Tootfinder

Please don't upload my code on GitHub
This is a call to free/libre and open source software developers to not upload the work of others to GitHub.
🚫 #NoGitHub

Our guide to every Week 13 NFL game: Matchup previews, predictions, picks and nuggets https://www.espn.com/nfl/story/_/page/viewersguide47085036/nfl-week-13-picks-predictions-schedule-fantasy-football-odds-…

Sur la page Möngönmort de wikipédia francophone
https://fr.wikipedia.org/w/index.php?title=Möngönmort&wprov=rarw1
On trouve comme page associée DaDal

Möngönmort — Wikipédia

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
- SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan

Nun: Shopumbau für den Advent!
Alles was in dieser Rubrik "Advents-Verweigerer-Klexe" #klexadventskalender dazu.)
#artShop #art

Maximum Spread of Vertex Degrees in a Simple Graph
Sergey Dmitrievich Onishchenko
https://arxiv.org/abs/2509.21429 https://arxiv.org/pdf/2509.21429

Maximum Spread of Vertex Degrees in a Simple Graph
We consider the following problem: let $n>k$ be natural numbers, and let $G$ be a graph on $n$ vertices (undirected, without loops or multiple edges). Denote by $h_k(G)$ the number of unordered pairs of vertices in the graph $G$ whose degrees differ by less than $k$. We aim to determine the smallest possible value $f(n,k)$ of the quantity $h_k(G)$. Interest in this question is motivated by the fact that the bipartite analogue of the problem enabled S. Cichomski and F. Petrov to prove the Burdzy…

Learning Admissible Heuristics for A*: Theory and Practice
Ehsan Futuhi, Nathan R. Sturtevant
https://arxiv.org/abs/2509.22626 https://arxiv.org/pdf/2509.2…

Learning Admissible Heuristics for A*: Theory and Practice
Heuristic functions are central to the performance of search algorithms such as A-star, where admissibility - the property of never overestimating the true shortest-path cost - guarantees solution optimality. Recent deep learning approaches often disregard admissibility and provide limited guarantees on generalization beyond the training data. This paper addresses both of these limitations. First, we pose heuristic learning as a constrained optimization problem and introduce Cross-Entropy Admis…

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/2]:
- Deep Learning-Based Cross-Anatomy CT Synthesis Using Adapted nnResU-Net with Anatomical Feature P...
Gonz\'alez, Longuefosse, Benito, Mart\'in, Baldacci

QMill: Representative Quantum Data Generation for Quantum Machine Learning Utility
Jason Ludmir, Ian Martin, Nicholas S. DiBrita, Daniel Leeds, Tirthak Patel
https://arxiv.org/abs/2509.21622

QMill: Representative Quantum Data Generation for Quantum Machine Learning Utility
Quantum machine learning (QML) promises significant speedups, particularly when operating on quantum datasets. However, its progress is hindered by the scarcity of suitable training data. Existing synthetic data generation methods fall short in capturing essential entanglement properties, limiting their utility for QML. To address this, we introduce QMill, a low-depth quantum data generation framework that produces entangled, high-quality samples emulating diverse classical and quantum distribu…

[2025-09-29 Mon (UTC), no new articles found for cs.OH Other Computer Science]
toXiv_bot_toot

Replaced article(s) found for math.MG. https://arxiv.org/list/math.MG/new
[1/1]:
- The Honeycomb Conjecture in normed planes and an alpha-convex variant of a theorem of Dowker
Zsolt L\'angi, Shanshan Wang

Replaced article(s) found for cond-mat.mes-hall. https://arxiv.org/list/cond-mat.mes-hall/new
[1/1]:
- Self-consistent tight-binding calculations with extended Hubbard interactions in rhombohedral mul...
Dongkyu Lee, Wooil Yang, Young-Woo Son, Jeil Jung

Replaced article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Formalizing Mason-Stothers Theorem and its Corollaries in Lean 4
Jineon Baek, Seewoo Lee

I only suggested Microsoft #dropthedot, but it seems the Aspire team has gone full "drop .NET" in its branding.
There's only one mention of “.NET" on the page, and it's from a quote. 🤔
https://aspire.dev/

Aspire—Your Stack, Streamlined
Add Aspire to your stack and streamline your development workflow with code-first control, modularity, and observability.

i've come around to the utility of the livenation-owned setlist.fm, but i still way prefer a loving fan-made setlist/chronology page. i wrote a bit about why & made a list of a few dozen favorites that i return to often (or just thought were swell). what did i miss? https://jessejarnow.com/202…

The Dark Art of Financial Disguise in Web3: Money Laundering Schemes and Countermeasures
Hesam Sarkhosh, Uzma Maroof, Diogo Barradas
https://arxiv.org/abs/2509.21831 https://

The Dark Art of Financial Disguise in Web3: Money Laundering Schemes and Countermeasures
The rise of Web3 and Decentralized Finance (DeFi) has enabled borderless access to financial services empowered by smart contracts and blockchain technology. However, the ecosystem's trustless, permissionless, and borderless nature presents substantial regulatory challenges. The absence of centralized oversight and the technical complexity create fertile ground for financial crimes. Among these, money laundering is particularly concerning, as in the event of successful scams, code exploits, and…

Crosslisted article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[2/2]:
- Rescuing double robustness: safe estimation under complete misspecification
Lorenzo Testa, Francesca Chiaromonte, Kathryn Roeder

Europe, famous for its quality of life.
European Research Council: "The deadline to submit the review [for a 25 page proposal] is: 06 January 2026".
Dudes, I don't even live in the EU, I'm doing you a favor. (They even make clear this is not compensated.)

Silicon Valley, drunk on exponential curves and both terrified and entranced by endless funding rounds,
has given us the "Hero Developer":
a figure who ships features at midnight,
who “moves fast and breaks things,”
who transforms whiteboard scribbles into billion-dollar unicorns through sheer caffeinated will.
We celebrate this person constantly.
They're on the front page of TechCrunch et al.
They keynote conferences.
Their G…

The Rime of the Ancient Maintainer
Every culture produces heroes that reflect its deepest anxieties. The Greeks, terrified of both mortality and immortality, gave us Achilles. The Victorians, haunted by social mobility, gave us the self-made industrialist. And Silicon Valley, drunk on exponential curves and both terrified and entranced by endless funding rounds, has given us

A Theoretical Analysis of Discrete Flow Matching Generative Models
Maojiang Su, Mingcheng Lu, Jerry Yao-Chieh Hu, Shang Wu, Zhao Song, Alex Reneau, Han Liu
https://arxiv.org/abs/2509.22623

A Theoretical Analysis of Discrete Flow Matching Generative Models
We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network to approximate the transformative velocity field. Our analysis establishes a clear chain of guarantees by decomposing the final distribution estimation error. We first prove that the total variation distance between the generated and target distributions is c…

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/2]:
- SGAligner : Cross-Modal Language-Aided 3D Scene Graph Alignment
Binod Singh, Sayan Deb Sarkar, Iro Armeni

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/3]:
- Mental Health Impacts of AI Companions: Triangulating Social Media Quasi-Experiments, User Perspe...
Yunhao Yuan, Jiaxun Zhang, Talayeh Aledavood, Renwen Zhang, Koustuv Saha

[2025-09-29 Mon (UTC), 2 new articles found for cs.ET Emerging Technologies]
toXiv_bot_toot

Crosslisted article(s) found for math.MG. https://arxiv.org/list/math.MG/new
[1/1]:
- Two-ends Furstenberg estimates in the plane
Hong Wang, Shukun Wu
https://

Crosslisted article(s) found for cond-mat.mes-hall. https://arxiv.org/list/cond-mat.mes-hall/new
[1/1]:
- Multiferroicity of oxygen-deficient Hf$_x$Zr$_{1-x}$O$_{2-y}$ nanoparticles
Anna N. Morozovska, et al.

Crosslisted article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration
Davide Bizzaro, Alessandro Daniele

Crosslisted article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/2]:
- Are Hallucinations Bad Estimations?
Hude Liu, Jerry Yao-Chieh Hu, Jennifer Yuntong Zhang, Zhao Song, Han Liu

spent quality snow-eve time with @…'s brilliant & inspiring "other networks," an asynchronous history of non-internet communications. like many readers, i imagine, it made me think of others that might belong & my contribution is... jukeboxes!

Crosslisted article(s) found for math.CO. https://arxiv.org/list/math.CO/new
[1/1]:
- Semi-Random Graphs, Robust Asymmetry, and Reconstruction
Julian Asilis, Xi Chen, Dutch Hansen, Shang-Hua Teng

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
https://arxiv.org/abs/2509.22621 https://arxiv…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and more calibrated responses compared to SFT in data scarce settings, at the cost of more inference compute. In this work, we ask the question: Can ICL's internal computations be used to improve the qual…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/3]:
- Accelerate Creation of Product Claims Using Generative AI
Po-Yu Liang, Yong Zhang, Tatiana Hwa, Aaron Byers

Crosslisted article(s) found for cs.ET. https://arxiv.org/list/cs.ET/new
[1/1]:
- Polymer-based probabilistic bits for thermodynamic computing
Foulger, Bandera, Luzinov, Wanless, Kostal, N\'adazdy, Janovsk\'y, Vil\v{c}\'akov\'a

Comparison estimates on nonsmooth spaces with integrable Ricci lower bounds via localization
Emanuele Caputo, Francesco Nobili, Tommaso Rossi
https://arxiv.org/abs/2509.22514 ht…

Comparison estimates on nonsmooth spaces with integrable Ricci lower bounds via localization
We study comparison estimates on metric measure spaces admitting a synthetic variable Ricci curvature lower bound. We obtain geometric and functional inequalities assuming that the deficit of the lower bound from a given constant is sufficiently integrable. More precisely, we extend to the nonsmooth setting the Bishop-Gromov comparison, the Myers' diameter estimate and the Cheng's comparison principle for Dirichlet eigenvalues. Our analysis relies on the localization method and on one-dimension…

Cryogenic In-Memory Computing with Phase-Change Memory
Davide G. F. Lombardo (IBM Research Europe, Ruschlikon, Switzerland), Siddharth Gautam (IBM Research Europe, Ruschlikon, Switzerland), Alberto Ferraris (IBM Research Europe, Ruschlikon, Switzerland), Manuel Le Gallo (IBM Research Europe, Ruschlikon, Switzerland), Abu Sebastian (IBM Research Europe, Ruschlikon, Switzerland), Ghazi Sarwat Syed (IBM Research Europe, Ruschlikon, Switzerland)

Cryogenic In-Memory Computing with Phase-Change Memory
In-memory computing (IMC) is an emerging non-von Neumann paradigm that leverages the intrinsic physics of memory devices to perform computations directly within the memory array. Among the various candidates, phase-change memory (PCM) has emerged as a leading non-volatile technology, showing significant promise for IMC, particularly in deep learning acceleration. PCM-based IMC is also poised to play a pivotal role in cryogenic applications, including quantum computing and deep space electronics…

Specifying an Obligation Taxonomy in the Non-Markovian Situation Calculus
Kalonji Kalala, Iluju Kiringa, Tet Yeap
https://arxiv.org/abs/2509.22533 https://…

Specifying an Obligation Taxonomy in the Non-Markovian Situation Calculus
Over more than three decades, the Situation Calculus has established itself as an elegant, powerful, and concise formalism for specifying dynamical domains as well as for reasoning about the effects of actions of those domains both in the world and in the mental state of the modelled agents. Moreover, it has also been established that the preconditions of a given action and its effects may be determined entirely by the current situation alone, or they may be determined by past situations as wel…

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
Gen Li, Yuling Yan
https://arxiv.org/abs/2509.22633 https://arxiv.org/p…

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large language models (LLMs) with human preferences. In this paper, we investigate exploration principles for online RLHF, where one seeks to adaptively collect new preference data to refine both the reward model and the policy in a data-efficient manner. By examining existing optimism-b…

Schur log-concavity and the quantum Pascal triangle
\'Alvaro Guti\'errez, Christian Krattenthaler
https://arxiv.org/abs/2509.22648 https://arxiv.or…

Schur log-concavity and the quantum Pascal triangle
We say a sequence $f_0, f_1, f_2, \ldots$ of symmetric functions is Schur log-concave if $f_n^2 - f_{n-1}f_{n+1}$ is Schur positive for all $n\ge1$. We conjecture that a very general class of sequences of Schur functions satisfies this property, and show it for sequences of Schur functions indexed by partitions with growing first part and column. Our findings are related to work of Lam, Postnikov and Pylyavskyy on Schur positivity, and of Butler, Sagan, and the second author on $q$-log-concavit…

Quantile Advantage Estimation for Entropy-Safe Reasoning
Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He
https://arxiv.org/abs/2509.22611 https://

Quantile Advantage Estimation for Entropy-Safe Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries …

Bacterial Gene Regulatory Neural Network as a Biocomputing Library of Mathematical Solvers
Adrian Ratwatte, Samitha Somathilaka, Thanh Cao, Xu Li, Sasitharan Balasubramaniam
https://arxiv.org/abs/2509.21598

Bacterial Gene Regulatory Neural Network as a Biocomputing Library of Mathematical Solvers
Current biocomputing approaches predominantly rely on engineered circuits with fixed logic, offering limited stability and reliability under diverse environmental conditions. Here, we use the GRNN framework introduced in our previous work to transform bacterial gene expression dynamics into a biocomputing library of mathematical solvers. We introduce a sub-GRNN search algorithm that identifies functional subnetworks tailored to specific mathematical calculation and classification tasks by evalu…

[2025-09-29 Mon (UTC), 1 new article found for math.MG Metric Geometry]
toXiv_bot_toot

Selective bulk-boundary correspondence in higher-order topological insulators with anticommuting mirror and chiral symmetries
Suman Aich (IUB), Babak Seradjeh (IUB)
https://arxiv.org/abs/2509.22304

Selective bulk-boundary correspondence in higher-order topological insulators with anticommuting mirror and chiral symmetries
We investigate higher-order topological insulators protected by chiral and mirror symmetries. Using models in the BDI class, which include the prototypical topological quadrupole insulator, we show that breaking mirror symmetries that anticommute with the chiral operator leads to edge-selective bulk-boundary correspondence, with gap closings and bound states appearing only along a subset of boundaries of the same orientation. We define a new edge-sensitive topological invariant, distinguishing …

A Correct by Construction Fault Tolerant Voter for Input Selection of a Control System
Arif Ali AP, Jasine Babu, Deepa Sara John
https://arxiv.org/abs/2509.22236 https://…

A Correct by Construction Fault Tolerant Voter for Input Selection of a Control System
Safety-critical systems use redundant input units to improve their reliability and fault tolerance. A voting logic is then used to select a reliable input from the redundant sources. A fault detection and isolation rules help in selecting input units that can participate in voting. This work deals with the formal requirement formulation, design, verification and synthesis of a generic voting unit for an $N$-modular redundant measurement system used for control applications in avionics systems. …

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Yulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li, Haojia Lin, Zongyi Li, Zihan Xu, Yuchen Shi, Siqi Cai, Renting Rui, Shaofei Cai, Yuzheng Cai, Xuan Zhang, Sheng Ye, Ke Li, Xing Sun
https://arxiv.org/abs/2509.22601

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL training instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation bala…

An exponential upper bound for induced Ramsey numbers
Lucas Arag\~ao, Marcelo Campos, Gabriel Dahia, Rafael Filipe, Jo\~ao Pedro Marciano
https://arxiv.org/abs/2509.22629 https:…

An exponential upper bound for induced Ramsey numbers
The induced Ramsey number $R_{\mathrm{ind}}(H; r)$ of a graph $H$ is the minimum number $N$ such that there exists a graph with $N$ vertices for which all $r$-colourings of its edges contain a monochromatic induced copy of $H$. Our main result is the existence of a constant $C > 0$ such that, for every graph $H$ on $k$ vertices, these numbers satisfy \begin{equation*} R_{\mathrm{ind}}(H; r) \le r^{C r k}. \end{equation*} When $r = 2$, this resolves a conjecture of Erdős from 1975. For $r > 2…

Antitoroidal magnets and anomalous Hall effect
Vladimir A. Zyuzin
https://arxiv.org/abs/2509.22266 https://arxiv.org/pdf/2509.22266

Antitoroidal magnets and anomalous Hall effect
In this paper we introduce a theoretical model of a metallic magnetic system with an antitoroidal order. We introduce a mechanism of indirect interaction of conducting fermions with localized spins based on the tunneling processes of conducting fermions through the localized spins. We demonstrate that interaction of conducting fermions with an antitoroidal order results in odd in momentum spin-momentum locking. The interaction resembles Rashba spin-orbit coupling but breaks the time-reversal sy…

Can Large Language Models Autoformalize Kinematics?
Aditi Kabra, Jonathan Laurent, Sagar Bharadwaj, Ruben Martins, Stefan Mitsch, Andr\'e Platzer
https://arxiv.org/abs/2509.21840

Can Large Language Models Autoformalize Kinematics?
Autonomous cyber-physical systems like robots and self-driving cars could greatly benefit from using formal methods to reason reliably about their control decisions. However, before a problem can be solved it needs to be stated. This requires writing a formal physics model of the cyber-physical system, which is a complex task that traditionally requires human expertise and becomes a bottleneck. This paper experimentally studies whether Large Language Models (LLMs) can automate the formalizati…

Transport Based Mean Flows for Generative Modeling
Elaheh Akbari, Ping He, Ahmadreza Moradipari, Yikun Bai, Soheil Kolouri
https://arxiv.org/abs/2509.22592 https://

Transport Based Mean Flows for Generative Modeling
Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despite their success, these models suffer from slow inference due to the requirement of numerous sequential sampling steps. Recent work has sought to accelerate inference by reducing the number of sampling steps. In particular, Mean Flows offer a one-step generation approach that delivers substantial s…

Quantum spin Hall effect in III-V semiconductors at elevated temperatures: advancing topological electronics
Manuel Meyer, Jonas Baumbach, Sergey Krishtopenko, Adriana Wolf, Monika Emmerling, Sebastian Schmid, Martin Kamp, Benoit Jouault, Jean-Baptiste Rodriguez, Eric Tournie, Tobias M\"uller, Ronny Thomale, Gerald Bastard, Frederic Teppe, Fabian Hartmann, Sven H\"ofling

Quantum spin Hall effect in III-V semiconductors at elevated temperatures: advancing topological electronics
The quantum spin Hall effect (QSHE), a hallmark of topological insulators, enables dissipationless, spin-polarized edge transport and has been predicted in various two-dimensional materials. However, challenges such as limited scalability, low-temperature operation, and the lack of robust electronic transport have hindered practical implementations. Here, we demonstrate the QSHE in an InAs/GaInSb/InAs trilayer quantum well structure operating at elevated temperatures. This platform meets key cr…

Most frequent subsequences in a word
Boris Bukh, Aleksandre Saatashvili
https://arxiv.org/abs/2509.22619 https://arxiv.org/pdf/2509.22619

Most frequent subsequences in a word
We prove that every $n$-letter word over $k$-letter alphabet contains some word as a subsequence in at least $k^{n/4k(1+o(1))}$ many ways, and that this is sharp as $k\to\infty$. For fixed $k$, we show that the analogous number deviates from $μ_k^n$, for some constant $μ_k$, by a factor of at most $n$.

[2025-09-29 Mon (UTC), 3 new articles found for cs.LO Logic in Computer Science]
toXiv_bot_toot

The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
Guannan Lai, Da-Wei Zhou, Xin Yang, Han-Jia Ye
https://arxiv.org/abs/2509.22580 https://

The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in which classes arrive is diverse and unpredictable, and model performance can vary substantially across different sequences. Yet mainstream evaluation protocols calculate mean and variance from only a small set of randomly sampled sequences. Our theoretical anal…

Ab initio study of magnetoresistance effect in $\mathrm{Mn_{3}Sn}/\mathrm{MgO}/\mathrm{Mn_{3}Sn}$ antiferromagnetic tunnel junction
Katsuhiro Tanaka, Yuta Toga, Susumu Minami, Satoru Nakatsuji, Takuya Nomoto, Takashi Koretsune, Ryotaro Arita
https://arxiv.org/abs/2509.21877

Ab initio study of magnetoresistance effect in $\mathrm{Mn_{3}Sn}/\mathrm{MgO}/\mathrm{Mn_{3}Sn}$ antiferromagnetic tunnel junction
The antiferromagnets with the time-reversal symmetry broken magnetic structures possess a finite spin splitting in the momentum space, and may contribute to a realization of a finite tunnel magnetoresistance (TMR) effect even with magnets with zero net spin polarization. In this paper, we study the TMR effect with the noncollinear antiferromagnet $\mathrm{Mn_{3}Sn}$ whose inverse $120^{\circ}$ antiferromagnetic order breaks the time-reversal symmetry. In particular, we employ the representative…

Visibility Polynomial of Some Graph Classes
Tonny K B, Shikhi M
https://arxiv.org/abs/2509.22571 https://arxiv.org/pdf/2509.22571

Visibility Polynomial of Some Graph Classes
Mutual visibility in graphs provides a framework for analysing how vertices can observe one another along shortest paths free of internal obstructions. The visibility polynomial, which enumerates mutual-visibility sets of all orders, has emerged as a central invariant in this study, with both theoretical significance and practical relevance in areas such as surveillance, target tracking, and distributed coordination. While computing this polynomial is computationally demanding, with known compl…

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitris
https://arxiv.org/abs/2509.22576

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical failure mode unique to this setting: the exploration-exploitation cascade failure. This cascade begins with early-stage policy premature convergence, where sparse feedback causes agents to commit to flawed, low-entropy strategies. Subsequently, agents enter late-…

Hexagonal boron nitride/bilayer graphene moir\'e superlattices in the Dirac-material family: energy-band engineering and carrier doping by dual gating
Takuya Iwasaki, Yoshifumi Morita
https://arxiv.org/abs/2509.21759

Hexagonal boron nitride/bilayer graphene moiré superlattices in the Dirac-material family: energy-band engineering and carrier doping by dual gating
We review the fabrication and transport characterization of hexagonal boron nitride (hBN)/Bernal bilayer graphene (BLG) moiré superlattices. Due to the moiré effect, the hBN/BLG moiré superlattices exhibit an energy gap at the charge neutrality point (CNP) even in the absence of a perpendicular electric field. In BLG, the application of a perpendicular electric field tunes the energy gap at the CNP, which contrasts with single-layer graphene and is similar to the family of rhombohedral multi…

Machine learning approaches to seismic event classification in the Ostrava region
Marek Pecha, Michael Skotnica, Jana Ru\v{s}ajov\'a, Bohdan Rieznikov, V\'it Wandrol, Mark\'eta R\"osnerov\'a, Jarom\'ir Knejzl\'ik
https://arxiv.org/abs/2509.22574

Machine learning approaches to seismic event classification in the Ostrava region
The northeastern region of the Czech Republic is among the most seismically active areas in the country. The most frequent seismic events are mining-induced since there used to be strong mining activity in the past. However, natural tectonic events may also occur. In addition, seismic stations often record explosions in quarries in the region. Despite the cessation of mining activities, mine-induced seismic events still occur. Therefore, a rapid differentiation between tectonic and anthropogeni…

Extremal distance spectral radius of graphs with $h$-extra $r$-component connectivity
Daoxia Zhang, Dan Li, Wenxiu Ding
https://arxiv.org/abs/2509.22538 https://

Extremal distance spectral radius of graphs with $h$-extra $r$-component connectivity
For two integers $r\geq 2$ and $h\geq 0$, the $h$-extra $r$-component connectivity of a graph $G$, denoted by $cκ_{r}^{h}$, is defined as the minimum number of vertices whose removal produces a disconnected graph with at least $r$ components, where each component contains at least $h+1$ vertices. Let $\mathcal{G}_{n,δ}^{cκ_{r}^{h}}$ represent the set of graphs of order $n$ with minimum degree $δ$ and $h$-extra $r$-component connectivity $cκ_{r}^{h}$. Hu, Lin, and Zhang [\textit{Discrete Ma…

A comprehensive equivalent circuit model for high overtone bulk acoustic resonators (HBARs)
Vikrant J. Gokhale, Brian P. Downey
https://arxiv.org/abs/2509.21640 https://

A comprehensive equivalent circuit model for high overtone bulk acoustic resonators (HBARs)
This paper presents a new and comprehensive equivalent circuit model for high overtone bulk acoustic resonators (HBARs). HBARs demonstrate several very sharp resonance modes distributed nearly periodically over a very wide frequency range. This spectrum response of HBARs offers unique advantages but poses significant modeling challenges. The proposed circuit incorporates and models the unique physical components of the HBAR: piezoelectric transducer, substrate (a perfectly periodic multimode ca…

From Parameters to Behavior: Unsupervised Compression of the Policy Space
Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
https://arxiv.org/abs/2509.22566 http…

From Parameters to Behavior: Unsupervised Compression of the Policy Space
Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant parameter space $Θ$. This challenge is greatly compounded in multi-task settings. In this work, we develop a novel, unsupervised approach that compresses the policy parameter space $Θ$ into a low-dimensional latent space $\mathcal{Z}$. We train a generativ…

On the D-finiteness of generating functions counting small steps walks in the quadrant
Charlotte Hardouin
https://arxiv.org/abs/2509.22464 https://arxiv.or…

On the D-finiteness of generating functions counting small steps walks in the quadrant
The enumeration of small steps walks confined to the first quadrant of the plane has attracted a lot of attention over the past fifteen years. The associated generating functions are trivariate formal power series in $x,y,t$ where the parameter $t$ encodes the length of the walk while the variables $x,y$ correspond to the coordinates of its ending point. These functions satisfy a functional equation in two catalytic variables. Bousquet-Mélou and Mishna have associated to any small steps mode…

Real Space Imaging of Spin Scattering in Chirality-Induced Spin Selectivity
Jaehyun Lee, Sang-hyuk Lee, Uiseok Jeong, Daryll J. C. Dalayoan, Soobeom Shin, Hu Young Jeong, Hosub Jin, Binghai Yan, Noejung Park, Seon Namgung
https://arxiv.org/abs/2509.21558

Real Space Imaging of Spin Scattering in Chirality-Induced Spin Selectivity
The interaction between electron spin and molecular chirality plays a fundamental role in quantum phenomena, with significant implications for spintronics and quantum computing. The chirality-induced spin selectivity (CISS) effect, where chiral materials preferentially transmit electrons of a particular spin, has sparked intense interest and debate regarding its underlying mechanism. Despite extensive research, the spatial distribution of spin polarization in chiral systems, the key evidence to…

Activation Function Design Sustains Plasticity in Continual Learning
Lute Lillo, Nick Cheney
https://arxiv.org/abs/2509.22562 https://arxiv.org/pdf/2509.22…

Activation Function Design Sustains Plasticity in Continual Learning
In independent, identically distributed (i.i.d.) training regimes, activation functions have been benchmarked extensively, and their differences often shrink once model size and optimization are tuned. In continual learning, however, the picture is different: beyond catastrophic forgetting, models can progressively lose the ability to adapt (referred to as loss of plasticity) and the role of the non-linearity in this failure mode remains underexplored. We show that activation choice is a primar…

Tensor rank of the determinant and periodic triangulations of $\mathbb{R}^n$
Sergey Avvakumov, Roman Karasev
https://arxiv.org/abs/2509.22333 https://arxiv…

Tensor rank of the determinant and periodic triangulations of $\mathbb{R}^n$
We prove that in any $\mathbb{Z}^n$-periodic triangulation of $\mathbb{R}^n$ the number of $\mathbb{Z}^n$-orbits of $n$-dimensional simplices is at least the tensor rank of the $n$th determinant tensor. The latter is known to be at least $\frac{n^{n-1}}{(n-1)!}$, which is approximately $\frac{e^n}{\sqrt{2πn}}$ for large $n$. The triangulation is not assumed to be geometric, meaning that its simplices can be ``curved''. We also provide lower bounds for general spaces. A simplicial cell comple…

Learning to Price Bundles: A GCN Approach for Mixed Bundling
Liangyu Ding, Chenghan Wu, Guokai Li, Zizhuo Wang
https://arxiv.org/abs/2509.22557 https://arx…

Learning to Price Bundles: A GCN Approach for Mixed Bundling
Bundle pricing refers to designing several product combinations (i.e., bundles) and determining their prices in order to maximize the expected profit. It is a classic problem in revenue management and arises in many industries, such as e-commerce, tourism, and video games. However, the problem is typically intractable due to the exponential number of candidate bundles. In this paper, we explore the usage of graph convolutional networks (GCNs) in solving the bundle pricing problem. Specifically,…

List coloring ordered graphs with forbidden induced subgraphs
Marta Piecyk, Pawe{\l} Rz\k{a}\.zewski
https://arxiv.org/abs/2509.22160 https://arxiv.org/pdf…

List coloring ordered graphs with forbidden induced subgraphs
In the List $k$-Coloring problem we are given a graph whose every vertex is equipped with a list, which is a subset of $\{1,\ldots,k\}$. We need to decide if $G$ admits a proper coloring, where every vertex receives a color from its list. The complexity of the problem in classes defined by forbidding induced subgraphs is a widely studied topic in algorithmic graph theory. Recently, Hajebi, Li, and Spirkl [SIAM J. Discr. Math. 38 (2024)] initiated the study of List $3$-Coloring in ordered grap…

ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
Chenyu Liu, Yuqiu Deng, Tianyu Liu, Jinan Zhou, Xinliang Zhou, Ziyu Jia, Yi Ding
https://arxiv.org/abs/2509.22556 h…

ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on large-scale unlabeled data to extract universal representations. While effective, these models lack decoders of comparable capacity, limiting the full utilization of the learned features. To address this issue, we introduce ECHO, a novel decoder-centric LEM p…

JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Guillem Capellera, Luis Ferraz, Antonio Rubio, Alexandre Alahi, Antonio Agudo
https://arxiv.org/abs/2509.22522

JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Generative models often treat continuous data and discrete events as separate processes, creating a gap in modeling complex systems where they interact synchronously. To bridge this gap, we introduce JointDiff, a novel diffusion framework designed to unify these two processes by simultaneously generating continuous spatio-temporal data and synchronous discrete events. We demonstrate its efficacy in the sports domain by simultaneously modeling multi-agent trajectories and key possession events. …

Majority Edge Colouring of Hypergraph
Jiangdong Ai, Feiyu Nan
https://arxiv.org/abs/2509.22157 https://arxiv.org/pdf/2509.22157

Majority Edge Colouring of Hypergraph
Let G = (V, E) be a hypergraph. A 1/k-majority (k+1)-edge-colouring of a hypergraph is an edge-colouring with k+1 colours such that for every vertex v and each colour i, at most floor(d(v)/k) hyperedges incident to v receive colour i. Motivated by a recent work of Pękała and Przybyło on majority edge-colouring in graphs, we prove that every hypergraph G with minimum degree delta(G) >= 2 r k^2 admits a 1/k-majority (k+1)-edge-colouring, where r = max_{e in E} |e|, by extending their…

Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data
Zahid Iqbal
https://arxiv.org/abs/2509.22507 https://

Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data
Federated Learning (FL) has emerged as a promising decentralized learning (DL) approach that enables the use of distributed data without compromising user privacy. However, FL poses several key challenges. First, it is frequently assumed that every client can train the same machine learning models, however, not all clients are able to meet this assumption because of differences in their business needs and computational resources. Second, statistical heterogeneity (a.k.a. non-IID data) poses a m…

Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
Juan Ramirez, Simon Lacoste-Julien
https://arxiv.org/abs/2509.22500 https://

Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
Constrained optimization is a powerful framework for enforcing requirements on neural networks. These constrained deep learning problems are typically solved using first-order methods on their min-max Lagrangian formulation, but such approaches often suffer from oscillations and can fail to find all local solutions. While the Augmented Lagrangian method (ALM) addresses these issues, practitioners often favor dual optimistic ascent schemes (PI control) on the standard Lagrangian, which perform w…

A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches
Samuele Punzo, Silvia Giulia Galfr\`e, Francesco Massafra, Alessandro Maglione, Corrado Priami, Alina S\^irbu
https://arxiv.org/abs/2509.22484

A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches
We present a machine learning pipeline for biomarker discovery in Multiple Sclerosis (MS), integrating eight publicly available microarray datasets from Peripheral Blood Mononuclear Cells (PBMC). After robust preprocessing we trained an XGBoost classifier optimized via Bayesian search. SHapley Additive exPlanations (SHAP) were used to identify key features for model prediction, indicating thus possible biomarkers. These were compared with genes identified through classical Differential Expressi…

OFMU: Optimization-Driven Framework for Machine Unlearning
Sadia Asif, Mohammad Mohammadi Amiri
https://arxiv.org/abs/2509.22483 https://arxiv.org/pdf/2509…

OFMU: Optimization-Driven Framework for Machine Unlearning
Large language models deployed in sensitive applications increasingly require the ability to unlearn specific knowledge, such as user requests, copyrighted materials, or outdated information, without retraining from scratch to ensure regulatory compliance, user privacy, and safety. This task, known as machine unlearning, aims to remove the influence of targeted data (forgetting) while maintaining performance on the remaining data (retention). A common approach is to formulate this as a multi-ob…

Bayesian Transfer Operators in Reproducing Kernel Hilbert Spaces
Septimus Boshoff, Sebastian Peitz, Stefan Klus
https://arxiv.org/abs/2509.22482 https://ar…

Bayesian Transfer Operators in Reproducing Kernel Hilbert Spaces
The Koopman operator, as a linear representation of a nonlinear dynamical system, has been attracting attention in many fields of science. Recently, Koopman operator theory has been combined with another concept that is popular in data science: reproducing kernel Hilbert spaces. We follow this thread into Gaussian process methods, and illustrate how these methods can alleviate two pervasive problems with kernel-based Koopman algorithms. The first being sparsity: most kernel methods do not scale…

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Boshra Ariguib, Mathias Niepert, Andrei Manolache
https://arxiv.org/abs/2509.22468

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on molecular graphs has shown promise, many existing approaches either depend on hand-crafted augmentations or complex generative objectives, and often rely solely on 2D topology, leaving valuable 3D structural information underutilized. To address this gap, we introduce C-FREE (Contrast-Free Representation learning on Ego…

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method
Xinyu Liu, Bei Li, Jiahao Liu, Junhao Ruan, Kechen Jiao, Hongyin Tang, Jingang Wang, Xiao Tong, Jingbo Zhu
https://arxiv.org/abs/2509.22463

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method
High-order numerical methods enhance Transformer performance in tasks like NLP and CV, but introduce a performance-efficiency trade-off due to increased computational overhead. Our analysis reveals that conventional efficiency techniques, such as distillation, can be detrimental to the performance of these models, exemplified by PCformer. To explore more optimizable ODE-based Transformer architectures, we propose the \textbf{I}terative \textbf{I}mplicit \textbf{E}uler \textbf{T}ransformer \text…

Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
Robert Parker, Oscar Dowson, Nicole LoGiudice, Manuel Garcia, Russell Bent
https://arxiv.org/abs/2509.22462

Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and constraints are not exposed to the optimization solver. Compared to the full-space formulation, in which intermediate variables and constraints are exposed to the optimization solver, the reduced-space formulation leads to faster solves and fewer iterations i…

Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
Changhun Kim, Timon Conrad, Redwanul Karim, Julian Oelhaf, David Riebesel, Tom\'as Arias-Vergara, Andreas Maier, Johann J\"ager, Siming Bayer
https://arxiv.org/abs/2509.22458

Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace classic Newton--Raphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via p…

Overclocking Electrostatic Generative Models
Daniil Shlenskii, Alexander Korotin
https://arxiv.org/abs/2509.22454 https://arxiv.org/pdf/2509.22454

Overclocking Electrostatic Generative Models
Electrostatic generative models such as PFGM++ have recently emerged as a powerful framework, achieving state-of-the-art performance in image synthesis. PFGM++ operates in an extended data space with auxiliary dimensionality $D$, recovering the diffusion model framework as $D\to\infty$, while yielding superior empirical results for finite $D$. Like diffusion models, PFGM++ relies on expensive ODE simulations to generate samples, making it computationally costly. To address this, we propose Inve…

Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
Peter Shaw, James Cohan, Jacob Eisenstein, Kristina Toutanova
https://arxiv.org/abs/2509.22445

Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transformers is challenging due to the lack of a principled, universal measure for model complexity. This paper introduces the theoretical notion of asymptotically optimal description length objectives, grounded in the theory of Kolmogorov complexity. We establish that a minimizer of such an objective achieves optimal compre…

Global Convergence in Neural ODEs: Impact of Activation Functions
Tianxiang Gao, Siyuan Sun, Hailiang Liu, Hongyang Gao
https://arxiv.org/abs/2509.22436 https://

Global Convergence in Neural ODEs: Impact of Activation Functions
Neural Ordinary Differential Equations (ODEs) have been successful in various applications due to their continuous nature and parameter-sharing efficiency. However, these unique characteristics also introduce challenges in training, particularly with respect to gradient computation accuracy and convergence analysis. In this paper, we address these challenges by investigating the impact of activation functions. We demonstrate that the properties of activation functions, specifically smoothness a…

The Flood Complex: Large-Scale Persistent Homology on Millions of Points
Florian Graf, Paolo Pellizzoni, Martin Uray, Stefan Huber, Roland Kwitt
https://arxiv.org/abs/2509.22432

The Flood Complex: Large-Scale Persistent Homology on Millions of Points
We consider the problem of computing persistent homology (PH) for large-scale Euclidean point cloud data, aimed at downstream machine learning tasks, where the exponential growth of the most widely-used Vietoris-Rips complex imposes serious computational limitations. Although more scalable alternatives such as the Alpha complex or sparse Rips approximations exist, they often still result in a prohibitively large number of simplices. This poses challenges in the complex construction and in the s…

Learning from Delayed Feedback in Games via Extra Prediction
Yuma Fujimoto, Kenshi Abe, Kaito Ariu
https://arxiv.org/abs/2509.22426 https://arxiv.org/pdf/2…

Learning from Delayed Feedback in Games via Extra Prediction
This study raises and addresses the problem of time-delayed feedback in learning in games. Because learning in games assumes that multiple agents independently learn their strategies, a discrepancy in optimization often emerges among the agents. To overcome this discrepancy, the prediction of the future reward is incorporated into algorithms, typically known as Optimistic Follow-the-Regularized-Leader (OFTRL). However, the time delay in observing the past rewards hinders the prediction. Indeed,…

Partial Parameter Updates for Efficient Distributed Training
Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert
https://arxiv.org/abs/2509.22418 https:…

Partial Parameter Updates for Efficient Distributed Training
We introduce a memory- and compute-efficient method for low-communication distributed training. Existing methods reduce communication by performing multiple local updates between infrequent global synchronizations. We demonstrate that their efficiency can be significantly improved by restricting backpropagation: instead of updating all the parameters, each node updates only a fixed subset while keeping the remainder frozen during local steps. This constraint substantially reduces peak memory us…

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Yongqi Huang, Jitao Zhao, Dongxiao He, Xiaobao Wang, Yawen Li, Yuxiao Huang, Di Jin, Zhiyong Feng
https://arxiv.org/abs/2509.22416 …

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Graph Prompt Learning (GPL) has emerged as a promising paradigm that bridges graph pretraining models and downstream scenarios, mitigating label dependency and the misalignment between upstream pretraining and downstream tasks. Although existing GPL studies explore various prompt strategies, their effectiveness and underlying principles remain unclear. We identify two critical limitations: (1) Lack of consensus on underlying mechanisms: Despite current GPLs have advanced the field, there is no …

Fast-Forward Lattice Boltzmann: Learning Kinetic Behaviour with Physics-Informed Neural Operators
Xiao Xue, Marco F. P. ten Eikelder, Mingyang Gao, Xiaoyuan Cheng, Yiming Yang, Yi He, Shuo Wang, Sibo Cheng, Yukun Hu, Peter V. Coveney
https://arxiv.org/abs/2509.22411

Fast-Forward Lattice Boltzmann: Learning Kinetic Behaviour with Physics-Informed Neural Operators
The lattice Boltzmann equation (LBE), rooted in kinetic theory, provides a powerful framework for capturing complex flow behaviour by describing the evolution of single-particle distribution functions (PDFs). Despite its success, solving the LBE numerically remains computationally intensive due to strict time-step restrictions imposed by collision kernels. Here, we introduce a physics-informed neural operator framework for the LBE that enables prediction over large time horizons without step-by…

MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
Fanjin Meng, Yuan Yuan, Jingtao Ding, Jie Feng, Chonghua Han, Yong Li
https://arxiv.org/abs/2509.22403

MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
Mobility Foundation Models (MFMs) have advanced the modeling of human movement patterns, yet they face a ceiling due to limitations in data scale and semantic understanding. While Large Language Models (LLMs) offer powerful semantic reasoning, they lack the innate understanding of spatio-temporal statistics required for generating physically plausible mobility trajectories. To address these gaps, we propose MoveFM-R, a novel framework that unlocks the full potential of mobility foundation model…

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
Nan Tang, Jing-Cheng Pang, Guanlin Li, Chao Qian, Yang Yu
https://arxiv.org/abs/2509.22402 https://

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise positional information is often unavailable in real-world visual settings due to sensory and perceptual limitations. In this study, we propose a method that implicitly infers spatial distances through keypoints extracted from images. Building on this, we introdu…

Improving accuracy in short mortality rate series: Exploring Multi-step Forecasting Approaches in Hybrid Systems
Filipe C. L. Duarte, Paulo S. G. de Mattos Neto, Paulo R. A. Firmino
https://arxiv.org/abs/2509.22395

Improving accuracy in short mortality rate series: Exploring Multi-step Forecasting Approaches in Hybrid Systems
The decline in interest rates and economic stabilization has heightened the importance of accurate mortality rate forecasting, particularly in insurance and pension markets. Multi-step-ahead predictions are crucial for public health, demographic planning, and insurance risk assessments; however, they face challenges when data are limited. Hybrid systems that combine statistical and Machine Learning (ML) models offer a promising solution for handling both linear and nonlinear patterns. This stud…

SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly
Narada Maugin, Tristan Cazenave
https://arxiv.org/abs/2509.22387 https://arxiv.org/pdf/…

SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly
The Counterfactual Regret Minimization (CFR) algorithm and its variants have enabled the development of pokerbots capable of beating the best human players in heads-up (1v1) cash games and competing with them in six-player formats. However, CFR's computational complexity rises exponentially with the number of players. Furthermore, in games with three or more players, following Nash equilibrium no longer guarantees a non-losing outcome. These limitations, along with others, significantly restric…

(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
Luca Bergamin, Roberto Confalonieri, Fabio Aiolli
https://arxiv.org/abs/2509.22384

(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple scenarios where high performance is not enough to adopt the proposed solution. In this work, a differentiable approximation of $L_0$ regularization is adapted into a logic-based neural network, the Multi-layer Logical Perceptron (MLLP), to study its efficacy in r…

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy
Haibo Wang, Lutfu S. Sua, Jun Huang, Figen Balo, Burak Dolar
https://arxiv.org/abs/2509.22381

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy
Effective credit risk management is fundamental to financial decision-making, necessitating robust models for default probability prediction and financial entity classification. Traditional machine learning approaches face significant challenges when confronted with high-dimensional data, limited interpretability, rare event detection, and multi-class imbalance problems in risk assessment. This research proposes a comprehensive meta-learning framework that synthesizes multiple complementary mod…

Role-Aware Multi-modal federated learning system for detecting phishing webpages
Bo Wang, Imran Khan, Martin White, Natalia Beloff
https://arxiv.org/abs/2509.22369 https://

Role-Aware Multi-modal federated learning system for detecting phishing webpages
We present a federated, multi-modal phishing website detector that supports URL, HTML, and IMAGE inputs without binding clients to a fixed modality at inference: any client can invoke any modality head trained elsewhere. Methodologically, we propose role-aware bucket aggregation on top of FedProx, inspired by Mixture-of-Experts and FedMM. We drop learnable routing and use hard gating (selecting the IMAGE/HTML/URL expert by sample modality), enabling separate aggregation of modality-specific par…

Investigating Faithfulness in Large Audio Language Models
Lovenya Jain, Pooneh Mousavi, Mirco Ravanelli, Cem Subakan
https://arxiv.org/abs/2509.22363 https://

Investigating Faithfulness in Large Audio Language Models
Faithfulness measures whether chain-of-thought (CoT) representations accurately reflect a model's decision process and can be used as reliable explanations. Prior work has shown that CoTs from text-based LLMs are often unfaithful. This question has not been explored for large audio-language models (LALMs), where faithfulness is critical for safety-sensitive applications. Reasoning in LALMs is also more challenging, as models must first extract relevant clues from audio before reasoning over the…

Neural Feature Geometry Evolves as Discrete Ricci Flow
Moritz Hehl, Max von Renesse, Melanie Weber
https://arxiv.org/abs/2509.22362 https://arxiv.org/pdf/2…

Neural Feature Geometry Evolves as Discrete Ricci Flow
Deep neural networks learn feature representations via complex geometric transformations of the input data manifold. Despite the models' empirical success across domains, our understanding of neural feature representations is still incomplete. In this work we investigate neural feature geometry through the lens of discrete geometry. Since the input data manifold is typically unobserved, we approximate it using geometric graphs that encode local similarity structure. We provide theoretical resul…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/6]:
- Nearly Tight Regret Bounds for Profit Maximization in Bilateral Trade
Simone Di Gregorio, Paul D\"utting, Federico Fusco, Chris Schwiegelshohn

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/6]:
- HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/6]:
- Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
Gu, Zhang, Feng, Chen, Fu, Lin, Wang, Sun, Wu, Wang, Wang

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/6]:
- MobiLLM: An Agentic AI Framework for Closed-Loop Threat Mitigation in 6G Open RANs
Prakhar Sharma, Haohuang Wen, Vinod Yegneswaran, Ashish Gehani, Phillip Porras, Zhiqiang Lin

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/6]:
- Foundation models for high-energy physics
Anna Hallin
https://

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/6]:
- Assessment of deep learning models integrated with weather and environmental variables for wildfi...
Jiyeon Kim, Yingjie Hu, Negar Elhami-Khorasani, Kai Sun, Ryan Zhenqi Zhou