overlooked. This is partly due to the lack of a uniform technique for embedding heterogeneous geometries seamlessly into a neural network framework. Existing neural approaches simplify complex ge…

A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals
Seong-A Park, Jong-Eui Chae, Sungdong Kim, Hyung-Chul Lee, Hyun-Lim Yang
https://arxiv.org/abs/2509.08830

A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals
In clinical settings, monitoring hemodynamics is crucial for managing patient prognosis, necessitating the integrated analysis of multiple physiological signals. While recent research has analyzed single signals such as electrocardiography (ECG) or photoplethysmography (PPG), there has yet to be a proposal for an approach that encompasses the complex signal analysis required in actual clinical scenarios. In this study, we introduce the SNUPHY-M (Seoul National University hospital PHYsiological …

Replaced article(s) found for cs.GR. https://arxiv.org/list/cs.GR/new
[1/1]:
- SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
Josi, Hafemann, Dib, Got, Cruz, Carbonneau

Branched covering representation of non-orientable $4$-manifolds
Valentina Bais, Riccardo Piergallini, Daniele Zuddas
https://arxiv.org/abs/2509.09319 https://

Branched covering representation of non-orientable $4$-manifolds
We show that every closed connected non-orientable PL $4$-manifold $X$ is a simple branched covering of $\RP^4$. We also show that $X$ is a simple branched covering of the twisted $S^3$-bundle $S^1 \simtimes S^3$ if and only if the first Stiefel--Whitney class $w_1(X)$ admits an integral lift. In both cases, the degree of the covering can be any number $d \geq 4$, provided that $d$ has the same parity of the Stiefel--Whitney number $w_1^4[X]$ in the case of $\RP^4$. Moreover, the branch set can…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/6]:
- Representation biases: will we achieve complete understanding by analyzing representations?
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Yuxuan Li, Katherine Hermann

Gauging the variational optimization of projected entangled-pair states
Wei Tang, Laurens Vanderstraeten, Jutho Haegeman
https://arxiv.org/abs/2508.10822 https://

Gauging the variational optimization of projected entangled-pair states
Projected entangled-pair states (PEPS) constitute a powerful variational ansatz for capturing ground state physics of two-dimensional quantum systems. However, accurately computing and minimizing the energy expectation value remains challenging, in part because the impact of the gauge degrees of freedom that are present in the tensor network representation is poorly understood. We analyze the role of gauge transformations for the case of a U(1)-symmetric PEPS with point group symmetry, thereby …

Emulating Public Opinion: A Proof-of-Concept of AI-Generated Synthetic Survey Responses for the Chilean Case
Basti\'an Gonz\'alez-Bustamante, Nando Verelst, Carla Cisternas
https://arxiv.org/abs/2509.09871

Emulating Public Opinion: A Proof-of-Concept of AI-Generated Synthetic Survey Responses for the Chilean Case
Large Language Models (LLMs) offer promising avenues for methodological and applied innovations in survey research by using synthetic respondents to emulate human answers and behaviour, potentially mitigating measurement and representation errors. However, the extent to which LLMs recover aggregate item distributions remains uncertain and downstream applications risk reproducing social stereotypes and biases inherited from training data. We evaluate the reliability of LLM-generated synthetic su…

On the Generalization Limits of Quantum Generative Adversarial Networks with Pure State Generators
Jasmin Frkatovic, Akash Malemath, Ivan Kankeu, Yannick Werner, Matthias Tsch\"ope, Vitor Fortes Rey, Sungho Suh, Paul Lukowicz, Nikolaos Palaiodimopoulos, Maximilian Kiefer-Emmanouilidis
https://arxiv.org/abs/2508.09844

On the Generalization Limits of Quantum Generative Adversarial Networks with Pure State Generators
We investigate the capabilities of Quantum Generative Adversarial Networks (QGANs) in image generations tasks. Our analysis centers on fully quantum implementations of both the generator and discriminator. Through extensive numerical testing of current main architectures, we find that QGANs struggle to generalize across datasets, converging on merely the average representation of the training data. When the output of the generator is a pure-state, we analytically derive a lower bound for the di…

On the Degenerate Whittaker space for some induced representations of ${\rm GL}_4(\mathfrak{o}_2)$
Ankita Parashar, Shiv Prakash Patel
https://arxiv.org/abs/2508.10796 https://

On the Degenerate Whittaker space for some induced representations of ${\rm GL}_4(\mathfrak{o}_2)$
Let $\mathfrak{o}_l$ be a finite principal ideal local ring of length $l$. The degenerate Whittaker space associated with a representation of ${\rm GL}_{2n}(\mathfrak{o}_l)$ is a representation of ${\rm GL}_n(\mathfrak{o}_l)$. For strongly cuspidal representations of ${\rm GL}_{2n}(\mathfrak{o}_l)$ the structure of degenerate Whittaker space is described by Prasad's conjecture, which has been proven for ${\rm GL}_4(\mathfrak{o}_2)$. In this paper, we describe the degenerate Whittaker space for …

KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learning
Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup, Steven Sloan, Kendall N. Niles, Ken Pathak
https://arxiv.org/abs/2508.08186

KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learning
Semantic segmentation of structural defects in civil infrastructure remains challenging due to variable defect appearances, harsh imaging conditions, and significant class imbalance. Current deep learning methods, despite their effectiveness, typically require millions of parameters, rendering them impractical for real-time inspection systems. We introduce KARMA (Kolmogorov-Arnold Representation Mapping Architecture), a highly efficient semantic segmentation framework that models complex defect…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/6]:
- Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inferenc...
Jialin Zhao, Yingtao Zhang, Carlo Vittorio Cannistraci

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/9]:
- Episodic Memory Representation for Long-form Video Understanding
Wang, Zhang, Liu, Yan, Zhang, Zheng, Yang, Wu, Chen, Li

AI-enabled tuberculosis screening in a high-burden setting using cough sound analysis and speech foundation models
Ning Ma, Bahman Mirheidari, Guy J. Brown, Minyoi M. Maimbolwa, Nsala Sanjase, Solomon Chifwamba, Seke Muzazu, Monde Muyoyeta, Mary Kagujje
https://arxiv.org/abs/2509.09746

AI-enabled tuberculosis screening in a high-burden setting using cough sound analysis and speech foundation models
Background Artificial intelligence (AI) can detect disease-related acoustic patterns in cough sounds, offering a scalable approach to tuberculosis (TB) screening in high-burden, low-resource settings. Previous studies have been limited by small datasets, under-representation of symptomatic non-TB patients, reliance on simple models, and recordings collected under idealised conditions. Methods We enrolled 512 participants at two hospitals in Zambia, grouped as bacteriologically confirmed T…

Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
Abdul Rehman Antall, Naveed Akhtar
https://arxiv.org/abs/2508.09865 https://

Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
This study evaluates the feasibility of lightweight Whisper models (Tiny, Base, Small) for Urdu speech recognition in low-resource settings. Despite Urdu being the 10th most spoken language globally with over 230 million speakers, its representation in automatic speech recognition (ASR) systems remains limited due to dialectal diversity, code-switching, and sparse training data. We benchmark these models on a curated Urdu dataset using word error rate (WER), without fine-tuning. Results show Wh…

FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
Zheng Dou, Deqing Wang, Fuzhen Zhuang, Jian Ren, Yanlin Hu
https://arxiv.org/abs/2509.07531

FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
Scientific document representation learning provides powerful embeddings for various tasks, while current methods face challenges across three approaches. 1) Contrastive training with citation-structural signals underutilizes citation information and still generates single-vector representations. 2) Fine-grained representation learning, which generates multiple vectors at the sentence or aspect level, requires costly integration and lacks domain generalization. 3) Task-aware learning depends on…

Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
Yian Huang, Yang Feng, Zhiliang Ying
https://arxiv.org/abs/2509.06575 https://

Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and theories assume a clean or near-clean setting, failing when contamination is significant. This paper tackles representation MTL with an unknown and potentially large contamination proportion, while also allowing for heterogeneity among inlier tasks. We introduce …

Perceptual Distortions and Autonomous Representation Learning in a Minimal Robotic System
David Warutumo, Ciira wa Maina
https://arxiv.org/abs/2507.07845 h…

Perceptual Distortions and Autonomous Representation Learning in a Minimal Robotic System
Autonomous agents, particularly in the field of robotics, rely on sensory information to perceive and navigate their environment. However, these sensory inputs are often imperfect, leading to distortions in the agent's internal representation of the world. This paper investigates the nature of these perceptual distortions and how they influence autonomous representation learning using a minimal robotic system. We utilize a simulated two-wheeled robot equipped with distance sensors and a compass…

Kallen-Lehmann representation for Spinor-Scalar Loops in de Sitter Space-time. Spectral equations
Boris L. Altshuler
https://arxiv.org/abs/2508.07467 https://

Kallen-Lehmann representation for Spinor-Scalar Loops in de Sitter Space-time. Spectral equations
Compact formulas (1), (28) presented in this paper permit to formulate the Kallen-Lehmann harmonic decompositions of the products of two spinor and of spinor and scalar harmonic functions in AdS and Wightman functions in dS spaces; the correct flat space limit of the corresponding Kallen-Lehmann densities is demonstrated. Also in Sec. 4 the relatively simple, suitable for calculations Kallen-Lehmann representations of the real parts of spinor and scalar one-loop self-energies in Yukawa model in…

Bailouts by Representation: A Minimal TLC Theory with Weighted Consent
Xinli Guo
https://arxiv.org/abs/2508.08693 https://arxiv.org/pdf/2508.08693

Bailouts by Representation: A Minimal TLC Theory with Weighted Consent
We develop a purely theoretical mechanism in which provincial bailouts are disciplined by two levers derived from Weighted Representative Democracy (WRD): a political shadow cost of public funds and a weighted-consent cap on any transfer. Bailouts are considered only when an externality threshold is met. With quadratic implementation costs, the static problem yields a simple ''threshold--linear--cap'' (TLC) policy: zero below a lower activation point, linear in the middle, and flat at an upper …

Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
Zheng Zhou, Yu-Jie Xiong, Chun-Ming Xia, Jia-Chen Zhang, Hong-Jian Zhan
https://arxiv.org/abs/2508.09239 https…

Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
The emergence of 3D Gaussian Splatting (3DGS) has significantly advanced novel view synthesis through explicit scene representation, enabling real-time photorealistic rendering. However, existing approaches manifest two critical limitations in complex scenarios: (1) Over-reconstruction occurs when persistent large Gaussians cannot meet adaptive splitting thresholds during density control. This is exacerbated by conflicting gradient directions that prevent effective splitting of these Gaussians;…

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
Rupert Mitchell, Kristian Kersting
https://arxiv.org/abs/2509.10406 https://

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
We present Multipole Semantic Attention (MuSe), an efficient approximation of softmax attention that combines semantic clustering with multipole expansions from computational physics. Our method addresses the quadratic computational complexity of transformers in the context length by clustering queries and keys separately in their learned representation spaces, enabling a hierarchical two-stage attention mechanism. Unlike prior clustering approaches that group only keys or use unified clusterin…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/4]:
- KeyRe-ID: Keypoint-Guided Person Re-Identification using Part-Aware Representation in Videos
Jinseong Kim, Junghoon Song, Gyeongseon Baek, Byeongjoon Noh

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
Brennen Hill
https://arxiv.org/abs/2509.09801 https://

HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of these techniques is diverse, with distinct methods operating in either the model's weight space or its representation space. This paper investigates the hypothesis that a synergistic combination of these paradigms can unlock superior performance and efficienc…

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Stable distributions and nilpotent orbital integrals
Jean-Loup Waldspurger (IMJ-PRG)

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Arushi Goel, Sreyan Ghosh, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro
https://arxiv.org/abs/2507.08128…

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) …

A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
Shuting He, Peilin Ji, Yitong Yang, Changshuo Wang, Jiayi Ji, Yinglin Wang, Henghui Ding
https://arxiv.org/abs/2508.09977

A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
3D Gaussian Splatting (3DGS) has recently emerged as a powerful alternative to Neural Radiance Fields (NeRF) for 3D scene representation, offering high-fidelity photorealistic rendering with real-time performance. Beyond novel view synthesis, the explicit and compact nature of 3DGS enables a wide range of downstream applications that require geometric and semantic understanding. This survey provides a comprehensive overview of recent progress in 3DGS applications. It first introduces 2D foundat…

Hybrid Data-Driven Predictive Control for Robust and Reactive Exoskeleton Locomotion Synthesis
Kejun Li, Jeeseop Kim, Maxime Brunet, Marine P\'etriaux, Yisong Yue, Aaron D. Ames
https://arxiv.org/abs/2508.10269

Hybrid Data-Driven Predictive Control for Robust and Reactive Exoskeleton Locomotion Synthesis
Robust bipedal locomotion in exoskeletons requires the ability to dynamically react to changes in the environment in real time. This paper introduces the hybrid data-driven predictive control (HDDPC) framework, an extension of the data-enabled predictive control, that addresses these challenges by simultaneously planning foot contact schedules and continuous domain trajectories. The proposed framework utilizes a Hankel matrix-based representation to model system dynamics, incorporating step-to-…

State Algebra for Propositional Logic
Dmitry Lesnik, Tobias Sch\"afer
https://arxiv.org/abs/2509.10326 https://arxiv.org/pdf/2509.10326

State Algebra for Propositional Logic
This paper presents State Algebra, a novel framework designed to represent and manipulate propositional logic using algebraic methods. The framework is structured as a hierarchy of three representations: Set, Coordinate, and Row Decomposition. These representations anchor the system in well-known semantics while facilitating the computation using a powerful algebraic engine. A key aspect of State Algebra is its flexibility in representation. We show that although the default reduction of a stat…

PromotionGo at SemEval-2025 Task 11: A Feature-Centric Framework for Cross-Lingual Multi-Emotion Detection in Short Texts
Ziyi Huang, Xia Cui
https://arxiv.org/abs/2507.08499

PromotionGo at SemEval-2025 Task 11: A Feature-Centric Framework for Cross-Lingual Multi-Emotion Detection in Short Texts
This paper presents our system for SemEval 2025 Task 11: Bridging the Gap in Text-Based Emotion Detection (Track A), which focuses on multi-label emotion detection in short texts. We propose a feature-centric framework that dynamically adapts document representations and learning algorithms to optimize language-specific performance. Our study evaluates three key components: document representation, dimensionality reduction, and model training in 28 languages, highlighting five for detailed anal…

Crosslisted article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Induced structures of averaging commutative and cocommutative infinitesimal bialgebras via a new ...
Chengming Bai, Li Guo, Guilai Liu, Quan Zhao

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
Geonhee Sim, Gyeongsik Moon
https://arxiv.org/abs/2508.09973 https://

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
Two major approaches exist for creating animatable human avatars. The first, a 3D-based approach, optimizes a NeRF- or 3DGS-based avatar from videos of a single person, achieving personalization through a disentangled identity representation. However, modeling pose-driven deformations, such as non-rigid cloth deformations, requires numerous pose-rich videos, which are costly and impractical to capture in daily life. The second, a diffusion-based approach, learns pose-driven deformations from la…

DECAMP: Towards Scene-Consistent Multi-Agent Motion Prediction with Disentangled Context-Aware Pre-Training
Jianxin Shi, Zengqi Peng, Xiaolong Chen, Tianyu Wo, Jun Ma
https://arxiv.org/abs/2509.10426

DECAMP: Towards Scene-Consistent Multi-Agent Motion Prediction with Disentangled Context-Aware Pre-Training
Trajectory prediction is a critical component of autonomous driving, essential for ensuring both safety and efficiency on the road. However, traditional approaches often struggle with the scarcity of labeled data and exhibit suboptimal performance in multi-agent prediction scenarios. To address these challenges, we introduce a disentangled context-aware pre-training framework for multi-agent motion prediction, named DECAMP. Unlike existing methods that entangle representation learning with pret…

FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
Sichen Zhao, Wei Shao, Jeffrey Chan, Ziqi Xu, Flora Salim
https://arxiv.org/abs/2508.07518

FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
As deep spatio-temporal neural networks are increasingly utilised in urban computing contexts, the deployment of such methods can have a direct impact on users of critical urban infrastructure, such as public transport, emergency services, and traffic management systems. While many spatio-temporal methods focus on improving accuracy, fairness has recently gained attention due to growing evidence that biased predictions in spatio-temporal applications can disproportionately disadvantage certain …

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim, YeonJe Cho, Seongwoo Kim
https://arxiv.org/abs/2508.10747

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by PDDL. However, existing approaches typically represent planning states as fully connected graphs, leading to a combinatorial explosion in edge information and substantial sparsity as problem scales grow, especially evident in large grid-based environments. This dense representation results in diluted node-level infor…

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- Diagrammatic representations of Generalized Temperley-Lieb algebras of affine type $\widetilde{B}...
Riccardo Biagioli, Giuliana Fatabbi, Elisa Sasso

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Matteo Trippodo, Federico Becattini, Lorenzo Seidenari
https://arxiv.org/abs/2509.10359 https://

Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that targets the visual component of editing methods. We introduce Attention Attack, which disrupts the cross-attention between a textual prompt and the visual representation of the image by using an automatically generated caption of the source image as a proxy for t…

Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
Fernando Martinez, Tao Li, Yingdong Lu, Juntao Chen
https://arxiv.org/abs/2508.07452 https://…

Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
Integrated, end-to-end learning of representations and policies remains a cornerstone of deep reinforcement learning (RL). However, to address the challenge of learning effective features from a sparse reward signal, recent trends have shifted towards adding complex auxiliary objectives or fully decoupling the two processes, often at the cost of increased design complexity. This work proposes an alternative to both decoupling and naive end-to-end learning, arguing that performance can be signif…

Replaced article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- The anti-spherical Hecke categories for Hermitian symmetric pairs
Chris Bowman, Maud De Visscher, Amit Hazi, Emily Norton

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Tao Han, Wanghan Xu, Junchao Gong, Xiaoyu Yue, Song Guo, Luping Zhou, Lei Bai
https://arxiv.org/abs/2509.10441

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Arbitrary resolution image generation provides a consistent visual experience across devices, having extensive applications for producers and consumers. Current diffusion models increase computational demand quadratically with resolution, causing 4K image generation delays over 100 seconds. To solve this, we explore the second generation upon the latent diffusion models, where the fixed latent generated by diffusion models is regarded as the content representation and we propose to decode arbit…

Real-Time 3D Vision-Language Embedding Mapping
Christian Rauch, Bj\"orn Ellensohn, Linus Nwankwo, Vedant Dave, Elmar Rueckert
https://arxiv.org/abs/2508.06291 https://

Real-Time 3D Vision-Language Embedding Mapping
A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time. We combine a local embedding masking strategy, for a more distinct embedding distribution, with a confidence-weighted 3D integration for more reliable 3D embeddings. The resulting metric-accurate embedding representation is task-agnostic and can represent sem…

Crosslisted article(s) found for math.RT. https://arxiv.org/list/math.RT/new
[1/1]:
- The characteristic quasi-polynomials of hyperplane arrangements with actions of finite groups
Ryo Uchiumi

Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Xunkai Li, Daohan Su, Sicheng Liu, Ru Zhang, Rong-Hua Li, Guoren Wang
https://arxiv.org/abs/2509.08401

Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Graph foundation models, inspired by the success of LLMs, are designed to learn the optimal embedding from multi-domain TAGs for the downstream cross-task generalization capability. During our investigation, graph VQ-MAE stands out among the increasingly diverse landscape of GFM architectures. This is attributed to its ability to jointly encode topology and textual attributes from multiple domains into discrete embedding spaces with clear semantic boundaries. Despite its potential, domain gener…

Representations of conformal nets associated with infinite-dimensional groups
Maria Stella Adamo, Luca Giorgetti, Yoh Tanimoto
https://arxiv.org/abs/2508.07109 https://

Representations of conformal nets associated with infinite-dimensional groups
We study the relation between representations of certain infinite-dimensional Lie groups and those of the associated conformal nets. For a chiral conformal net extending the net generated by the vacuum representation of a loop group or diffeomorphism group of the circle, we show that any conformal net representation induces a positive-energy representation of the corresponding group. Consequently, we prove that any representation of such a conformal net is automatically diffeomorphism covariant…

Visual Representation Alignment for Multimodal Large Language Models
Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim
https://arxiv.org/abs/2509.07979

Visual Representation Alignment for Multimodal Large Language Models
Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We attribute this gap to the prevailing text-only supervision paradigm, which provides only indirect guidance for the visual pathway and often leads MLLMs to discard fine-grained visual details during training. In this paper, we present VIsual Representation ALignment (…

[2025-09-15 Mon (UTC), 2 new articles found for math.RT Representation Theory]
toXiv_bot_toot

Low-rank Momentum Factorization for Memory Efficient Training
Pouria Mahdavinia, Mehrdad Mahdavi
https://arxiv.org/abs/2507.08091 https://arxiv.org/pdf/2507.08091 https://arxiv.org/html/2507.08091
arXiv:2507.08091v1 Announce Type: new
Abstract: Fine-tuning large foundation models presents significant memory challenges due to stateful optimizers like AdamW, often requiring several times more GPU memory than inference. While memory-efficient methods like parameter-efficient fine-tuning (e.g., LoRA) and optimizer state compression exist, recent approaches like GaLore bridge these by using low-rank gradient projections and subspace moment accumulation. However, such methods may struggle with fixed subspaces or computationally costly offline resampling (e.g., requiring full-matrix SVDs). We propose Momentum Factorized SGD (MoFaSGD), which maintains a dynamically updated low-rank SVD representation of the first-order momentum, closely approximating its full-rank counterpart throughout training. This factorization enables a memory-efficient fine-tuning method that adaptively updates the optimization subspace at each iteration. Crucially, MoFaSGD leverages the computed low-rank momentum factors to perform efficient spectrally normalized updates, offering an alternative to subspace moment accumulation. We establish theoretical convergence guarantees for MoFaSGD, proving it achieves an optimal rate for non-convex stochastic optimization under standard assumptions. Empirically, we demonstrate MoFaSGD's effectiveness on large language model alignment benchmarks, achieving a competitive trade-off between memory reduction (comparable to LoRA) and performance compared to state-of-the-art low-rank optimization methods. Our implementation is available at https://github.com/pmahdavi/MoFaSGD.
toXiv_bot_toot

SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Rongsheng Wang, Fenghe Tang, Qingsong Yao, Rui Yan, Xu Zhang, Zhen Huang, Haoran Lai, Zhiyang He, Xiaodong Tao, Zihang Jiang, Shaohua Kevin Zhou
https://arxiv.org/abs/2509.08311

SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Medical vision-language pre-training shows great potential in learning representative features from massive paired radiographs and reports. However, in computed tomography (CT) scans, the distribution of lesions which contain intricate structures is characterized by spatial sparsity. Besides, the complex and implicit relationships between different pathological descriptions in each sentence of the report and their corresponding sub-regions in radiographs pose additional challenges. In this pape…

[2025-08-14 Thu (UTC), 1 new article found for math.RT Representation Theory]
toXiv_bot_toot

Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
Piyush Bagad, Andrew Zisserman
https://arxiv.org/abs/2509.08502 https://

Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
Our objective is to develop compact video representations that are sensitive to visual change over time. To measure such time-sensitivity, we introduce a new task: chiral action recognition, where one needs to distinguish between a pair of temporally opposite actions, such as "opening vs. closing a door", "approaching vs. moving away from something", "folding vs. unfolding paper", etc. Such actions (i) occur frequently in everyday life, (ii) require understanding of simple visual change over ti…

[2025-07-14 Mon (UTC), 3 new articles found for math.RT Representation Theory]
toXiv_bot_toot

[2025-08-15 Fri (UTC), 5 new articles found for math.RT Representation Theory]
toXiv_bot_toot

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Haoyu Wu, Diankun Wu, Tianyu He, Junliang Guo, Yang Ye, Yueqi Duan, Jiang Bian
https://arxiv.org/abs/2507.07982

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned representations. To bridge this gap between video diffusion models and the underlying 3D nature of the physical world, we propose Geometry Forcing, a simple yet effective method that encourages video diffusion models to internalize latent 3D representations. Our ke…

Leaps in the depth of compositions of irreducible morphisms
Viktor Chust, Fl\'avio U. Coelho
https://arxiv.org/abs/2507.08094 https://

Leaps in the depth of compositions of irreducible morphisms
In this article, we give a family of examples of algebras, showing that for every $n \geq 2$ and $m \geq 0$, there is an algebra displaying a path of n irreducible morphisms between indecomposable modules whose composite lies in the $(n+m+3)$-th power of the radical, but not in the $(n + m + 4)$-th power. Such an algebra may be also supposed to be string and representation-finite.

Scaling Learned Image Compression Models up to 1 Billion
Yuqi Li, Haotian Zhang, Li Li, Dong Liu, Feng Wu
https://arxiv.org/abs/2508.09075 https://arxiv.or…

Scaling Learned Image Compression Models up to 1 Billion
Recent advances in large language models (LLMs) highlight a strong connection between intelligence and compression. Learned image compression, a fundamental task in modern data compression, has made significant progress in recent years. However, current models remain limited in scale, restricting their representation capacity, and how scaling model size influences compression performance remains unexplored. In this work, we present a pioneering study on scaling up learned image compression mode…