Tootfinder

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Liwei Kang, Yue Deng, Yao Xiao, Zhanfeng Mo, Wee Sun Lee, Lidong Bing
https://arxiv.org/abs/2510.08308 h…

First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to performance improvement remains unclear. In this paper, we systematically analyze the rollouts of eight reasoning models on five mathematical datasets. We focus on reflective behaviours where the model has already produced an answer but continues reflecting …

Learning Coulomb Potentials and Beyond with Fermions in Continuous Space
Andreas Bluhm, Marius Lemm, Tim M\"obus, Oliver Siebert
https://arxiv.org/abs/2510.08471 https://…

Learning Coulomb Potentials and Beyond with Fermions in Continuous Space
We present a modular algorithm for learning external potentials in continuous-space free-fermion models including Coulomb potentials in any dimension. Compared to the lattice-based approaches, the continuum presents new mathematical challenges: the state space is infinite-dimensional and the Hamiltonian contains the Laplacian, which is unbounded in the continuum and thus produces an unbounded speed of information propagation. Our framework addresses these difficulties through novel optimization…

Iterated Agent for Symbolic Regression
Zhuo-Yang Song, Zeyu Cai, Shutao Zhang, Jiashen Wei, Jichen Pan, Shi Qiu, Qing-Hong Cao, Tie-Jiun Hou, Xiaohui Liu, Ming-xing Luo, Hua Xing Zhu
https://arxiv.org/abs/2510.08317

Iterated Agent for Symbolic Regression
Symbolic regression (SR), the automated discovery of mathematical expressions from data, is a cornerstone of scientific inquiry. However, it is often hindered by the combinatorial explosion of the search space and a tendency to overfit. Popular methods, rooted in genetic programming, explore this space syntactically, often yielding overly complex, uninterpretable models. This paper introduces IdeaSearchFitter, a framework that employs Large Language Models (LLMs) as semantic operators within an…

Multi-level informed optimization via decomposed Kriging for large design problems under uncertainty
Enrico Ampellio, Blazhe Gjorgiev, Giovanni Sansavini
https://arxiv.org/abs/2510.07904

Multi-level informed optimization via decomposed Kriging for large design problems under uncertainty
Engineering design involves demanding models encompassing many decision variables and uncontrollable parameters. In addition, unavoidable aleatoric and epistemic uncertainties can be very impactful and add further complexity. The state-of-the-art adopts two steps, uncertainty quantification and design optimization, to optimize systems under uncertainty by means of robust or stochastic metrics. However, conventional scenario-based, surrogate-assisted, and mathematical programming methods are not…

🐪 Mathematical models reveal a 'hidden order' in dryland vegetation worldwide
https://phys.org/news/2025-10-mathematical-reveal-hidden-dryland-vegetation.html

Mathematical models reveal a 'hidden order' in dryland vegetation worldwide
If you've ever traveled through drylands, you may have noticed striking vegetation patterns—stripes, spots, or rings—scattered across otherwise barren landscapes. From "tiger bush" in West Africa to the enigmatic "fairy circles" of Namibia, these patterns have long inspired wonder and scientific curiosity.

"Christopher Bishop’s 2006 book “Pattern Recognition and Machine Learning,” arguably one of the triggers of the current popularity of machine learning, is quite literally a book about applied mathematics, diving into probabilities, linear algebra, neural networks, Markov models, and combinatorics. And rightfully so; if your objective is to find a job as an engineer at OpenAI, knowing a thing or two about eigenvalues and eigenvectors is definitely going to be useful."

In Praise Of Mathematics
How much math knowledge does a programmer need to know to fulfill their job? How deep should the mathematical knowledge of full-stack engineers, computer security experts, or large language model engineers be? The spectrum of possible answers to these questions is too large to be useful. Perhaps the eternal answer "it depends" is enough?

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu
https://arxiv.org/abs/2510.11718

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problems. Most LLMs and VLMs are constrained to text-only reasoning chains, while multimodal unified models that can generate interleaved text and images lack the necessary precision and controllability for…

StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
Yuchen Lu, Run Yang, Yichen Zhang, Shuguang Yu, Runpeng Dai, Ziwei Wang, Jiayi Xiang, Wenxin E, Siran Gao, Xinyao Ruan, Yirui Huang, Chenjing Xi, Haibo Hu, Yueming Fu, Qinglan Yu, Xiaobing Wei, Jiani Gu, Rui Sun, Jiaxuan Jia, Fan Zhou
https://arxiv.org/abs/2510.095…

StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
Large language models (LLMs) have demonstrated remarkable advances in mathematical and logical reasoning, yet statistics, as a distinct and integrative discipline, remains underexplored in benchmarking efforts. To address this gap, we introduce \textbf{StatEval}, the first comprehensive benchmark dedicated to statistics, spanning both breadth and depth across difficulty levels. StatEval consists of 13,817 foundational problems covering undergraduate and graduate curricula, together with 2374 re…

Martingale Optimal Transport and Martingale Schr\"odinger Bridges for Calibration of Stochastic Volatility Models
Antonios Zitridis
https://arxiv.org/abs/2510.10860 https:/…

Martingale Optimal Transport and Martingale Schrödinger Bridges for Calibration of Stochastic Volatility Models
Motivated by recent developments in the calibration of stochastic volatility models (SVMs for short), we study continuous-time formulations of martingale optimal transport and martingale Schrödinger bridge problems. We establish duality formulas and also provide alternative proofs, via different techniques, of duality results previously established in the mathematical finance literature. Applications include calibration of SVMs to SPX options, as well as joint calibration to both SPX and VIX o…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

Travel Bans vs. Social Distancing: A Mathematical Analysis
Christian Borgs, Karissa Huang, Geng Zhao
https://arxiv.org/abs/2510.08895 https://arxiv.org/pdf…

Travel Bans vs. Social Distancing: A Mathematical Analysis
As the world grows increasingly connected, infectious disease transmission and outbreaks become a pressing global concern for public health officials and policymakers. While policy interventions to contain and prevent the spread of disease have been proposed and implemented, there has been little rigorous quantitative analysis of the effectiveness of such interventions. In this paper, we study the susceptible-infected-recovered (SIR) infection process on a dynamic network model that models two …

⏰ Electric Vehicle Range Prediction Models: A Review of Machine Learning, Mathematical, and Simulation Approaches
#ev

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Joachim Diederich
https://arxiv.org/abs/2510.09338 https://arxiv.org/pdf/2510.09338

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings. The key innovation is a locality dial, a tunable parameter that dynamically controls the degree of localization during both training and inference without requiring model retraining. This is achieved through group sparsity penalties on attention mechanisms, …

Mathematical basis, phase transitions and singularities of (3 1)-dimensional phi4 scalar field model
Zhidong Zhang
https://arxiv.org/abs/2511.07439 https://arxiv.org/pdf/2511.07439 https://arxiv.org/html/2511.07439
arXiv:2511.07439v1 Announce Type: new
Abstract: The lambda phi4 scalar field model that can be applied to interpret pion-pion scattering and properties of hadrons. In this work, the mathematical basis, phase transitions and singularities of a (3 1)-dimensional (i.e., (3 1)D) phi4 scalar field model are investigated. It is found that as a specific example of topological quantum field theories, the (3 1)D phi4 scalar field model must be set up on the Jordan-von Neumann-Wigner framework and dealt with the parameter space of complex time (or complex temperature). The use of the time average and the topologic Lorentz transformation representing Reidemeister moves ensure the integrability, which takes into account for the contributions of nontrivial topological structures to physical properties of the many-body interacting system. The ergodic hypothesis is violated at finite temperatures in the (3 1)D phi4 scalar field model. Because the quantum field theories with ultraviolet cutoff can be mapped to the models in statistical mechanics, the (3 1)D phi4 scalar field model with ultraviolet cutoff is studied by inspecting its relation with the three-dimensional (3D) Ising model. Furthermore, the direct relation between the coupling K in the 3D Ising model and the bare coupling lambda0 in the (3 1)D phi4 scalar field model is determined in the strong coupling limit. The results obtained in the present work can be utilized to investigate thermodynamic physical properties and critical phenomena of quantum (scalar) field theories.
toXiv_bot_toot

Replaced article(s) found for stat.ME. https://arxiv.org/list/stat.ME/new
[1/1]:
- General Bayesian L2 calibration of mathematical models
Antony M. Overstall, James M. McGree

The Lotka-Volterra Predator-Prey Model with Disturbance
Arhonefe Joseph Ogethakpo, Sunday Amaju Ojobor
https://arxiv.org/abs/2510.09628 https://arxiv.org/p…

The Lotka-Volterra Predator-Prey Model with Disturbance
The forces which drive growth, development, survival and change within an ecological system involving a predator and prey specie are not easily addressed in the field. To better understand the dynamics in the system, ecologists have turned to mathematical models. The predator-prey dynamics of rat and cat population in a given ecology is studied. The mathematical model proposed by Alfred J. Lotka and Vito Volterra called the Lotka-Volterra model for studying predator-prey dynamics is utilized. A…

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Hamed Mahdavi (Pennsylvania State University), Pouria Mahdavinia (Pennsylvania State University), Samira Malek (Pennsylvania State University), Pegah Mohammadipour (Pennsylvania State University), Alireza Hashemi (City University of New York), Majid Daliri (New York University), Alireza Farhadi (Amirkabir University of Technology), Amir Khasahmadi (Autodesk), Niloofar Mireshghallah (Carnegie Mellon …

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these models can grade proofs: detecting errors, judging their severity, and assigning fair scores beyond binary correctness. We study proof-analysis capabilities using a corpus of 90 Gemini 2.5 Pro-generated solutions that we grade on a 1-4 scale with detailed err…

Parametric Sensitivity Analysis: Local and Global Approaches in Stochastic Biochemical Models
Kannon Hossain, Roger Sidje, Fahad Mostafa
https://arxiv.org/abs/2510.10416 https:/…

Parametric Sensitivity Analysis: Local and Global Approaches in Stochastic Biochemical Models
The recent advancements in mathematical modeling of biochemical systems have generated increased interest in sensitivity analysis methodologies. There are two primary approaches for analyzing these mathematical models: the stochastic approach, which employs chemical master equations (CME), and the deterministic approach, which utilizes ordinary differential equations (ODEs). The intractable discrete states present in most biochemical processes render the direct simulation of the CME infeasible.…

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thadd\"aus Wiedemer, Wieland Brendel
https://arxiv.org/abs/2510.11653

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., $\texttt{pass@1024}$), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literatur…

⛐ Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves
#cs

Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves
While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less explored. Pictographic characters, which combine visual form with symbolic structure, provide an ideal test case for this capability. We formulate this visual recognition challenge in the mathematical domain, where each character is represented by an executable program of geometric primitives. This is framed as a program …

CapGeo: A Caption-Assisted Approach to Geometric Reasoning
Yuying Li, Siyi Qian, Hao Liang, Leqi Zheng, Ruichuan An, Yongzhen Guo, Wentao Zhang
https://arxiv.org/abs/2510.09302 …

CapGeo: A Caption-Assisted Approach to Geometric Reasoning
Geometric reasoning remains a core challenge for Multimodal Large Language Models (MLLMs). Even the most advanced closed-source systems, such as GPT-O3 and Gemini-2.5-Pro, still struggle to solve geometry problems reliably, despite exhibiting strong textual reasoning abilities on tasks like the International Mathematical Olympiad (IMO). This gap suggests that the bottleneck lies in understanding geometric diagrams rather than reasoning itself. Since geometric figures can often be faithfully des…

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
Huiyin Xue, Nafise Sadat Moosavi, Nikolaos Aletras
https://arxiv.org/abs/2510.11602 htt…

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions), sequence-dependent activations (where attention weights adapt to each input), a specific mathematical form (dot-product similarities plus softmax weighting), and coupling of queries and keys to evolving hidden states (grounding attention in the current layer). However, th…

RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
Hyundong Jin, Joonghyuk Hahn, Yo-Sub Han
https://arxiv.org/abs/2510.09227 https://…

RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
Large language models (LLMs) show strong performance across natural language processing (NLP), mathematical reasoning, and programming, and recent large reasoning models (LRMs) further emphasize explicit reasoning. Yet their computational limits, particularly spatial complexity constrained by finite context windows, remain poorly understood. While recent works often focus on problems within the NP complexity class, we push the boundary by introducing a novel benchmark grounded in two PSPACE-com…

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
Xingyu Lin, Yilin Wen, En Wang, Du Su, Wenbin Liu, Chenfu Bao, Zhonghou Lv
https://arxiv.org/abs/2510.09369

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods still face challenges rooted in the sparse token rewards inherent to chain-of-thought (CoT). Current approaches often rely on undifferentiated token-level entropy adjustments, which frequently lead to entropy collapse or model collapse. In this work, we propose…

Interplay of sync and swarm: Theory and application of swarmalators
Gourab Kumar Sar, Kevin O'Keeffe, Joao U. F. Lizarraga, Marcus A. M. de Aguiar, Christian Bettstetter, Dibakar Ghosh
https://arxiv.org/abs/2510.09819

Interplay of sync and swarm: Theory and application of swarmalators
Swarmalators, entities that combine the properties of swarming particles with synchronized oscillations, represent a novel and growing area of research in the study of collective behavior. This review provides a comprehensive overview of the current state of swarmalator research, focusing on the interplay between spatial organization and temporal synchronization. After a brief introduction to synchronization and swarming as separate phenomena, we discuss the various mathematical models that hav…

Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa, Frank Schneider, Philipp Hennig, Jose Miguel Hernandez-Lobato
https://arxiv.org/abs/2512.17720 https://arxiv.org/pdf/2512.17720 https://arxiv.org/html/2512.17720
arXiv:2512.17720v1 Announce Type: new
Abstract: Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the model's prior domain knowledge. We address this issue with LaLoRA, a weight-space regularization technique that applies a Laplace approximation to Low-Rank Adaptation. Our approach estimates the model's confidence in each parameter and constrains updates in high-curvature directions, preserving prior knowledge while enabling efficient target-domain learning. By applying the Laplace approximation only to the LoRA weights, the method remains lightweight. We evaluate LaLoRA by fine-tuning a Llama model for mathematical reasoning and demonstrate an improved learning-forgetting trade-off, which can be directly controlled via the method's regularization strength. We further explore different loss landscape curvature approximations for estimating parameter confidence, analyze the effect of the data used for the Laplace approximation, and study robustness across hyperparameters.
toXiv_bot_toot

RAG-Anything: All-in-One RAG Framework
Zirui Guo, Xubin Ren, Lingrui Xu, Jiahao Zhang, Chao Huang
https://arxiv.org/abs/2510.12323 https://arxiv.org/pdf/25…

RAG-Anything: All-in-One RAG Framework
Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalignment exists between current RAG capabilities and real-world information environments. Modern knowledge repositories are inherently multimodal, containing rich combinations of textual content, visual elements, structured tables, and mathematical expressions. Yet existing RAG frameworks are limited to textual content, …