Tootfinder

Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
Haoxiang Ye, Tao Sun, Qing Ling
https://arxiv.org/abs/2506.09438

Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
Decentralized learning, which facilitates joint model training across geographically scattered agents, has gained significant attention in the field of signal and information processing in recent years. While the optimization errors of decentralized learning algorithms have been extensively studied, their generalization errors remain relatively under-explored. As the generalization errors reflect the scalability of trained models on unseen data and are crucial in determining the performance of …

Khovanov-Rozansky cycle calculus for bipartite links
A. Anokhina, E. Lanina, A. Morozov
https://arxiv.org/abs/2506.08721 https://arxi…

Khovanov-Rozansky cycle calculus for bipartite links
Bipartite calculus is a direct generalization of Kauffman planar expansion from $N=2$ to arbitrary $N$, applicable to the restricted class of knots which are entirely made of antiparallel lock tangles. Whenever applicable, it allows a straightforward generalization of the Khovanov calculus without a need of the technically complicated matrix factorization used for arbitrary $N$ in the Khovanov-Rozansky (KR) approach. The main object here is the $3^{n}$-dimensional hypercube with $n$ being the n…

$\ast$-$\eta$-Ricci solitons on weak Kenmotsu $f$-manifolds
Vladimir Rovenski
https://arxiv.org/abs/2506.08973 https://arxiv.org/pdf/…

$\ast$-$η$-Ricci solitons on weak Kenmotsu $f$-manifolds
Recent interest among geometers in $f$-structures of K. Yano is due to the study of topology and dynamics of contact foliations and generalized A. Weinstein conjectures. Weak metric $f$-structures, introduced by the author and R. Wolak as a generalization of Hermitian structure, as well as $f$-structure allow for a fresh perspective on the classical theory. An important case of such manifolds, which is locally a twisted product, is a weak $βf$-Kenmotsu manifold defined as a generalization of K…

Generalization of Cauchy type theorems for matrix Polynomials
Idrees Qasim
https://arxiv.org/abs/2506.09013 https://arxiv.org/pdf/250…

Generalization of Cauchy type theorems for matrix Polynomials
In this paper, we find bounds for the eigenvalues of matrix polynomials. In particular, we find generalizations of Cauchy's classical Theorem for distribution of eigenvalues of matrix polynomial.

This https://arxiv.org/abs/2409.05191 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly sampled points over an embedded manifold with topological information captured. We prove a generalization gap between the optimal empirical risk and the optimal statistical risk of this GNN, which decreases with the number of sampled points from the manifold and increases with the dimension of the underlying manifold…

Wreath Generalization of Littlewood Reciprocity
Milo Bechtloff Weising
https://arxiv.org/abs/2506.07727 https://arxiv.org/pdf/2506.07…

Wreath Generalization of Littlewood Reciprocity
We generalize Littlewood's reciprocity formula for the restriction coefficients between $\mathrm{GL}_n(\mathbb{C})$ and the symmetric group of permutation matrices $\mathfrak{S}_n$ to the case of the wreath product groups $μ_m^n\rtimes \mathfrak{S}_n $.

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
Jonathan Yang, Chuyuan Kelly Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Tingnan Zhang
https://arxiv.org/abs/2506.06196

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as…

Stochastic Krasnosel skii-Mann Iterations in Banach Spaces with Bregman Distances
Saeed Hashemi Sababe, Ehsan Lotfali Ghasab
https://arxiv.org/abs/2506.08031

Stochastic Krasnosel skii-Mann Iterations in Banach Spaces with Bregman Distances
We propose a generalization of the stochastic Krasnoselskil-Mann $(SKM)$ algorithm to reflexive Banach spaces endowed with Bregman distances. Under standard martingale-difference noise assumptions in the dual space and mild conditions on the distance-generating function, we establish almost-sure convergence to a fixed point and derive non-asymptotic residual bounds that depend on the uniform convexity modulus of the generating function. Extensions to adaptive Bregman geometries and robust noise…

On the Generalization of Data-Assisted Control in port-Hamiltonian Systems (DAC-pH)
Mostafa Eslami, Maryam Babazadeh
https://arxiv.org/abs/2506.07079 https…

On the Generalization of Data-Assisted Control in port-Hamiltonian Systems (DAC-pH)
This paper introduces a hypothetical hybrid control framework for port-Hamiltonian (p$\mathcal{H}$) systems, employing a dynamic decomposition based on Data-Assisted Control (DAC). The system's evolution is split into two parts with fixed topology: Right-Hand Side (RHS)- an intrinsic Hamiltonian flow handling worst-case parametric uncertainties, and Left-Hand Side (LHS)- a dissipative/input flow addressing both structural and parametric uncertainties. A virtual port variable $Π$ serves as the …

ThinkQE: Query Expansion via an Evolving Thinking Process
Yibin Lei, Tao Shen, Andrew Yates
https://arxiv.org/abs/2506.09260 https://…

ThinkQE: Query Expansion via an Evolving Thinking Process
Effective query expansion for web search benefits from promoting both exploration and result diversity to capture multiple interpretations and facets of a query. While recent LLM-based methods have improved retrieval performance and demonstrate strong domain generalization without additional training, they often generate narrowly focused expansions that overlook these desiderata. We propose ThinkQE, a test-time query expansion framework addressing this limitation through two key components: a t…

Reed-Muller Codes for Quantum Pauli and Multiple Access Channels
Dina Abdelhadi, Colin Sandon, Emmanuel Abbe, Ruediger Urbanke
https://arxiv.org/abs/2506.08651

Reed-Muller Codes for Quantum Pauli and Multiple Access Channels
Reed-Muller (RM) codes have undergone significant analytical advancements over the past decade, particularly for binary memoryless symmetric (BMS) channels. We extend the scope of RM codes development and analysis to multiple-access channels (MACs) and quantum Pauli channels, leveraging a unified approach. Specifically, we first derive the achievable rate region for RM codes on so-called Q-MACs, a class of MACs with additive correlated noise. This is achieved via a generalization of the bending…

A viable wormhole model in a five-dimensional spacetime
Peter K. F. Kuhfittig
https://arxiv.org/abs/2506.09111 https://arxiv.org/pdf/…

A viable wormhole model in a five-dimensional spacetime
This paper generalizes two of the author's earlier wormhole solutions that are characterized by an extra spatial dimension. This paper adds the assumption that the components of the line element are functions not only of the radial coordinate $r$ but of the extra coordinate $l$ as well, resulting in a significant generalization. It is shown that the throat of the wormhole can be threaded with ordinary matter and that the unavoidable violation of the null energy condition can be attributed to th…

A generalization of Carter-Payne homomorphisms
Mart\'in Forsberg Conde
https://arxiv.org/abs/2506.05800 https://arxiv.org/pdf/250…

A generalization of Carter-Payne homomorphisms
We construct graded homomorphisms between Specht modules of quiver Hecke algebras of type A that differ by an ``$e$-small'' partition-shaped removable set of nodes by expanding on methods by Lyle and Mathas. Our main result constitutes a full generalization of the classical result by Carter and Payne for Specht modules of the symmetric group.

Generalization of Ramanujan's formula for the sum of half-integer powers of consecutive integers via formal Bernoulli series
Max A. Alekseyev, Rafael Gonzalez, Keryn Loor, Aviad Susman, Cesar Valverde
https://arxiv.org/abs/2506.05961

Generalization of Ramanujan's formula for the sum of half-integer powers of consecutive integers via formal Bernoulli series
Faulhaber's formula expresses the sum of the first $n$ positive integers, each raised to an integer power $p\geq 0$ as a polynomial in $n$ of degree $p+1$. Ramanujan expressed this sum for $p\in\{\frac12,\frac32,\frac52,\frac72\}$ as the sum of a polynomial in $\sqrt{n}$ and a certain infinite series. In the present work, we explore the connection to Bernoulli polynomials, and by generalizing those to formal series, we extend the Ramanujan result to all positive half-integers $p$.

A Generalization of a Classical Geometric Extremum Problem
Petar Kenderov, Oleg Mushkarov, Nikolai Nikolov
https://arxiv.org/abs/2506.07252 https://…

A Generalization of a Classical Geometric Extremum Problem
Let $\partial \,\mathcal{C}$ be the boundary of a compact convex body $\mathcal{C}$ in $\mathbb{R}^n,\, n\geq 2$, and $O$ be an interior point of $\mathcal C$. Every straight line $l$ containing $O$ cuts from $\mathcal{C}$ a segment $[AB]$ with end-points on $\partial \,\mathcal{C}$. It is shown that if $[AB]$ is the shortest such segment, then $\partial \,\mathcal{C}$ is smooth at the points $A$ and $ B$ (i.e. at both of them there is only one supporting hyperplane for $\mathcal{C}$) and, some…

Kinetically Coupled Dark Matter Condensates
Michael W. Toomey, Savvas M. Koushiappas, Stephon Alexander
https://arxiv.org/abs/2506.08076 https://

Kinetically Coupled Dark Matter Condensates
Dark matter consisting of ultralight bosons can form a macroscopic Bose-Einstein condensate with distinctive observational signatures. While this possibility has been extensively studied for axions and axion-like particles $-$ pseudoscalars with masses protected by shift symmetry $-$ realistic models from string theory and other higher-dimensional theories predict more complex structures. Here we investigate a two-field generalization where an axion couples to a moduli field through its kinetic…

This https://arxiv.org/abs/2506.03100 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard…

This https://arxiv.org/abs/2405.06912 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A simple model for twisted arrow $\infty$-categories
Twisted arrow $\infty$-categories of $(\infty,1)$-categories were introduced by Lurie, and they have various applications in higher category theory. Abellán García and Stern gave a generalization to twisted arrow $\infty$-categories of $(\infty,2)$-categories. In this paper we introduce another simple model for twisted arrow $\infty$-categories of $(\infty,2)$-categories.

This https://arxiv.org/abs/2505.22942 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framew…

On the exact solutions of a two-dimensional hydrogen atom in a constant magnetic field
Francisco M. Fern\'andez
https://arxiv.org/abs/2506.07765 https:…

On the exact solutions of a two-dimensional hydrogen atom in a constant magnetic field
We analyse the exact solutions to some quantum-mechanical models derived recently by means of a generalization of the Frobenius method. In particular, we carry out an interpretation of the polynomial solutions obtained for the two-dimensional hydrogen atom in a constant magnetic field by comparing the exact solutions with numerical results provided by the Rayleigh-Ritz method.

TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
Zengjue Chen, Runliang Niu, He Kong, Qi Wang
https://arxiv.org/abs/2506.08440

TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
Recent advances in Vision-Language-Action (VLA) model have demonstrated strong generalization capabilities across diverse scenes, tasks, and robotic platforms when pretrained at large-scale datasets. However, these models still require task-specific fine-tuning in novel environments, a process that relies almost exclusively on supervised fine-tuning (SFT) using static trajectory datasets. Such approaches neither allow robot to interact with environment nor do they leverage feedback from live ex…

Exploring Length Generalization For Transformer-based Speech Enhancement
Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah, Haizhou Li
https://arxiv.org/abs/2506.06697

Exploring Length Generalization For Transformer-based Speech Enhancement
Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios, speech enhancement models are often required to perform on noisy speech at run-time that is substantially longer than the training utterances. It remains a challenge how a Transformer-based speech enhancement model can generalize to long speech utterances. I…

This https://arxiv.org/abs/2504.19203 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Improving Generalization in MRI-Based Deep Learning Models for Total Knee Replacement Prediction
Knee osteoarthritis (KOA) is a common joint disease that causes pain and mobility issues. While MRI-based deep learning models have demonstrated superior performance in predicting total knee replacement (TKR) and disease progression, their generalizability remains challenging, particularly when applied to imaging data from different sources. In this study, we have shown that replacing batch normalization with instance normalization, using data augmentation, and applying contrastive loss improve…

New Polynomial Identities and Some Consequences
Kunle Adegoke
https://arxiv.org/abs/2506.06617 https://arxiv.org/pdf/2506.06617

New Polynomial Identities and Some Consequences
Using an elementary approach involving the Euler Beta function and the binomial theorem, we derive two polynomial identities; one of which is a generalization of a known polynomial identity. Two well-known combinatorial identities, namely Frisch's identity and Klamkin's identity, appear as immediate consequences of the polynomial identities. We subsequently establish several combinatorial identities, including a generalization of each of Frisch's identity and Klamkin's identity. Finally, we dev…

This https://arxiv.org/abs/2503.04091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Generalization in Federated Learning: A Conditional Mutual Information Framework
Federated learning (FL) is a widely adopted privacy-preserving distributed learning framework, yet its generalization performance remains less explored compared to centralized learning. In FL, the generalization error consists of two components: the out-of-sample gap, which measures the gap between the empirical and true risk for participating clients, and the participation gap, which quantifies the risk difference between participating and non-participating clients. In this work, we apply an i…

pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization
Mrinmay Sen, Chalavadi Krishna Mohan
https://arxiv.org/abs/2506.07159

pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization
Personalized Federated Learning (PFL) enables clients to collaboratively train personalized models tailored to their individual objectives, addressing the challenge of model generalization in traditional Federated Learning (FL) due to high data heterogeneity. However, existing PFL methods often require increased communication rounds to achieve the desired performance, primarily due to slow training caused by the use of first-order optimization, which has linear convergence. Additionally, many o…

This https://arxiv.org/abs/2106.04244 has been replaced.
link: https://scholar.google.com/scholar?q=a

The consistency strength of determinacy when all sets are universally Baire
It is known that the large cardinal strength of the Axiom of Determinacy when enhanced with the hypothesis that all sets of reals are universally Baire is much stronger than the Axiom of Determinacy itself. Sargsyan conjectured it to be as strong as the existence of a cardinal that is both a limit of Woodin cardinals and a limit of strong cardinals. Larson, Sargsyan and Wilson used a generalization of Woodin's derived model construction to show that this conjectured result would be optimal. In …

From Local Updates to Global Balance: A Framework for Distributed Matrix Scaling
Giacomo Aletti, Giovanni Naldi
https://arxiv.org/abs/2506.08035 https://…

From Local Updates to Global Balance: A Framework for Distributed Matrix Scaling
This paper investigates matrix scaling processes in the context of local normalization algorithms and their convergence behavior. Starting from the classical Sinkhorn algorithm, the authors introduce a generalization where only a single row or column is normalized at each step, without restrictions on the update order. They extend Birkhoff's theorem to characterize the convergence properties of these algorithms, especially when the normalization sequence is arbitrary. A novel application is exp…

This https://arxiv.org/abs/2202.01660 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the Complexity of Winner Determination and Strategic Control in Conditional Approval Voting
We focus on a generalization of the classic Minisum approval voting rule, introduced by Barrot and Lang (2016), and referred to as Conditional Minisum (CMS), for multi-issue elections with preferential dependencies. Under this rule, voters are allowed to declare dependencies between different issues, but the price we have to pay for this higher level of expressiveness is that we end up with a computationally hard rule. Motivated by this, we first focus on finding special cases that admit effici…

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Yufa Zhou, Shaobo Wang, Xingyu Dong, Xiangqi Jin, Yifang Chen, Yue Min, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang
https://arxiv.org/abs/2506.00577

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in m…

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
Muhammad Sohail Danish, Muhammad Akhtar Munir, Syed Roshaan Ali Shah, Muhammad Haris Khan, Rao Muhammad Anwer, Jorma Laaksonen, Fahad Shahbaz Khan, Salman Khan
https://arxiv.org/abs/2506.06281

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO tasks, many remain limited by the scale, geographical coverage, and spectral diversity of their training data, factors critical for learning globally transferable representations. In this work, we introduce TerraFM, a scalable self-supervised learning model that l…

This https://arxiv.org/abs/2505.03144 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Soliton resolution, asymptotic stability and Painlevé transcendents in the combined Wadati-Konno-Ichikawa and short-pulse equation
In this paper, we develop a Riemann-Hilbert (RH) approach to the Cauchy problem for the combined Wadati-Konno-Ichikawa and short-pulse (WKI-SP) equation. The solution of the Cauchy problem is first expressed in terms of the solution of a RH problem with direct scattering transform based on the Lax pair. Further through a series of deformations to the RH problem by using the $\bar{\partial}$-generalization of Deift-Zhou steepest descent method, we obtain the long-time asymptotic approximations t…

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Gaurav Chaudhary, Wassim Uddin Mondal, Laxmidhar Behera
https://arxiv.org/abs/2506.09574

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Sample efficiency and exploration remain critical challenges in Deep Reinforcement Learning (DRL), particularly in complex domains. Offline RL, which enables agents to learn optimal policies from static, pre-collected datasets, has emerged as a promising alternative. However, offline RL is constrained by issues such as out-of-distribution (OOD) actions that limit policy performance and generalization. To overcome these limitations, we propose Meta Offline-Online Reinforcement Learning (MOORL), …

Fuzzy Lattice-based Description Logic
Yiwen Ding, Krishna Manoorkar
https://arxiv.org/abs/2506.05833 https://arxiv.org/pdf/2506.05833…

Fuzzy Lattice-based Description Logic
Recently, description logic LE-ALC was introduced for reasoning in the semantic environment of enriched formal contexts, and a polynomial-time tableaux algorithm was developed to check the consistency of knowledge bases with acyclic TBoxes. In this work, we introduce a fuzzy generalization of LE-ALC called LE-FALC which provides a description logic counterpart of many-valued normal non-distributive logic a.k.a. many-valued LE-logic. This description logic can be used to represent and reason a…

This https://arxiv.org/abs/2505.04248 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

On minimal free resolutions of the cover ideals of clique-whiskered graphs
We explicitly construct a minimal free resolution of the cover ideals of clique-whiskered graphs. In particular, Cohen--Macaulay chordal graphs, clique corona graphs, and Cohen--Macaulay Cameron--Walker graphs are examples of clique-whiskered graphs. We also introduce multi-clique-whiskered graphs as a generalization of both clique-whiskered graphs and multi-whisker graphs. We prove that multi-clique-whiskered graphs are vertex decomposable and hence sequentially Cohen--Macaulay. Moreover, we p…

Geometric effects of hyperbolic cohomology classes on K\"ahler manifolds
Francesco Bei, Simone Diverio, Stefano Trapani
https://arxiv.org/abs/2506.09907

Geometric effects of hyperbolic cohomology classes on Kähler manifolds
We introduce the notion of Kähler topologically hyperbolic manifold, as a"topological" generalization of Kähler [Gro91] and weakly Kähler [BDET24] hyperbolic manifolds. Analogously to [BCDT24], we show the birational invariance of this property and then that Kähler topologically hyperbolic manifolds are not uniruled nor bimeromorphic to compact Kähler manifolds with trivial first real Chern class. Then, we prove spectral gap theorems for positive holomorphic Hermitian vector bundles on Kä…

This https://arxiv.org/abs/2502.15786 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding
Decoding functional magnetic resonance imaging (fMRI) signals into text has been a key challenge in the neuroscience community, with the potential to advance brain-computer interfaces and uncover deeper insights into brain mechanisms. However, existing approaches often struggle with suboptimal predictive performance, limited task variety, and poor generalization across subjects. In response to this, we propose MindLLM, a model designed for subject-agnostic and versatile fMRI-to-text decoding. M…

This https://arxiv.org/abs/2412.13751 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Notions of entropy for unitary representations
Several notions of entropy are studied widely in the ergodic theory of probability-preserving actions of countable groups. These include the generalization of Kolmogorov--Sinai entropy for amenable groups using Følner sequences, percolative entropy entropy for general countable groups, and Bowen's sofic entropy for sofic groups. In this work we pursue these notions across the analogy between ergodic theory and representation theory. We arrive at new quantities associated to unitary represent…

On Inverse Problems, Parameter Estimation, and Domain Generalization
Deborah Pereg
https://arxiv.org/abs/2506.06024 https://arxiv.org…

On Inverse Problems, Parameter Estimation, and Domain Generalization
Signal restoration and inverse problems are key elements in most real-world data science applications. In the past decades, with the emergence of machine learning methods, inversion of measurements has become a popular step in almost all physical applications, which is normally executed prior to downstream tasks that often involve parameter estimation. In this work, we analyze the general problem of parameter estimation in an inverse problem setting. First, we address the domain-shift problem b…

This https://arxiv.org/abs/2206.04896 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Formal Definition of Scale-dependent Complexity and the Multi-scale Law of Requisite Variety
Ashby's law of requisite variety allows a comparison of systems with their environments, providing a necessary (but not sufficient) condition for system efficacy: a system must possess at least as much complexity as any set of environmental behaviors that require distinct responses from the system. However, to account for the dependence of a system's complexity on the level of detail -- or scale -- of its description, a multi-scale generalization of Ashby's law is needed. We define a class of c…

Nature: Cortical circuits for cross-modal generalization (in mice) https://www.nature.com/articles/s41467-025-59342-9 "Optogenetic sensory substitution and systematic silencing of these associative areas revealed that a single area in the dorsal stream is necessary an…

Cortical circuits for cross-modal generalization - Nature Communications
Neural mechanisms underlying cross-modal generalization of learned sensorimotor associations are not fully understood. Here authors show that mice use a specialized cortical circuit to generalize learned behaviors between vision and touch. A single region in the dorsal cortex is essential for forming abstract spatial representations that enable cross-modal flexibility.

Solving Convex-Concave Problems with $\tilde{\mathcal{O}}(\epsilon^{-4/7})$ Second-Order Oracle Complexity
Lesi Chen, Chengchang Liu, Luo Luo, Jingzhao Zhang
https://arxiv.org/abs/2506.08362

Solving Convex-Concave Problems with $\tilde{\mathcal{O}}(ε^{-4/7})$ Second-Order Oracle Complexity
Previous algorithms can solve convex-concave minimax problems $\min_{x \in \mathcal{X}} \max_{y \in \mathcal{Y}} f(x,y)$ with $\mathcal{O}(ε^{-2/3})$ second-order oracle calls using Newton-type methods. This result has been speculated to be optimal because the upper bound is achieved by a natural generalization of the optimal first-order method. In this work, we show an improved upper bound of $\tilde{\mathcal{O}}(ε^{-4/7})$ by generalizing the optimal second-order method for convex optimizat…

TD-TOG Dataset: Benchmarking Zero-Shot and One-Shot Task-Oriented Grasping for Object Generalization
Valerija Holomjova, Jamie Grech, Dewei Yi, Bruno Yun, Andrew Starkey, Pascal Mei{\ss}ner
https://arxiv.org/abs/2506.05576

TD-TOG Dataset: Benchmarking Zero-Shot and One-Shot Task-Oriented Grasping for Object Generalization
Task-oriented grasping (TOG) is an essential preliminary step for robotic task execution, which involves predicting grasps on regions of target objects that facilitate intended tasks. Existing literature reveals there is a limited availability of TOG datasets for training and benchmarking despite large demand, which are often synthetic or have artifacts in mask annotations that hinder model performance. Moreover, TOG solutions often require affordance masks, grasps, and object masks for trainin…

This https://arxiv.org/abs/2504.11666 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A note on the second supplementary law of rational power residue symbols
As a natural generalization of the Legendre symbol, the $q$-th power residue symbol $(a/p)_q$ is defined for primes $p$ and $q$ with $p\equiv 1 \bmod q$. In this paper, we generalize the second supplementary law by providing an explicit condition for $(q/p)_q = 1$, when $p$ has a special form $p = \sum_{i=0}^{q-1} m^i n^{q-1-i}$. This condition is expressed in terms of the polylogarithm $\mathrm{Li}_{1-q}(x)$ of negative index. Our proof relies on an argument similar to Lemmermeyer's proof of E…

This https://arxiv.org/abs/2401.12526 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
In this paper, we derive refined generalization bounds for the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs). For the DRM, we focus on two prototype elliptic partial differential equations (PDEs): Poisson equation and static Schrödinger equation on the $d$-dimensional unit hypercube with the Neumann boundary condition. Furthermore, sharper generalization bounds are derived based on the localization techniques under the assumptions that the exact solutions of the PDEs lie …

This https://arxiv.org/abs/2503.00493 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
Recent advancements in language models (LMs) have demonstrated strong capabilities in semantic understanding and contextual modeling, which have flourished in generative speech enhancement (SE). However, many LM-based SE approaches primarily focus on semantic information, often neglecting the critical role of acoustic information, which leads to acoustic inconsistency after enhancement and limited generalization across diverse SE tasks. In this paper, we introduce LLaSE-G1, a LLaMA-based langua…

The Artificial Benchmark for Community Detection with Outliers and Overlapping Communities (ABCD $o^2$)
Jordan Barrett, Ryan DeWolfe, Bogumi{\l} Kami\'nski, Pawe{\l} Pra{\l}at, Aaron Smith, Fran\c{c}ois Th\'eberge
https://arxiv.org/abs/2506.05486

The Artificial Benchmark for Community Detection with Outliers and Overlapping Communities (ABCD+$o^2$)
The Artificial Benchmark for Community Detection (ABCD) graph is a random graph model with community structure and power-law distribution for both degrees and community sizes. The model generates graphs similar to the well-known LFR model but it is faster, more interpretable, and can be investigated analytically. In this paper, we use the underlying ingredients of the ABCD model, and its generalization to include outliers (ABCD+$o$), and introduce another variant that allows for overlapping com…

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Muhammed Ustaomeroglu, Guannan Qu
https://arxiv.org/abs/2506.06179

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in multi-agent reinforcement learning to alleles in genetic sequences, and show that a single layer linear self-attention can efficiently represent, learn, and generalize functions capturing pairwise interactions, including out-of-distribution scenarios. Our analysis r…

Deep Equivariant Multi-Agent Control Barrier Functions
Nikolaos Bousias, Lars Lindemann, George Pappas
https://arxiv.org/abs/2506.07755 https://

Deep Equivariant Multi-Agent Control Barrier Functions
With multi-agent systems increasingly deployed autonomously at scale in complex environments, ensuring safety of the data-driven policies is critical. Control Barrier Functions have emerged as an effective tool for enforcing safety constraints, yet existing learning-based methods often lack in scalability, generalization and sampling efficiency as they overlook inherent geometric structures of the system. To address this gap, we introduce symmetries-infused distributed Control Barrier Functions…

This https://arxiv.org/abs/2502.14948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation
Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available high-quality data. Prior work has shown the potential of synthetic self-instruct data, but naively training on a model's own outputs can cause error accumulation, especially in coding tasks, where generalization may collapse due to overly simple or erroneous training data, highlighting the need for rigorous quality ch…

Field generalization of elliptic Calogero-Moser system in the form of higher rank Landau-Lifshitz model
K. Atalikov, A. Zotov
https://arxiv.org/abs/2506.00938

Field generalization of elliptic Calogero-Moser system in the form of higher rank Landau-Lifshitz model
We prove gauge equivalence between integrable field generalization of the elliptic Calogero-Moser model and the higher rank XYZ Landau-Lifshitz model of vector type on 1+1 dimensional space-time. Explicit formulae for the change of variables are derived, thus providing the Poisson map between these models.

This https://arxiv.org/abs/2501.16144 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A Survey of the Holroyd-Talbot Conjecture
A family of sets is intersecting if every pair of its members has an element in common. Such a family of sets is called a star if some element is in every set of the family. Given a graph $G$, let $μ(G)$ denote the size of the smallest maximal independent set of $G$. In 2005, Holroyd and Talbot conjectured the following generalization of the Erdős-Ko-Rado Theorem: for $1\le r\le μ(G)/2$, there is a maximum size intersecting family of independent $r$-sets that is a star. In this paper we pres…

Multi-Modal Large Models Based Beam Prediction: An Example Empowered by DeepSeek
Yizhu Zhao, Li Yu, Lianzheng Shi, Jianhua Zhang, Guangyi Liu
https://arxiv.org/abs/2506.05921

Multi-Modal Large Models Based Beam Prediction: An Example Empowered by DeepSeek
Beam prediction is an effective approach to reduce training overhead in massive multiple-input multiple-output (MIMO) systems. However, existing beam prediction models still exhibit limited generalization ability in diverse scenarios, which remains a critical challenge. In this paper, we propose MLM-BP, a beam prediction framework based on the multi-modal large model released by DeepSeek, with full consideration of multi-modal environmental information. Specifically, the distribution of scatter…

This https://arxiv.org/abs/2505.11370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding Nonlinear Implicit Bias via Region Counts in Input Space
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize implicit bias by the count of connected regions in the input space with the same predicted label. Compared with parameter-dependent metrics (e.g., norm or normalized margin), region count can be better adapted to nonlinear, overparameterized models, because it is de…

This https://arxiv.org/abs/2504.09712 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

The Structural Safety Generalization Problem
LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the target by requiring desirable tractability properties of attacks to study: explainability, transferability between models, and transferability between goals. We perform red-teaming within this framework by uncovering new vulnerabilities to multi-turn, multi-im…

This https://arxiv.org/abs/2501.00296 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained …

This https://arxiv.org/abs/2503.01779 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Curvature, macroscopic dimensions, and symmetric products of surfaces
We present a detailed study of the curvature and symplectic asphericity properties of symmetric products of surfaces. We show that these spaces can be used to answer nuanced questions arising in the study of closed Riemannian manifolds with positive scalar curvature. For example, we prove that symmetric products of surfaces sharply distinguish between two distinct notions of macroscopic dimension introduced by Gromov and the second-named author. As a natural generalization of this circle of ide…

A remark on Continuous K-theory and Fourier-Sato transform
Bingyu Zhang
https://arxiv.org/abs/2506.02329 https://arxiv.org/pdf/2506.0…

A remark on Continuous K-theory and Fourier-Sato transform
In this note, we prove a generalization of Efimov's computation for the universal localizing invariant of categories of sheaves with certain microsupport constraints. The proof is based on certain categorical equivalences given by the Fourier-Sato transform, which is different from the original proof. As an application, we compute the universal localizing invariant of the category of almost quasi-coherent sheaves on the Novikov toric scheme introduced by Vaintrob.

This https://arxiv.org/abs/2403.10366 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A Graded Schur Lemma and a graded-monoidal structure for induced modules over graded-commutative algebras
We consider algebras and Frobenius algebras, internal to a monoidal category, that are graded over a finite abelian group. For the case that A is a twisted group algebra in a linear abelian monoidal category we obtain a graded generalization of the Schur Lemma for the category of induced A-modules. We further show that if the monoidal category is braided and A is commutative up to a bicharacter of the grading group, then the category of induced A-modules can be endowed with a graded-monoidal st…

A generalization of the ADM mass for asymptotically Euclidean manifolds of weak regularity
Stig Lundgren, Benjamin Meco
https://arxiv.org/abs/2506.02670 ht…

A generalization of the ADM mass for asymptotically Euclidean manifolds of weak regularity
We propose a new definition of the ADM mass for asymptotically Euclidean manifolds inspired by the definition of mass for weakly regular asymptotically hyperbolic manifolds by Gicquaud and Sakovich. This version of the mass allows one to work with metrics of local Sobolev regularity $ W^{1,2}_\text{loc} \cap L^\infty $ and we show, under suitable asymptotic assumptions, that the mass is finite, invariant under a change of coordinates at infinity and that it agrees with the classical ADM mass in…

Generic orbits, normal bases, and generation degree for fields of rational invariants
Ben Blum-Smith, Harm Derksen
https://arxiv.org/abs/2506.05650 https:/…

Generic orbits, normal bases, and generation degree for fields of rational invariants
For a linear representation of a finite group in coprime characteristic, we bound the degrees of the invariant polynomials needed to generate the field of rational invariants as a field, in terms of the degrees of the polynomials needed to span the field of rational functions as a vector space over the invariant field. This provides a far-reaching generalization of a recent result of Edidin and Katz.

Strong stability of linear delay-difference equations
Felipe Gon\c{c}alves Netto, Yacine Chitour, Guilherme Mazanti
https://arxiv.org/abs/2506.05002 https:…

Strong stability of linear delay-difference equations
This paper considers linear delay-difference equations, that is, equations relating the state at a given time with its past values over a given bounded interval. After providing a well-posedness result and recalling Hale--Silkowski Criterion for strong stability in the case of equations with finitely many pointwise delays, we propose a generalization of the notion of strong stability to the more general class of linear delay-difference equations with an integral term defined by a matrix-valued …

This https://arxiv.org/abs/2103.01285 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the intersection cohomology of the moduli of $\mathrm{SL}_n$-Higgs bundles on a curve
We explore the cohomological structure for the (possibly singular) moduli of $\mathrm{SL}_n$-Higgs bundles for arbitrary degree on a genus g curve with respect to an effective divisor of degree >2g-2. We prove a support theorem for the $\mathrm{SL}_n$-Hitchin fibration extending de Cataldo's support theorem in the nonsingular case, and a version of the Hausel-Thaddeus topological mirror symmetry conjecture for intersection cohomology. This implies a generalization of the Harder-Narasimhan theor…

A subset generalization of the Erd\H{o}s-Kac theorem over number fields with applications
Sourabhashis Das, Wentang Kuo, Yu-Ru Liu
https://arxiv.org/abs/2506.03215

A subset generalization of the Erdős-Kac theorem over number fields with applications
Let $ω(n)$ denote the number of distinct prime factors of a natural number $n$. In 1940, Erdős and Kac established that $ω(n)$ obeys the Gaussian distribution over natural numbers. In 2004, the third author generalized their theorem to all abelian monoids. In this work, we extend the work of the third author to any subset of the set of ideals of a number field satisfying some additional conditions. Finally, we apply this theorem to prove the Erdős-Kac theorem over $h$-free and over $h$-full…

Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity
Jun-Pyo Hong, Hyowoon Seo, Kisong Lee
https://arxiv.org/abs/2506.06090

Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity
The conventional FL methods face critical challenges in realistic wireless edge networks, where training data is both limited and heterogeneous, often leading to unstable training and poor generalization. To address these challenges in a principled manner, we propose a novel wireless FL framework grounded in Bayesian inference. By virtue of the Bayesian approach, our framework captures model uncertainty by maintaining distributions over local weights and performs distribution-level aggregation …

This https://arxiv.org/abs/2502.12089 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a combinatorially large number of novel data? What signal in the data is exploited to learn those rules? We investigate these questions in the context of diffusion models both theoretically and empirically. Theoretically, we consider a simple probabilistic context-free grammar - a tree-like graphical model used to represe…

A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair
Zanis Ali Khan, Aayush Garg, Qiang Tang
https://arxiv.org/abs/2506.04987 https://…

A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair
Software vulnerabilities pose significant security threats, requiring effective mitigation. While Automated Program Repair (APR) has advanced in fixing general bugs, vulnerability patching, a security-critical aspect of APR remains underexplored. This study investigates pre-trained language models, CodeBERT and CodeT5, for automated vulnerability patching across six datasets and four languages. We evaluate their accuracy and generalization to unknown vulnerabilities. Results show that while bot…

This https://arxiv.org/abs/2505.02515 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization
Traditional domain generalization approaches predominantly focus on leveraging target domain-aware features while overlooking the critical role of source domain-specific characteristics, particularly in federated settings with inherent data isolation. To address this gap, we propose the Federated Source Domain Awareness Framework (FedSDAF), the first method to systematically exploit source domain-aware features for enhanced federated domain generalization (FedDG). The FedSDAF framework consists…

Enumerating planar stuffed maps as hypertrees of mobiles
Nathan Pagliaroli
https://arxiv.org/abs/2506.06086 https://arxiv.org/pdf/250…

Enumerating planar stuffed maps as hypertrees of mobiles
A planar stuffed map is an embedding of a graph into the 2-sphere $S^{2}$, considered up to orientation-preserving homeomorphisms, such that the complement of the graph is a collection of disjoint topologically connected components that are each homeomorphic to $S^{2}$ with multiple boundaries. This is a generalization of planar maps whose complement of the graph is a collection of disjoint topologically connected components that are each homeomorphic to a disc. In this work, we construct a bij…

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
Chen Bao, Chuanbing Huo, Qinyu Chen, Chang Gao
https://arxiv.org/abs/2506.06566

AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically combines standard and aphasic speech at varying ratios, enabling robust generalization, and a GPT-4-based reference enhancement method that refines noisy aphasic transcripts, improving supervision quality. We conduct extensive experiments across multiple data mix…

This https://arxiv.org/abs/2411.06842 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation
Fetal brain tissue segmentation in magnetic resonance imaging (MRI) is a crucial tool that supports understanding of neurodevelopment, yet it faces challenges due to the heterogeneity of data coming from different scanners and settings, as well as data scarcity. Recent approaches based on domain randomization, like SynthSeg, have shown great potential for single-source domain generalization by simulating images with randomized contrast and image resolution from the label maps. In this work, we …

Where Do We Look When We Teach? Analyzing Human Gaze Behavior Across Demonstration Devices in Robot Imitation Learning
Yutaro Ishida, Takamitsu Matsubara, Takayuki Kanai, Kazuhiro Shintani, Hiroshi Bito
https://arxiv.org/abs/2506.05808

Where Do We Look When We Teach? Analyzing Human Gaze Behavior Across Demonstration Devices in Robot Imitation Learning
Imitation learning for acquiring generalizable policies often requires a large volume of demonstration data, making the process significantly costly. One promising strategy to address this challenge is to leverage the cognitive and decision-making skills of human demonstrators with strong generalization capability, particularly by extracting task-relevant cues from their gaze behavior. However, imitation learning typically involves humans collecting data using demonstration devices that emulate…

The Free Functional Calculus in General
Julian Bushelli
https://arxiv.org/abs/2506.00170 https://arxiv.org/pdf/2506.00170

The Free Functional Calculus in General
The classical theory of free analysis generalizes the noncommutative (nc) polynomials and rational functions, easily providing such results as an nc analogue of the Jacobian conjecture. However, the classical theory misses out on important functions, such as the Schur complement. This paper presents a generalization of free functions, viewing them as a natural categorial structure: functors between functor categories that commute with natural transformation. We study this construction on genera…

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, Kang Liu
https://arxiv.org/abs/2506.01710

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL)…

This https://arxiv.org/abs/2501.07198 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Large charge operators at large spin from relativistically rotating vortices
We study the ground states of CFTs with a global $U(1)$ symmetry on $\mathbb{R}\times S^2$ in the regime of large charge $Q$ and large angular momentum $J$, using large charge EFT. We find that in the range $Q \ll J \ll Q^2$, the ground state solution is a superfluid densely populated with vortices rotating at a constant angular velocity $Ω$. This is a relativistic generalization of the known (non-relativistic) rigid rotation phase, which corresponds to the small $Ω$ limit of our solution. In…

This https://arxiv.org/abs/2502.05206 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Safety at Scale: A Comprehensive Survey of Large Model Safety
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raisin…

Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
Xiyu Zhao, Qimei Cui, Ziqiang Du, Weicai Li, Xi Yu, Wei Ni, Ji Zhang, Xiaofeng Tao, Ping Zhang
https://arxiv.org/abs/2506.02422

Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). Little attention has been given to wireless PFL (WPFL), where privacy concerns arise. Performance fairness of PL models is another challenge resulting from communication bottlenecks in WPFL. This paper exploits quantization errors to enhance the privacy of WPFL and proposes a novel quantization-assisted Gaussian differ…

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
Tobias W\"urth, Niklas Freymuth, Gerhard Neumann, Luise K\"arger
https://arxiv.org/abs/2506.06045

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
Graph-based learned simulators have emerged as a promising approach for simulating physical systems on unstructured meshes, offering speed and generalization across diverse geometries. However, they often struggle with capturing global phenomena, such as bending or long-range correlations, and suffer from error accumulation over long rollouts due to their reliance on local message passing and direct next-step prediction. We address these limitations by introducing the Rolling Diffusion-Batched …

Optimal T depth quantum circuits for implementing arbitrary Boolean functions
Suman Dutta, Anik Basu Bhaumik, Anupam Chattopadhyay, Subhamoy Maitra
https://arxiv.org/abs/2506.01542

Optimal T depth quantum circuits for implementing arbitrary Boolean functions
In this paper we present a generic construction to obtain an optimal T depth quantum circuit for any arbitrary $n$-input $m$-output Boolean function $f: \{0,1\}^n \rightarrow \{0,1\}^m$ having algebraic degree $k\leq n$, and it achieves an exact Toffoli (and T) depth of $\lceil \log_2 k \rceil$. This is a broader generalization of the recent result establishing the optimal Toffoli (and consequently T) depth for multi-controlled Toffoli decompositions (Dutta et al., Phys. Rev. A, 2025). We achie…

Generalizable, real-time neural decoding with hybrid state-space models
Avery Hee-Woon Ryoo, Nanda H. Krishna, Ximeng Mao, Mehdi Azabou, Eva L. Dyer, Matthew G. Perich, Guillaume Lajoie
https://arxiv.org/abs/2506.05320

Generalizable, real-time neural decoding with hybrid state-space models
Real-time decoding of neural activity is central to neuroscience and neurotechnology applications, from closed-loop experiments to brain-computer interfaces, where models are subject to strict latency constraints. Traditional methods, including simple recurrent neural networks, are fast and lightweight but often struggle to generalize to unseen data. In contrast, recent Transformer-based approaches leverage large-scale pretraining for strong generalization performance, but typically have much l…

A study on Heisenberg-Weyl linear maps
Saikat Patra, Bihalan Bhattacharya
https://arxiv.org/abs/2506.05097 https://arxiv.org/pdf/2506…

A study on Heisenberg-Weyl linear maps
Heisenberg-Weyl operators provide a Hermitian generalization of Pauli operators in higher dimensions. Positive maps arising from Heisenberg-Weyl operators have been studied along with several algebraic and spectral properties of Heisenberg-Weyl observables. This allows to generalize the study of Pauli type maps in higher dimesional algebra of operators.

LightGTS: A Lightweight General Time Series Forecasting Model
Yihang Wang, Yuying Qiu, Peng Chen, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
https://arxiv.org/abs/2506.06005

LightGTS: A Lightweight General Time Series Forecasting Model
Existing works on general time series forecasting build foundation models with heavy model parameters through large-scale multi-source pre-training. These models achieve superior generalization ability across various datasets at the cost of significant computational burdens and limitations in resource-constrained scenarios. This paper introduces LightGTS, a lightweight general time series forecasting model designed from the perspective of consistent periodical modeling. To handle diverse scales…

UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models
Zewen Yang, Xiaobing Dai, Dian Yu, Qianru Li, Yu Li, Valentin Le Mesle
https://arxiv.org/abs/2506.02955

UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of constraints, such as collision avoidance and dynamic consistency, which are often treated separately or only partially considered. This paper proposes UniConFlow, a unified flow matching (FM) based framework for trajectory generation that systematically incorp…

Higher-dimensional generalization of Youngs' theorem and circular colorings
Kengo Enami, Takahiro Matsushita
https://arxiv.org/abs/2505.23562 https://

Higher-dimensional generalization of Youngs' theorem and circular colorings
In 1996, Youngs proved that any quadrangulation of the real projective plane is not 3-chromatic. This result has been extended in various directions over the years, including to other non-orientable closed surfaces, higher-dimensional analogues of quadrangulations and circular colorings. In this paper, we provide a generalization which yields some of these extensions of Youngs' theorem.

This https://arxiv.org/abs/2501.18564 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages multi-reso…

This https://arxiv.org/abs/2409.04108 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

An Extension of the Adversarial Threat Model in Quantitative Information Flow
In this paper, we propose an extended framework for quantitative information flow (QIF), aligned with the previously proposed core-concave generalization of entropy measures, to include adversaries that use Kolmogorov-Nagumo $f$-mean to infer secrets in a private system. Specifically, in our setting, an adversary uses Kolmogorov-Nagumo $f$-mean to compute its best actions before and after observing the system's randomized outputs. This leads to generalized notions of prior and posterior vulnera…

This https://arxiv.org/abs/2401.16310 has been replaced.
link: https://scholar.google.com/scholar?q=a

An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors
Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false positive rates, and coarse detection granularity. Large Language Models (LLMs) have been considered promising candidates for addressing those challenges. In this study, we conducted an empirical study to explore the potential of LLMs in detecting security defect…

This https://arxiv.org/abs/2505.08549 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A generalization of Dumas irreducibility criterion
Using Newton polygons, a key factorization result for polynomials over discrete valuation domains is proved, which in particular yields new irreducibility criteria including a generalization of the classical irreducibility criterion of Dumas.

This https://arxiv.org/abs/2410.12134 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Distributionally Robust Newsvendor on a Metric
We consider a fundamental generalization of the classical newsvendor problem where the seller needs to decide on the inventory of a product jointly for multiple locations on a metric as well as a fulfillment policy to satisfy the uncertain demand that arises sequentially over time after the inventory decisions have been made. To address the distributional ambiguity, we consider a distributionally robust setting where the decision-maker only knows the mean and variance of the demand, and the goa…

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis
https://arxiv.org/abs/2506.01196

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and multi-view RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On …

The Telephone Exchange Problem Revisited: A Combinatorial Approach
Sithembele Nkonkobe
https://arxiv.org/abs/2506.05145 https://arxiv…

The Telephone Exchange Problem Revisited: A Combinatorial Approach
In this study we revisit the telephone exchange problem. We discuss a generalization of the telephone exchange problem by discuss two generalizations of the Bessel polynomials. We study combinatorial properties of these polynomials, and show how the numbers are related to the well known Whitney numbers and Dowling numbers

This https://arxiv.org/abs/2504.00804 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

The prime number theorem over integers of power-free polynomial values
Let $f(x)\in \mathbb{Z}[x]$ be an irreducible polynomial of degree $d\ge 1$. Let $k\ge2$ be an integer. The number of integers $n$ such that $f(n)$ is $k$-free is widely studied in the literature. In principle, one expects that $f(n)$ is $k$-free infinitely often, if $f$ has no fixed $k$-th power divisor. In 2022, Bergelson and Richter established a new dynamical generalization of the prime number theorem (PNT). Inspired by their work, one may expect that this generalization of the PNT also hol…

This https://arxiv.org/abs/2410.06123 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Supersingular elliptic curves, quaternion algebras and applications to cryptography
This paper contains a survey of supersingular isogeny graphs associated to supersingular elliptic curves and their various applications to cryptography. Within limitation of space, we attempt to address a broad audience and make this part widely accessible. For those graphs we also present three recent results and sketch their proofs. We then discuss a generalization to superspecial isogeny graphs associated to superspecial abelian varieties with real multiplication. These graphs were introduce…

This https://arxiv.org/abs/2505.00812 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperp…

Strongly regular and strongly walk-regular graphs that admit perfect state transfer
Sho Kubota, Hiroto Sekido, Harunobu Yata, Kiyoto Yoshino
https://arxiv.org/abs/2506.02530

Strongly regular and strongly walk-regular graphs that admit perfect state transfer
We study perfect state transfer in Grover walks on two important classes of graphs: strongly regular graphs and strongly walk-regular graphs. The latter class is a generalization of the former. We first give a complete classification of strongly regular graphs that admit perfect state transfer. The only such graphs are the complete bipartite graph $K_{2,2}$ and the complete tripartite graph $K_{2,2,2}$. We then show that, if a genuine strongly walk-regular graph admits perfect state transfer, t…

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
Junting Chen, Haotian Liang, Lingxiao Du, Weiyun Wang, Mengkang Hu, Yao Mu, Wenhai Wang, Jifeng Dai, Ping Luo, Wenqi Shao, Lin Shao
https://arxiv.org/abs/2506.04217

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
The rapid progress of navigation, manipulation, and vision models has made mobile manipulators capable in many specialized tasks. However, the open-world mobile manipulation (OWMM) task remains a challenge due to the need for generalization to open-ended instructions and environments, as well as the systematic complexity to integrate high-level decision making with low-level robot control based on both global scene understanding and current agent state. To address this complexity, we propose a …

This https://arxiv.org/abs/2505.03793 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all candidates due to computational constraints. Despite the recent advances in LLM selection, a fundamental research question largely remains nascent: how can we model the dynamic behaviors of LLMs during fine-tuning, thereby enhancing our understanding of their generalization performance across diverse downstream tasks? In …

Rodrigues Network for Learning Robot Actions
Jialiang Zhang, Haoran Geng, Yang You, Congyue Deng, Pieter Abbeel, Jitendra Malik, Leonidas Guibas
https://arxiv.org/abs/2506.02618

Rodrigues Network for Learning Robot Actions
Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the underlying kinematic structure of articulated systems. To this end, we propose the Neural Rodrigues Operator, a learnable generalization of the classical forward kinematics operation, designed to inject kinematics-aware inductive bias into neural computation. Building on this operator, we design the Rodrigues Network …

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Yifan Hao, Chenlu Ye, Chi Han, Tong Zhang
https://arxiv.org/abs/2506.01919

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive theoretical understanding of this phenomenon remains limited. In this work, we investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability. Taking explorations on a typical sequence model, i.e, H…

This https://arxiv.org/abs/2402.11871 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning
Humans efficiently generalize from limited demonstrations, but robots still struggle to transfer learned knowledge to complex, unseen tasks with longer horizons and increased complexity. We propose the first known method enabling robots to autonomously invent relational concepts directly from small sets of unannotated, unsegmented demonstrations. The learned symbolic concepts are grounded into logic-based world models, facilitating efficient zero-shot generalization to significantly more comple…