Tootfinder

Efficient Learned Image Compression Through Knowledge Distillation
Fabien Allemand, Attilio Fiandrotti, Sumanta Chaudhuri, Alaa Eddine Mazouz
https://arxiv.org/abs/2509.10366 ht…

Efficient Learned Image Compression Through Knowledge Distillation
Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a low-dimensional latent space, which is then quantized, entropy-coded into a binary bitstream, and transmitted to the receiver. At the receiver end, the bitstream is entropy-decoded, and a decoder reconstructs an approximation of the original image. Recent research sugges…

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Sahil Sethi, Kai Sundmacher, Caroline Ganzer
https://arxiv.org/abs/2509.10273

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework that leverages a neural recommender system (NRS) to enable reliable property predicti…

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang
https://arxiv.org/abs/2508.10433

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data…

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Seyed Muhammad Hossein Mousavi, S. Younes Mirinezhad
https://arxiv.org/abs/2508.09188

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Affective computing faces a major challenge: the lack of high-quality, diverse depth facial datasets for recognizing subtle emotional expressions. We propose a framework for synthetic depth face generation using an optimized GAN with Knowledge Distillation (EMA teacher models) to stabilize training, improve quality, and prevent mode collapse. We also apply Genetic Algorithms to evolve GAN latent vectors based on image statistics, boosting diversity and visual quality for target emotions. The ap…

A time-space B-spline integrator for the Burgers' equation
Idris Dag, Serkan U\u{g}urluo\u{g}lu, Nihat Adar
https://arxiv.org/abs/2510.09408 https://ar…

A time-space B-spline integrator for the Burgers' equation
The purpose of this paper is to propose a new algorithm for obtaining approximate solutions to the Burgers' equation (BE). Integration in time by a quadratic B-spline collocation method is shown. To the best of our knowledge, B-splines have not previously been used to integrate partial differential equations in both time and space. First, the BE is integrated using quadratic B-spline functions in time, and then the time-integrated BE is further solved in space via the cubic B-spline collocation…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Soumia Mehimeh
https://arxiv.org/abs/2508.09277 https://…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Value function initialization (VFI) is an effective way to achieve a jumpstart in reinforcement learning (RL) by leveraging value estimates from prior tasks. While this approach is well established in tabular settings, extending it to deep reinforcement learning (DRL) poses challenges due to the continuous nature of the state-action space, the noisy approximations of neural networks, and the impracticality of storing all past models for reuse. In this work, we address these challenges and intro…

DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
Guanxin Jiang, Andreas Brendel, Pablo M. Delgado, J\"urgen Herre
https://arxiv.org/abs/2510.12326

DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the music foundation model MERT, guided by surrogate labels, to construct an embedding space that captures distortion intensity in general audio. To the best of our knowledge, DeePAQ is the first in the general audio quality domain to leverage weakly supervised labels and metric learning for fine-tuning a music foundation…

Reweighting metric measure spaces and Onsager-Machlup
Zachary Selk
https://arxiv.org/abs/2510.10591 https://arxiv.org/pdf/2510.10591

Reweighting metric measure spaces and Onsager-Machlup
Given a metric measure space $M:=(X,d,μ)$ the Onsager-Machlup (OM) functional is a real valued function that has been seen as a generalized notion of a probability density function. The effect of reweighting the measure on OM functionals has been studied, however analogous reweightings of the metric to the best of our knowledge remain open. In this short note, we prove a transformation formula for OM functionals on geodesic metric measure spaces under reweighting of both the metric and the mea…

"""
All of which was of the utmost importance for subsequent developments in the medicine of the mind. In its positivist incarnation, this was little more than the combination of the two experiences that classicism had juxtaposed without ever joining them together: a social, normative and dichotomous experience of madness that revolved entirely around the imperative of confinement, formulated in a style as simple as ‘yes or no’, ‘dangerous or harmless’, and ‘good or not good for confinement’, and a finely differentiated, qualitative, juridical experience, well aware of limits and degrees, which looked into all the aspects of the behaviour of the subject for the polymorphous incarnations that insanity might assume. The psychopathology of the nineteenth century (and perhaps our own too, even now) believes that it orients itself and takes its bearings in relation to a homo natura, or a normal man pre-existing all experience of mental illness. Such a man is in fact an invention, and if he is to be situated, it is not in a natural space, but in a system that identifies the socius to the subject of the law. Consequently a madman is not recognised as such because an illness has pushed him to the margins of normality, but because our culture situates him at the meeting point between the social decree of confinement and the juridical knowledge that evaluates the responsibility of individuals before the law. The ‘positive’ science of mental illness and the humanitarian sentiments that brought the mad back into the realm of the human were only possible once that synthesis had been solidly established. They could be said to form the concrete a priori of any psychopathology with scientific pretensions.
"""
(Michel Foucault, History of Madness)

Fast and the Furious: Hot Starts in Pursuit-Evasion Games
Gabriel Smithline, Scott Nivison
https://arxiv.org/abs/2510.10830 https://arxiv.org/pdf/2510.1083…

Fast and the Furious: Hot Starts in Pursuit-Evasion Games
Effectively positioning pursuers in pursuit-evasion games without prior knowledge of evader locations remains a significant challenge. A novel approach that combines game-theoretic control theory with Graph Neural Networks is introduced in this work. By conceptualizing pursuer configurations as strategic arrangements and representing them as graphs, a Graph Characteristic Space is constructed via multi-objective optimization to identify Pareto-optimal configurations. A Graph Convolutional Netwo…

Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework
Jingjing Wang, Pengyu Liang, Tingyu Wang, Ming Li, Yanmei Cui, Siwei Liu, Xin Huang, Xiang Li, Minghui Zhang, Yunshi Zeng, Zhu Cao, Jiekang Feng, Qinghua Hu, Bingxian Luo, Bing Cao
https://arxiv.org/abs/2508.06892…

Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework
Solar activity drives space weather, affecting Earth's magnetosphere and technological infrastructure, which makes accurate solar flare forecasting critical. Current space weather models under-utilize multi-modal solar data, lack iterative enhancement via expert knowledge, and rely heavily on human forecasters under the Observation-Orientation-Decision-Action (OODA) paradigm. Here we present the "Solar Activity AI Forecaster", a scalable dual data-model driven framework built on foundational mo…

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
Yuhao Zhang, Yuhao Du, Zhanchen Dai, Xiangnan Ma, Kaiqi Kou, Benyou Wang, Haizhou Li
https://arxiv.org/abs/2509.09174

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech trainin…

Data Augmentation for Visualization Design Knowledge Bases
Hyeok Kim, Jeffrey Heer
https://arxiv.org/abs/2508.02216 https://arxiv.org/pdf/2508.02216…

Data Augmentation for Visualization Design Knowledge Bases
Visualization knowledge bases enable computational reasoning and recommendation over a visualization design space. These systems evaluate design trade-offs using numeric weights assigned to different features (e.g., binning a variable). Feature weights can be learned automatically by fitting a model to a collection of chart pairs, in which one chart is deemed preferable to the other. To date, labeled chart pairs have been drawn from published empirical research results; however, such pairs are …

Constraint-Level Design of zkEVMs: Architectures, Trade-offs, and Evolution
Yahya Hassanzadeh-Nazarabadi, Sanaz Taheri-Boshrooyeh
https://arxiv.org/abs/2510.05376 https://

Constraint-Level Design of zkEVMs: Architectures, Trade-offs, and Evolution
Zero-knowledge Ethereum Virtual Machines (zkEVMs) must reconcile a fundamental contradiction: the Ethereum Virtual Machine was designed for transparent sequential execution, while zero-knowledge proofs require algebraic circuit representations. This survey provides the first systematic analysis of how existing major production zkEVM implementations resolve this tension through distinct constraint engineering strategies. We develop a comparative framework that maps the design space across three …

Experimental Reconstruction of Source 4D Phase Space Without Prior Knowledge of Transfer Matrix
Charles Zhang, Elena Echeverria, Abigail Flint, William H Li, Christopher M. Pierce, Alice Galdi, Chad Penningto, Adam Bartnik, Ivan Bazarov, Jared Maxson
https://arxiv.org/abs/2510.04768

Experimental Reconstruction of Source 4D Phase Space Without Prior Knowledge of Transfer Matrix
We experimentally demonstrate a method for reconstructing the transverse 4D phase space of an electron beam at the time of emission from downstream diagnostics of the 4D phase space. This method does not rely on detailed knowledge of the beamline transport, besides assuming that linearity and symplecticity are satisfied. We apply this method to measure the transverse position and momentum phase space of electrons emitted from a spatially-structured alkali-antimonide cathode. This method can unc…

Opening Knowledge Gaps Drives Scientific Progress
Kara Kedrick, Wenlong Yang, Thomas Gebhart, Yang Wang, Russell J. Funk
https://arxiv.org/abs/2509.21899 https://

Opening Knowledge Gaps Drives Scientific Progress
Knowledge production is often viewed as an endogenous process in which discovery arises through the recombination of existing theories, findings, and concepts. Yet given the vast space of potential recombinations, not all are equally valuable, and identifying those that may prove most generative remains challenging. We argue that a crucial form of recombination occurs when linking concepts creates knowledge gaps-empty regions in the conceptual landscape that focus scientific attention on proxim…

Optimal Simultaneous Byzantine Agreement, Common Knowledge and Limited Information Exchange
Ron van der Meyden
https://arxiv.org/abs/2508.03418 https://arx…

Optimal Simultaneous Byzantine Agreement, Common Knowledge and Limited Information Exchange
In order to develop solutions that perform actions as early as possible, analysis of distributed algorithms using epistemic logic has generally concentrated on ``full information protocols'', which may be inefficient with respect to space and computation time. The paper reconsiders the epistemic analysis of the problem of Simultaneous Byzantine Agreement with respect to weaker, but more practical, exchanges of information. The paper first clarifies some issues concerning both the specification …

Quantum Relational Knowledge Distillation
Chen-Yu Liu, Kuan-Cheng Chen, Keisuke Murota, Samuel Yen-Chi Chen, Enrico Rinaldi
https://arxiv.org/abs/2508.13054 https://

Quantum Relational Knowledge Distillation
Knowledge distillation (KD) is a widely adopted technique for compressing large models into smaller, more efficient student models that can be deployed on devices with limited computational resources. Among various KD methods, Relational Knowledge Distillation (RKD) improves student performance by aligning relational structures in the feature space, such as pairwise distances and angles. In this work, we propose Quantum Relational Knowledge Distillation (QRKD), which extends RKD by incorporatin…

MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
Zihan Yan, Rui Xi, Mengshu Hou
https://arxiv.org/abs/2509.06298 https://…

MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
Database knob tuning is essential for optimizing the performance of modern database management systems, which often expose hundreds of knobs with continuous or categorical values. However, the large number of knobs and the vast configuration space make it difficult to identify optimal settings efficiently. Although learning-based tuning has shown promise, existing approaches either ignore domain knowledge by relying solely on benchmark feedback or struggle to explore the high-dimensional knob s…

Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
Dongliang Cao, Guoxing Sun, Marc Habermann, Florian Bernard
https://arxiv.org/abs/2509.04145

Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
Creating human avatars is a highly desirable yet challenging task. Recent advancements in radiance field rendering have achieved unprecedented photorealism and real-time performance for personalized dynamic human avatars. However, these approaches are typically limited to person-specific rendering models trained on multi-view video data for a single individual, limiting their ability to generalize across different identities. On the other hand, generative approaches leveraging prior knowledge f…

Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
Yueqi Zhao, Michael M. Fogler, Yi-Zhuang You
https://arxiv.org/abs/2510.06508 …

Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
We introduce RGFlow, a deep neural network-based real-space renormalization group (RG) framework tailored for continuum scalar field theories. Leveraging generative capabilities of flow-based neural networks, RGFlow autonomously learns real-space RG transformations from data without prior knowledge of the underlying model. In contrast to conventional approaches, RGFlow is bijective (information-preserving) and is optimized based on the principle of minimal mutual information. We demonstrate the…

Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
Dhruv Kohli, Sawyer J. Robertson, Gal Mishne, Alexander Cloninger
https://arxiv.org/abs/2510.02308

Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
Estimating the tangent spaces of a data manifold is a fundamental problem in data analysis. The standard approach, Local Principal Component Analysis (LPCA), struggles in high-noise settings due to a critical trade-off in choosing the neighborhood size. Selecting an optimal size requires prior knowledge of the geometric and noise characteristics of the data that are often unavailable. In this paper, we propose a spectral method, Laplacian Eigenvector Gradient Orthogonalization (LEGO), that util…

Robust Confidence Intervals for a Binomial Proportion: Local Optimality and Adaptivity
Minjun Cho, Yuetian Luo, Chao Gao
https://arxiv.org/abs/2509.05568 https://

Robust Confidence Intervals for a Binomial Proportion: Local Optimality and Adaptivity
This paper revisits the classical problem of interval estimation of a binomial proportion under Huber contamination. Our main result derives the rate of optimal interval length when the contamination proportion is unknown under a local minimax framework, where the performance of an interval is evaluated at each point in the parameter space. By comparing the rate with the optimal length of a confidence interval that is allowed to use the knowledge of contamination proportion, we characterize the…

Symmetry breaking for inductive logic programming
Andrew Cropper, David M. Cerna, Matti J\"arvisalo
https://arxiv.org/abs/2508.06263 https://arxiv.org…

Symmetry breaking for inductive logic programming
The goal of inductive logic programming is to search for a hypothesis that generalises training data and background knowledge. The challenge is searching vast hypothesis spaces, which is exacerbated because many logically equivalent hypotheses exist. To address this challenge, we introduce a method to break symmetries in the hypothesis space. We implement our idea in answer set programming. Our experiments on multiple domains, including visual reasoning and game playing, show that our approach …

Evolutionary hypergame dynamics: Introspection reasoning and social learning
Feipeng Zhang, Te Wu, Guofeng Zhang, Long Wang
https://arxiv.org/abs/2509.24398 https://

Evolutionary hypergame dynamics: Introspection reasoning and social learning
In the realm of evolutionary game theory, standard frameworks typically presuppose that every player possesses comprehensive knowledge and unrestricted access to the entire strategy space. However, real-world human society inherently harbors diverse levels of knowledge, experience, and background among individuals. Hypergames incorporate this heterogeneity by permitting individuals to differ in their access to the full strategy set, reflecting cognitive or informational constraints and giving r…

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han
https://arxiv.org/abs/2509.00918

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. Recent work has revealed that model editing in the fingerprinting domain offers distinct advantages, including significantly lower false positive rates, enhanced harmlessness, and su…

A Collaborative Framework Integrating Large Language Model and Chemical Fragment Space: Mutual Inspiration for Lead Design
Hao Tuo, Yan Li, Xuanning Hu, Haishi Zhao, Xueyan Liu, Bo Yang
https://arxiv.org/abs/2507.13580

A Collaborative Framework Integrating Large Language Model and Chemical Fragment Space: Mutual Inspiration for Lead Design
Combinatorial optimization algorithm is essential in computer-aided drug design by progressively exploring chemical space to design lead compounds with high affinity to target protein. However current methods face inherent challenges in integrating domain knowledge, limiting their performance in identifying lead compounds with novel and valid binding mode. Here, we propose AutoLeadDesign, a lead compounds design framework that inspires extensive domain knowledge encoded in large language models…

Quantifying Coupled Dynamics in Phase-Space from State Distribution Snapshots
Erez Aghion, Nava Leibovich
https://arxiv.org/abs/2507.18648 https://arxiv.or…

Quantifying Coupled Dynamics in Phase-Space from State Distribution Snapshots
We quantify nonlinear interactions between coupled complex processes, when the system is subject to noise and not all its components are measurable. Our method is applicable even when the system cannot be continuously monitored over time, but is rather observed only in snapshots. Having only partial information about the local topology of the network and observations of relevant interacting variables is sufficient to translate qualitative knowledge of interactions into a quantitative characteri…

LHS in LHS: A new expansion strategy for Latin hypercube sampling in simulation design
Matteo Boschini, Davide Gerosa, Alessandro Crespi, Matteo Falcone
https://arxiv.org/abs/2509.00159

LHS in LHS: A new expansion strategy for Latin hypercube sampling in simulation design
Latin Hypercube Sampling (LHS) is a prominent tool in simulation design, with a variety of applications in high-dimensional and computationally expensive problems. LHS allows for various optimization strategies, most notably to ensure space-filling properties. However, LHS is a single-stage algorithm that requires a priori knowledge of the targeted sample size. In this work, we present LHS in LHS, a new expansion algorithm for LHS that enables the addition of new samples to an existing LHS-dist…

State Space Models Naturally Produce Traveling Waves, Time Cells, and Scale to Abstract Cognitive Functions
Sen Lu, Xiaoyu Zhang, Mingtao Hu, Eric Yeu-Jer Lee, Soohyeon Kim, Wei D. Lu
https://arxiv.org/abs/2507.13638

State Space Models Naturally Produce Traveling Waves, Time Cells, and Scale to Abstract Cognitive Functions
A grand challenge in modern neuroscience is to bridge the gap between the detailed mapping of microscale neural circuits and a mechanistic understanding of cognitive functions. While extensive knowledge exists about neuronal connectivity and biophysics, a significant gap remains in how these elements combine to produce flexible, learned behaviors. Here, we propose that a framework based on State-Space Models (SSMs), an emerging class of deep learning architectures, can bridge this gap. We argue…

Finished reading "The Steerswoman" by Rosemary Kirstein. It's a great little fantasy novel. I'd call it "hard sci-fi" if it was set in space. Is there a term for medieval stories that don't get too magical?
The hero of this story is a member of a special guild that is all about preserving and acquiring knowledge. Sworn to speak the truth. Much of the story is her drawing conclusions about the world she inhabits. There are swords and scheming wizards. On t…

Geodesic convexity and strengthened functional inequalities in submanifolds of Wasserstein space
Louis-Pierre Chaintron (DMA), Daniel Lacker
https://arxiv.org/abs/2508.13698 htt…

Geodesic convexity and strengthened functional inequalities in submanifolds of Wasserstein space
We study the geodesic convexity of various energy and entropy functionals restricted to (non-geodesically convex) submanifolds of Wasserstein spaces with their induced geometry. We prove a variety of convexity results by means of a simple general principle, which holds in the metric space setting, and which crucially requires no knowledge of the structure of geodesics in the submanifold: If the EVI gradient flow of a functional exists and leaves the submanifold invariant, then the restriction o…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

BioBO: Biology-informed Bayesian Optimization for Perturbation Design
Yanke Li, Tianyu Cui, Tommaso Mansi, Mangal Prakash, Rui Liao
https://arxiv.org/abs/2509.19988 https://

BioBO: Biology-informed Bayesian Optimization for Perturbation Design
Efficient design of genomic perturbation experiments is crucial for accelerating drug discovery and therapeutic target identification, yet exhaustive perturbation of the human genome remains infeasible due to the vast search space of potential genetic interactions and experimental constraints. Bayesian optimization (BO) has emerged as a powerful framework for selecting informative interventions, but existing approaches often fail to exploit domain-specific biological prior knowledge. We propose…

Causal perturbation theory and scattering amplitudes
H. A. C. Grande, J. C. A Barata
https://arxiv.org/abs/2509.20573 https://arxiv.org/pdf/2509.20573

Causal perturbation theory and scattering amplitudes
Motivated by the limited interaction between the mathematical physics community and theoretical physicists - particularly in high-energy theory - we present a computation that is typically the first example in QFT courses but, to our knowledge, does not appear in the literature: the scattering amplitudes of the $λϕ^4$ model in four-dimensional space-time, derived within the framework of causal perturbation theory. Our aim is to introduce this mathematically rigorous formalism in the most acce…

The Weakly-Nonlinear Admittance at Open Ends of Two- and Three-Dimensional Acoustic Waveguides
Freddie Jensen, Harry Turnbull, Edward James Brambley
https://arxiv.org/abs/2509.21615

The Weakly-Nonlinear Admittance at Open Ends of Two- and Three-Dimensional Acoustic Waveguides
We formulate a weakly-nonlinear exit condition for open ends of acoustic waveguides without mean flow; to our knowledge this is the first time an acoustic open end has been analysed outside the linear regime. The resulting admittance boundary condition, and its weakly-nonlinear counterpart, extends recent weakly-nonlinear modelling of curved ducts (Jensen & Brambley 2025, arXiv:2503.11536) to include open ends. We approximate free space by considering the open-ended duct to be enclosed within a…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
Kaiyan Chang, Wenlong Zhu, Shengwen Liang, Huawei Li, Ying Wang
https://arxiv.org/abs/2508.17826

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and input-dependent control flows. We present LLMulator, a progressive numeric modeling framework leveraging the program semantic knowledge of pre-trained large language models (LLMs) for robust, hardware- and application-aware prediction. Our numeric model treats performance …

Universal $L_2$-approximation using median lattice algorithms
Zexin Pan, Takashi Goda, Peter Kritzer
https://arxiv.org/abs/2509.24582 https://arxiv.org/pdf…

Universal $L_2$-approximation using median lattice algorithms
We study the problem of multivariate $L_2$-approximation of functions in a weighted Korobov space using a median lattice-based algorithm recently proposed by the authors. In the original work, the algorithm requires knowledge of the smoothness and weights of the Korobov space to construct the hyperbolic cross index set, where each coefficient is estimated via the median of approximations obtained from randomly shifted, randomly chosen rank-1 lattice rules. In this paper, we introduce a \emph{un…

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
Yucen Wang, Rui Yu, Shenghua Wan, Le Gan, De-Chuan Zhan
https://arxiv.org/abs/2507.12496

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task solving in embodied environments in a reward-free manner. We learn a mapping function that grounds FM representations in the WM state space, effectively inferring the agent's physical states in the wo…

MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Yi Xu, Moyu Zhang, Chenxuan Li, Zhihao Liao, Haibo Xing, Hao Deng, Jinxin Hu, Yu Zhang, Xiaoyi Zeng, Jing Zhang
https://arxiv.org/abs/2508.15281

MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived from multimodal content such as text and images, offer a promising alternative by mapping items into a shared semantic space, enabling knowledge transfer and improving recommendations for new or rare items. However, existing methods face two key challenges: (1) …

Code2Video: A Code-centric Paradigm for Educational Video Generation
Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou
https://arxiv.org/abs/2510.01174 https://

Code2Video: A Code-centric Paradigm for Educational Video Generation
While recent generative models advance pixel-space video synthesis, they remain limited in producing professional educational videos, which demand disciplinary knowledge, precise visual structures, and coherent transitions, limiting their applicability in educational scenarios. Intuitively, such requirements are better addressed through the manipulation of a renderable environment, which can be explicitly controlled via logical commands (e.g., code). In this work, we propose Code2Video, a code-…

Optimal decay of semi-uniformly stable operator semigroups with empty spectrum
Morgan Callewaert, Lenny Neyt, Jasson Vindas
https://arxiv.org/abs/2507.20376 https://

Optimal decay of semi-uniformly stable operator semigroups with empty spectrum
We show that it is impossible to quantify the decay rate of a semi-uniformly stable operator semigroup based on sole knowledge of its spectrum. More precisely, given an arbitrary positive function $r$ vanishing at $\infty$, we construct a Banach space $X$ and a bounded semigroup $ (T(t))_{t \geq 0}$ of operators on it whose infinitesimal generator $A$ has empty spectrum $σ(A)=\varnothing$, but for which, for some $x \in X$, $$\limsup_{t\to\infty} \frac{\|T(t)A^{-1}x\|_{X}}{r(t)}=\inf…

Enhancing Cross-task Transfer of Large Language Models via Activation Steering
Xinyu Tang, Zhihao Lv, Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Zujie Wen, Zhiqiang Zhang, Jun Zhou
https://arxiv.org/abs/2507.13236

Enhancing Cross-task Transfer of Large Language Models via Activation Steering
Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers a direct solution for transferring knowledge across tasks, it still faces critical challenges in terms of robustness, scalability, and efficiency. In this paper, we investigate whether cross-task transfer can be achieved via latent space steering without par…

Conversations over Clicks: Impact of Chatbots on Information Search in Interdisciplinary Learning
Hannah Kim, Sergei L. Kosakovsky Pond, Stephen MacNeil
https://arxiv.org/abs/2507.21490

Conversations over Clicks: Impact of Chatbots on Information Search in Interdisciplinary Learning
This full research paper investigates the impact of generative AI (GenAI) on the learner experience, with a focus on how learners engage with and utilize the information it provides. In e-learning environments, learners often need to navigate a complex information space on their own. This challenge is further compounded in interdisciplinary fields like bioinformatics, due to the varied prior knowledge and backgrounds. In this paper, we studied how GenAI influences information search in bioinfor…

Is Sequence Information All You Need for Bayesian Optimization of Antibodies?
Sebastian W. Ober, Calvin McCarter, Aniruddh Raghu, Yucen Lily Li, Alan N. Amin, Andrew Gordon Wilson, Hunter Elliott
https://arxiv.org/abs/2509.24933

Is Sequence Information All You Need for Bayesian Optimization of Antibodies?
Bayesian optimization is a natural candidate for the engineering of antibody therapeutic properties, which is often iterative and expensive. However, finding the optimal choice of surrogate model for optimization over the highly structured antibody space is difficult, and may differ depending on the property being optimized. Moreover, to the best of our knowledge, no prior works have attempted to incorporate structural information into antibody Bayesian optimization. In this work, we explore di…

Enhanced Interpretable Knowledge Tracing for Students Performance Prediction with Human understandable Feature Space
Sein Minn, Roger Nkambou
https://arxiv.org/abs/2509.18231 ht…

SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Yifei Li, Lingling Zhang, Hang Yan, Tianzhe Zhao, Zihan Ma, Muye Huang, Jun Liu
https://arxiv.org/abs/2508.11347

SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs are dynamically evolving with the constant addition of entities, relations and facts. To address such dynamic nature of KGs, several continual knowledge graph embedding (CKGE) methods have been developed to efficiently update KG embeddings to accommodate new facts while maintaining learned knowledge. As KGs grow at di…

Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)
Semih Kara, Tamer Ba\c{s}ar
https://arxiv.org/abs/2508.19371 https://

Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)
Fictitious play (FP) is a well-studied algorithm that enables agents to learn Nash equilibrium in games with certain reward structures. However, when agents have no prior knowledge of the reward functions, FP faces a major challenge: the joint action space grows exponentially with the number of agents, which slows down reward exploration. Anonymous games offer a structure that mitigates this issue. In these games, the rewards depend only on the actions taken; not on who is taking which action. …

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Ziming Wei, Zichen Kong, Yuan Wang, David Z. Pan, Xiyuan Tang
https://arxiv.org/abs/2509.14169

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language m…

Stability of Gel'fand's inverse interior spectral problem for Schr\"odinger operators
Jinpeng Lu
https://arxiv.org/abs/2507.15560 https://

Stability of Gel'fand's inverse interior spectral problem for Schrödinger operators
We study Gel'fand's inverse interior spectral problem of determining a closed Riemannian manifold $(M,g)$ and a potential function $q$ from the knowledge of the eigenvalues $λ_j$ of the Schrödinger operator $-Δ_g + q$ and the restriction of the eigenfunctions $ϕ_j|_U$ on a given open subset $U\subset M$, where $Δ_g$ is the Laplace-Beltrami operator on $(M,g)$. We prove that an approximation of finitely many spectral data on $U$ determines a finite metric space that is close to $(M,g)$…

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
Alina Klerings, Jannik Brinkmann, Daniel Ruffinelli, Simone Ponzetto
https://arxiv.org/abs/2509.12065

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the representation and control of two multidimensional hierarchical grammar phenomena - verb tense and aspect - and for each, identify distinct, orthogonal directions in residual space using linear discriminant analysis. Next, we demonstrate causal control over b…

Discovering Association Rules in High-Dimensional Small Tabular Data
Erkan Karabulut, Daniel Daza, Paul Groth, Victoria Degeler
https://arxiv.org/abs/2509.20113 https://

Discovering Association Rules in High-Dimensional Small Tabular Data
Association Rule Mining (ARM) aims to discover patterns between features in datasets in the form of propositional rules, supporting both knowledge discovery and interpretable machine learning in high-stakes decision-making. However, in high-dimensional settings, rule explosion and computational overhead render popular algorithmic approaches impractical without effective search space reduction, challenges that propagate to downstream tasks. Neurosymbolic methods, such as Aerial+, have recently b…

A-MHA*: Anytime Multi-Heuristic A*
Ramkumar Natarajan, Muhammad Suhail Saleem, William Xiao, Sandip Aine, Howie Choset, Maxim Likhachev
https://arxiv.org/abs/2508.21637 https://…

A-MHA*: Anytime Multi-Heuristic A*
Designing good heuristic functions for graph search requires adequate domain knowledge. It is often easy to design heuristics that perform well and correlate with the underlying true cost-to-go values in certain parts of the search space but these may not be admissible throughout the domain thereby affecting the optimality guarantees of the search. Bounded suboptimal search using several such partially good but inadmissible heuristics was developed in Multi-Heuristic A* (MHA*). Although MHA* le…

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
Junjie Li, Jing Peng, Yangui Fang, Shuai Wang, Kai Yu
https://arxiv.org/abs/2508.18998

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
End-to-end multilingual ASR aims to transcribe speech from different languages into corresponding text, but is often limited by scarce multilingual data. LLM-based ASR aligns speech encoder outputs with LLM input space via a projector and has achieved notable success. However, prior work mainly improves performance by increasing data, with little focus on cross-lingual knowledge sharing. Moreover, a single complex projector struggles to capture both shared and language-specific features effecti…

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli
https://arxiv.org/abs/2509.14001 https…

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a knowledge distillation approach that transfers region-level multimodal semantics from a large vision-language teacher (e.g., LLaVa) into a lightweight vision-only object detector student (e.g., YOLO). A translation module maps student features into a joint space, where the training of the student and translator is guided by a dual-objective loss that enforces both local alignment and global relational consistency. Un…

Schatten-von Neumann classes of tensors of invariant operators
Julio Delgado, Liliana Posada, Michael Ruzhansky
https://arxiv.org/abs/2507.15055 https://…

Schatten-von Neumann classes of tensors of invariant operators
In this work we study Schatten-von Neumann classes of tensor products of invariant operators on Hilbert spaces. In the first part we first deduce some spectral properties for tensors of anharmonic oscillators thanks to the knowledge on corresponding Schatten-von Neumann properties. In the second part we specialised on tensors of invariant operators. In the special case where a suitable Fourier analysis associated to a fixed partition of a Hilbert space into finite dimensional subspaces is avail…

Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models
Wenkai Yu, Jianhang Tang, Yang Zhang, Shanjiang Tang, Kebing Jin, Hankz Hankui Zhuo
https://arxiv.org/abs/2508.11524

Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models
Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and actions. Recently, researchers have explored the effectiveness of leveraging Large Language Models (LLMs) to generate helpful actions and states to prune the search space. However, prior works have largely overlooked integrating LLMs with domain-specific knowledge to ensure valid plans. In this paper, we propose a nove…

Clinical semantics for lung cancer prediction
Luis H. John, Jan A. Kors, Jenna M. Reps, Peter R. Rijnbeek, Egill A. Fridgeirsson
https://arxiv.org/abs/2508.14627 https://…

Clinical semantics for lung cancer prediction
Background: Existing clinical prediction models often represent patient data using features that ignore the semantic relationships between clinical concepts. This study integrates domain-specific semantic information by mapping the SNOMED medical term hierarchy into a low-dimensional hyperbolic space using Poincaré embeddings, with the aim of improving lung cancer onset prediction. Methods: Using a retrospective cohort from the Optum EHR dataset, we derived a clinical knowledge graph from th…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/8]:
- Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space
Hung Nghiep Tran, Atsuhiro Takasu