Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Monday 7 September

Machine Learning

Temporal-Causal Inference for Reinforcement Learning via Automata Learning

We consider reinforcement learning in environments with dynamics that undergo an irreversible phase transition governed by a hidden temporal pattern. The agent observes the base state but cannot observe the phase directly. We formalize this problem as a two-phase non-Markovian decision process and introduce Temporal-Causal Inference for Reinforcement Learning (TCIRL), a framework that jointly learns a control policy and infers the hidden temporal cause of the phase transition. TCIRL maintains a hypothesis deterministic finite automaton (DFA) to track what phase is active and refines it via counterexample-driven SAT-based synthesis. We prove that the hypothesis converges almost surely to a DFA whose language induces the same dynamics as the cause language, yielding an optimal policy for the original non-Markovian decision process. Experiments on a genetic therapy gridworld and a traffic signal environment show that TCIRL recovers the correct cause DFA and matches the full-information baseline in both domains.
Read the full abstract

All authors Jan Corazza, Daniil Kaminskyi, Simon Lutz, Patrick Nossol, Hadi Partovi Aria, Zhe Xu, Daniel Neider

Computer Vision

Latent-to-Latent Flow for Volumetric Stochastic Segmentation

Uncertainty arising from inter-observer variability in medical image segmentation plays an important role in developing treatment plans. Research in this area is inhibited by the lack of multiple annotations for large-scale medical datasets, especially for volumetric data, which suffers from additional scaling and computational complexity challenges. Flow matching has emerged as a powerful framework for generative modelling and has also been demonstrated to maintain strong performance when working with latent representations of images. In this work, we introduce a latent-to-latent flow technique for stochastic segmentation of medical volumes via encoded representations of both the image and label space. We evaluate our method on two challenging applications covering delineation uncertainty for radiotherapy planning and multiple organ structure segmentation, improving efficiency up to 14x compared with full resolution models while maintaining clinically relevant performance.
Read the full abstract

All authors Omar Todd, Sooha Kim, Raghav Mehta, Katherine Mackay, David Bernstein, Alexandra Taylor, Fabio De Sousa Ribeiro, Ben Glocker

Group Theory

Enumeration of orientably-regular maps with automorphism group $\PGam(2,2^p)$ for prime $p$

With help of group characters we enumerate orientably-regular maps of a given type with automorphism group isomorphic to $\PGam(2,2^p)$ for prime $p$.
Read the full abstract

All authors Yan-Quan Feng, Soňa Pavlíková, Jozef Širáň, Chihao Wang, Jin-Xin Zhou

Analysis of PDEs

Geometric regularity for semi-convex viscosity solutions to the special Lagrangian equation

We prove that the gradient graph of any $W^{2,1}$ semi-convex viscosity solution to the three-dimensional subcritical special Lagrangian equation is area-minimizing and smooth. Furthermore, we prove the smoothness of $W^{2,1}\cap C^{1,1/3+}$ semi-convex viscosity solutions. This yields progress on the conjecture proposed by Wang–Yuan [WY13]. The corresponding results in higher dimensions are also established.
Read the full abstract

Combinatorics

Real-rootedness of the $\tau$-polynomial under graph joins

For a simple graph $G$ with $n$ vertices, write its chromatic polynomial in the rising factorial basis as $$ \chi_G(x)=\sum_{i=0}^{n}(-1)^{n-i}c_i(G)\langle x\rangle_i,$$ where $ \langle x\rangle_i=x(x+1)\cdots(x+i-1).$ The associated $\tau$-polynomial $$ \tau_G(x)=\sum_{i=0}^{n}c_i(G)x^i $$ was defined and systematically investigated by Brenti in 1992. In this paper, we prove that if the $\tau$-polynomials of two vertex-disjoint simple graphs $G$ and $H$ have only real zeros, then the $\tau$-polynomial of their join $G\vee H$ has only real zeros. This settles a conjecture posed by Brenti, Royle and Wagner since 1994.
Read the full abstract

All authors Mingyang Kang, Zhixin Liu, Sophie C.C. Sun, Philip B. Zhang

Disordered Systems and Neural Networks

Graph neural networks and the energetic cavity method for combinatorial optimization

We study the use of graph neural networks (GNNs) for finding approximate ground states of Ising models. Efficiently finding these ground states is of broad significance because many combinatorial optimization problems can be formulated as an Ising model with the appropriate choice of couplings and fields. Exactly solving these problems is hard but there are many good heuristic methods. A lineage of these heuristics build from mean-field approximations: one approach uses the leading eigenvector of an appropriately defined matrix, another is the min-sum algorithm, also known as the energetic cavity method. Without modification, GNNs perform worse than both of these methods. We consider small modifications to the GNN to incorporate these heuristics and find that this considerably improves performance. While the modified approach is competitive against other deep-learning approaches, we still find that simulated annealing is reliably at least as good as deep learning methods for the same computational cost.
Read the full abstract

Computer Vision

Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection

How can vision-language models help video anomaly detection (VAD) when surveillance data remain distributed, weakly labeled, and resource-constrained? Most weakly supervised VAD methods assume centralized training; recent VLM-based extensions further rely on dense inference, generated explanations, or additional adaptation. We introduce a lightweight federated MIL-VLM cascade in which only a compact MIL scorer is trained across clients, while a frozen VLM verifies high-scoring suspect segments post hoc. We study two VLM feedback interfaces: parsed text-generation decisions and a logit-based interface that extracts a continuous anomaly score from next-token Yes/No probabilities. Experiments on UCF-Crime with InternVL3.5-2B and Qwen3-VL-2B-Instruct show that text-generation verification can improve frame-level AUC after diagnostic temporal post-processing, but remains sensitive to prompts, parsers, model choice, and smoothing. In contrast, the logit interface provides a fixed parser-free signal that improves both frame-level AUC and frame-level AP over the MIL baseline across both VLMs, without temporal post-processing in its main configuration. Since suspect segments are updated independently once available, next-token logit feedback provides a simple segment-local alternative to text-generation verification.
Read the full abstract

All authors Sébastien Thuau, Amira Gran, Siba Haidar, Rachid Chelouah

Quantum Physics

High-purity fluorescence photon bundle emission from two separate emitters

We propose a scheme for generating high-purity fluorescence two-photon bundles from two spatially separate two-level emitters, whose correlated excitation is mediated by a strongly driven auxiliary emitter. Unlike bosonic-mode-based approaches, the finite excitation space of the two target emitters intrinsically excludes higher-excitation manifolds, and thus eliminates impurity photons associated with undesired higher-excitation states. We further analytically characterize the residual population of off-resonant single-excitation states and show that suppressing the corresponding leakage improves photon bundle purity. Our scheme offers a feasible pathway for constructing high-purity quantum light sources with promising applications in quantum information processing.
Read the full abstract

All authors Zhicai Chen, Jun Xu, Deyi Kong, Xiangming Hu, Fei Wang

Nuclear Theory

Reduced Order Modelling for Nuclear Linear Response and the Incompressibility of Pb-208

Linear response theory provides essential information regarding the excitations of many-body systems, such as atomic nuclei. It yields ground state transition probabilities, or strength functions, from which reaction rates and cross-sections can be derived. These quantities are for example a critical input for astrophysical simulations and modelling of beta-decay. Currently, the most general theoretical framework for modelling global nuclear properties is Energy Density Functional (EDF) theory. Modern approaches for linear response employ the quasiparticle random-phase approximation (QRPA) on top of a mean-field vacuum. This can be done by using conventional matrix QRPA formulations, but can be sped up substantially by using the finite amplitude method (FAM). Nevertheless, obtaining highly-resolved response functions over the complete nuclear chart remains computationally demanding, which limits large-scale applications. This work introduces a Reduced Order Modeling (ROM) approach to emulate Finite Amplitude Method (FAM-QRPA) calculations, significantly reducing the computational cost of obtaining nuclear response functions. By employing a 2D-greedy strategy to interpolate from a small set of snapshots, the emulator achieves a x20 speed-up while maintaining high accuracy across various nuclei, operators, and energy density functionals (EDFs). A second objective of this work is to investigate the correlation between the infinite nuclear matter incompressibility and the ISGMR centroid position of Pb-208, specifically for EDF forms and parametrisations developed in Brussels: the BSk(G)-family. Our results indicate that the correlation does not persist.
Read the full abstract

Nuclear Theory

Universal reduced order modelling for the nuclear finite amplitude method

The quasiparticle random phase approximation or QRPA has been a foundational many-body technique for decades across quantum chemistry, condensed matter and nuclear physics. Although computing power has increased and the matrix-free Finite Amplitude Method (FAM) exists, the computational complexity of FAM-QRPA calculations remains a limiting factor for the generation of linear response data on atomic nuclei that are crucial for several research fields. In this work, we establish that the FAM-QRPA equations are inherently suited to a reduced order modelling framework and can be emulated efficiently. Moreover, we present a greedy snapshot selection strategy that leverages the reduced cost of FAM-QRPA calculations when the imaginary part of the excitation frequency is large. Even when accounting for its construction, the resulting emulator accelerates strength function calculations by significantly more than an order of magnitude. We demonstrate that this framework and its speed-up generalize to light and heavy nuclei, different numerical representations, and diverse nuclear models including chiral EFT and configuration-interaction shell model approaches, as well as Skyrme, Gogny, and relativistic energy density functionals.
Read the full abstract

All authors Emma Vancayseele, Pepijn Demol, Luis González-Miret Zaragoza, Mikael Frosini, Wouter Ryssens

High Energy Physics (Phenomenology)

LZ nuclear recoil event from inelastic singlet-doublet scalar dark matter

We study the possibility of explaining the recently reported high-energy nuclear recoil event by the LUX-ZEPLIN (LZ) collaboration within the framework of singlet-doublet scalar dark matter (DM). Considering DM to be the CP even mass eigenstate formed out of a scalar doublet and a real scalar singlet, both being odd under an unbroken $Z_2$ symmetry, we find the parameter space of the model consistent with correct relic abundance and direct-detection limits on elastic scattering rates. A large part of the parameter space can also lead to inelastic up-scattering of DM with a rate and recoil energy consistent with the recent LZ event. Depending upon the singlet-doublet mixing, the model allows a much wider range of currently allowed parameter space compared to the pure scalar doublet DM limit, which is disfavored due to non-observations of high-energy neutrinos from solar-captured DM annihilation by the IceCube experiment. Presence of $Z_2$-odd right-handed neutrinos also leads to other interesting phenomenology related to the origin of light neutrino masses and leptogenesis.
Read the full abstract

Logic

Failure of the $G_0$-dichotomy for generalized Cantor spaces

Kechris, Solecki and Todorčević's $G_0$-dichotomy characterizes Borel graphs that admit a Borel measurable coloring with countably many colors. We show that the analogue to the $G_0$-dichotomy for generalized Cantor spaces fails at the lowest possible complexity, namely for closed graphs.
Read the full abstract

Astrophysics of Galaxies

Irreducible-Mass Balance for Magnetized Null Horizons with an Internal Current Sheet

We begin with a general question: how does the irreducible mass of a magnetized black hole change when the horizon is not stationary? The null Raychaudhuri equation gives an exact area balance for any smooth null horizon, without assuming stationarity or axisymmetry. When the horizon is axisymmetric and admits an integrable quasilocal Hamiltonian, this geometrical identity becomes an energy balance. The equation keeps area growth, rotational and electromagnetic work, nonstationary focusing, canonical-flux corrections, and internal-boundary terms separate. We then turn to Wang's self-gravitating split-monopole Blandford-Znajek engine. In the weak-field and slow-rotation regime, P/M_H\ll1 and a/M_H\ll1, our general balance reproduces Wang's mass- and angular-momentum loss rates. The irreducible mass, M_{irr}=\sqrt{A_H/(16\pi)}, reveals what those rates do not show by themselves. It measures the part of the rotational work absorbed irreversibly by the horizon. At fixed magnetic flux and under impedance matching, half of the instantaneous rotational work leaves as electromagnetic power. The other half increases the horizon area and M_{irr}. The assumptions behind this reduction are derived explicitly. A minimal nondissipative world-volume action makes the current-sheet contribution vanish through O(p^2\epsilon^2). Direct power counting of Wang's perturbative fields, together with a compatible canonical-flux prescription, gives a relative focusing and canonical correction of O(p^2)+O(\epsilon^2). These estimates mark the range in which the reduced Blandford-Znajek trajectory remains controlled. Extending that trajectory to high spin requires an additional extrapolation. Relating the quasilocal horizon loss to energy measured at infinity requires a separate asymptotic flux calculation.
Read the full abstract

Computation and Language

FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect

We introduce FramingQA, a benchmark that measures the model sensitivity to question framing across law, medicine, finance, and robotic simulations. Large language models (LLMs) often change their responses to subtle rephrasings that align with an implied stance by users. This can leave users with advice tainted by how they happened to phrase a question rather than by the underlying facts, and the consequences are highly costly in high-stakes domains. Because in the realistic scenarios, both expert practitioners and non-expert users frequently ask LLMs questions containing incomplete or misleading assumptions, models are highly susceptible to those framings. To test this, we inject the framing bias across three nested levels: a framing-biased question phrasing (root), an injected framing-biased premise prepended to a neutral question (propositional), and a premise paired with a framing-biased question (global). Evaluating nine open models (3.8B-70B) across four families, we find that strong per-variant accuracy does not guarantee the robustness across differently phrased questions under the fixed factual information.
Read the full abstract

All authors Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo, Shanyu Chauhan, Felix Drinkall, Jade Kosché, Chenyang Ma, Glory Nwaugbala, Nabeel Seedat, Bradley Max Segal, Samuel Recht, Hinrich Schütze, Philip H.S. Torr

Computation and Language

An LLM-Associated Register Shift in Korean Journal Abstracts: A Morphology-Aware Excess-Vocabulary Study, 2018-2026

Excess vocabulary, a word's frequency above its pre-2023 trend, is how the change in scholarly English after 2022 has been measured. We adapt it to Korean with morphological units on 398,296 KCI abstracts (2018-August 2026), with 47,165 Vietnamese abstracts for comparison. Placebo floors are 0.1-2.2 points for the single-word statistic and at most 2.9 for the re-selected split-half set statistic. Korean abstracts show nothing in 2023, onset in late 2024, a rise through 2025 flattening in mid-2026: sisahada "suggest" appears in 21.4% of 2026 abstracts against 5.3% expected; plain verbs like araboda "look into" fall to a quarter of trend. Under stated assumptions the single-word conditional lower bound on LLM-processed abstracts is 3.5%, 10.5% and 16.1% for 2024-2026 and a split-half set bound 7.8%, 20.6% and 33.0%. Holzwarth et al.'s estimator under the same discipline gives 41.9% and 72.1% for 2025-2026. Subject-matter controls reduce but do not remove it: restricting the set to lemmas three language-model annotators all call style leaves 14.7 of the 33.0 points, and pairing each 2026 abstract with its journal's closest base-period abstract leaves 34.1. Tested translation routes do not explain it: the surface marks of translated Korean fall as the markers rise. In the same articles' English abstracts the excess appears a year earlier; where the English side carries none, the Korean shift persists at 30 to 66% of the rate where it does. Control abstracts from three providers reproduce the rising words, with marker turnover consistent with model generations; implied prevalences are scenario-dependent.
Read the full abstract

Probability

Critical-Window Fluctuations and Disorder Universality for the Sherrington–Kirkpatrick Model

We establish free-energy fluctuation limits for the Ising Sherrington–Kirkpatrick model in the nonzero parts of its critical window. For fixed $b\ne0$ and $\beta_N=1+bN^{-1/3}\sqrt{\log N}$, our main Gaussian orthogonal ensemble (GOE) result is \[ \sqrt{\frac6{\log N}}\left(F_{N,\beta_N}-N\,\mathrm{FE}(\beta_N)+\frac{\log N}{12}\right)\xrightarrow{d}G+\sqrt{\frac32}\,b_+TW_1, \] where $G$ is standard Gaussian, $TW_1$ has the real Tracy–Widom law, and $G$ is independent of $TW_1$, and $\mathrm{FE}$ denotes the limit of spherical Sherrington–Kirkpatrick free-energy. Additionally, we show that in a moderately supercritical regime \[ \frac{2}{N^{1/3}(\beta_N-1)}\left(F_{N,\beta_N}-N\,\mathrm{FE}(\beta_N)+\frac{\log N}{12}\right)\xrightarrow{d}TW_1. \] We also show that the above results remains valid for independent, not necessarily identically distributed, disorder matrices whose first three moments match the Gaussian law and whose fourth moments satisfy an averaged bound.
Read the full abstract

All authors Yu Cheng, Song-Hao Liu, Qi-Man Shao, Jing-Yu Xu

Robotics

SMaRT-Tug: Structured Multi-Agent Reinforcement Learning for Physics-Based Tugboat-Barge Collaborative Manipulation

Autonomous tugboating is central for automating maritime operations such as port logistics and vessel maneuvering, where multiple tugboats must cooperatively transport/manipulate a larger vessel. Collaborative pushing in this setting is challenging due to coupled hydrodynamics, low resistance, strong environmental disturbances, underactuated barge dynamics, and contact-rich interactions. Conventional control methods often rely on simplified models and fixed configurations, which limit their adaptability, while learning-based approaches are constrained by the lack of scalable and physically realistic training environments. We address these challenges by introducing a physics-based, GPU-accelerated simulation and learning framework for collaborative tugboat manipulation. Our simulator incorporates a customized buoyancy model, wave modeling, and hydrodynamic resistance, and supports large-scale multi-agent training under marine dynamics. In this simulator, we train a decentralized MAPPO (Multi-Agent PPO) policy augmented with a structured control prior (SCP) to improve training stability and maintain feasible pushing configurations. We evaluate our learned policy on straight-line transit, turning, and deceleration tasks, where we show that our decentralized framework yields more reliable and accurate maneuvering performance compared to a PID-based controller and a centralized PPO baseline. We further demonstrate zero-shot generalization to more challenging sea states and advanced maneuvers, as well as zero-shot scalability to larger teams of three and four tugboats despite training with only two agents.
Read the full abstract

All authors Junkai Lu, Jiadong Zhao, Jiacheng Zhang, Wenqi Zhao, Hao Gen Chia, Qun Shen Png, Germaine Ee, Chengyang He, Yifeng Zhang, Nathanael Tan, Guillaume Sartoretti

Machine Learning

TASTE: Throughput-Aware Batch Size Tuning for On-Device Edge Learning

The rise of privacy-preserving artificial intelligence (AI) has shifted the focus of model adaptation and personalization towards on-device learning, where deep learning models are finetuned directly on edge hardware using local user data. However, this shift requires optimization of deep learning training on resource-constrained hardware to maximize throughput while maintaining predictive accuracy. This paper introduces a novel technique for on-device model training that incorporates an efficient Bayesian optimization-based batch size tuning approach to maximize hardware throughput. To evaluate the impact of this hyperparameter on the learning dynamics, we investigated two distinct paradigms: standard supervised learning (SL) and online continual learning (CL). Experimental results across various edge devices demonstrate a throughput ceiling, beyond which increasing the batch size yields no additional throughput gains. The proposed tuning approach identifies the optimal batch size, which, when combined with gradient accumulation and linear learning rate scaling, achieves up to a 2X increase in training throughput on platforms such as Raspberry Pi 4 compared to maximum batch sizes, without compromising model accuracy. Furthermore, in the CL paradigm, we demonstrate that optimal batch sizes maintain the stability-plasticity balance required for incremental learning, effectively mitigating catastrophic forgetting while maximizing computational efficiency on edge-hardware.
Read the full abstract

Mesoscale and Nanoscale Physics

Direct Realization of Near-Ideal Carbyne in Ultrathin Boron Nitride Nanotubes

Carbyne, the sp-hybridized one-dimensional allotrope of carbon, is predicted to be the stiffest known material, with electronic and optical properties set by a single structural parameter, the bond length alternation. However, its intrinsic properties have never been measured: chains synthesized through molecular chemistry carry endgroup and finite-length perturbations that persist even in the longest molecules available, while chains grown inside carbon nanotubes strongly couple to the host, which renormalizes their vibrational frequency by up to 110 cm$^{-1}$ in a diameter-dependent manner. Here, we show that encapsulating and thermally converting hydrogen-capped polyynes inside ultrathin boron nitride nanotubes, structural analogues of carbon nanotubes but electrically insulating, yields carbyne chains in a near-ideal regime, where endgroup, finite length, and host-guest perturbations are reduced to secondary effects. Statistical Raman spectroscopy across 245 locations returns a vibrational frequency distribution an order of magnitude narrower than in carbon nanotubes, an anharmonicity consistent with the universal law for carbyne-like materials, and a bond length alternation matching correlated calculations for the free chain. No photoluminescence is detected, despite the transparent host, as expected for the dipole-forbidden emission of an unperturbed carbyne chain. Boron nitride nanotubes give experimental access to carbyne in its near-ideal form.
Read the full abstract

All authors Iryna Ivanenko, Pietro Marabotti, Yifan Zhang, Getulio Silva e Souza Júnior, Johannes M. A. Lechner, Pablo Hernández López, Martin Magg, Shivani Shivaprakash, Carlo Spartaco Casari, Sebastian Heeg, Benjamin S. Flavel

Nuclear Theory

A phenomenological approach to direct ${\rm{K}}^{*}$ production and hadronic medium effects in nucleus-nucleus collisions at high baryon density

Short-lived hadron resonances serve as sensitive probes of the late-stage hadronic medium in heavy-ion collisions. Using the AMPT-HC model, we study ${\rm{K}}^{*}(892)$ production and its hadronic medium effects in Au+Au collisions at $\sqrt{s_{\rm{NN}}} = 3$ GeV, a region of high baryon density. We introduce a phenomenological direct-production mechanism for ${\rm K}^{*}$ by replacing a fraction of the final-state kaons produced in the ${\rm NN} \to {\rm NYK}$ and ${\rm MN} \to {\rm YK}$ channels with ${\rm K}^{*}$ resonances, with the substitution fraction controlled by a parameter $\alpha$ while conserving four-momentum. The direct ${\rm K}^{*}$ is produced early, at about 6 fm/$c$, with little centrality dependence, whereas resonance fusion via ${\rm K}+\pi\to{\rm K}^{*}$ occurs later, with the mean production time increasing from about 8 to 10 fm/$c$ toward central collisions. Consequently, direct ${\rm K}^{*}$ mesons suffer stronger daughter rescattering, leading to a pronounced decrease in reconstruction efficiency toward central collisions, while the ${\rm K}^{*}$ survival rate remains close to unity. Elastic scattering of the daughters also shifts the invariant mass away from the resonance peak, contributing to the background-like component. The ${\rm K}^{*}/{\rm K}$ centrality dependence reflects the competition between direct production and resonance fusion and is sensitive to $\alpha$. At 3 GeV, a moderate direct-production contribution may result in an increasing ${\rm K}^{*}/{\rm K}$ ratio toward central collisions, providing a testable prediction for future measurements.
Read the full abstract

All authors Hongcan Li, Yun Liu, Guangyu Zheng, Yaping Wang, Guannan Xie, Gao-chan Yong

Machine Learning

TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables

Biomedical tables often combine thousands of measured variables with only tens or hundreds of labelled samples, a regime that is poorly represented in general-purpose tabular benchmarks. We introduce TabBench-Bio, a living and interactive benchmark of 43 biomedical datasets spanning multiple domains. Under a shared cross-validation protocol, we compare classical estimators, neural networks, and tabular foundation models across 28 feature-by-sample operating points. At the reference cell of 10,000 features and 100 training samples, RealTabPFN 2.5 has the highest point estimate, closely followed by TabPFN 3 and Logistic Regression. A paired bootstrap over the target pool separates RealTabPFN 2.5 from TabPFN 3 by 87 Elo (95% interval [43, 129]). Tabular foundation models generally occupy the leading ranks, while the strongest configuration depends on the operating point and biomedical modality. The AutoML framework AutoGluon, using its one-hour "extreme" preset, is configured as a separate resource-intensive reference and reported here at the reference and full cell. Fold-level predictions, run status, and deterministic aggregations make every reported result reproducible and reusable. The benchmark is open to contributions of new biomedical datasets. The interactive leaderboard is available at https://tabbench-bio.eu.
Read the full abstract

All authors Jules Kreuer, Sofiane Ouaari, Julia Hellmig, Julius Braitinger, Nico Pfeifer

Robotics

Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer

This paper proposes an open-set ego-noise separation framework for legged-robot audition via annotation-free adaptation and pretrained-model transfer. The framework removes robot-specific ego-noise while preserving environmental sounds whose classes are not specified in advance. Acoustic sensing provides cues about a robot's surroundings beyond the visual field, but walking-induced ego-noise from footstep impacts, joint-backlash rattling, and motor noise severely contaminates the recordings. The framework first uses RecurGraph to select ego-noise-dominant clips from the unlabeled recordings by aggregating clip embeddings into an embedding centroid and propagating scores over an audio-embedding graph. The selected clips are mixed with diverse environmental sounds from a large-scale sound-event dataset to provide paired mixture–target supervision for open-set separation. Transfer-DiT then adapts a general-purpose zero-shot neural separator to achieve high-fidelity open-set ego-noise separation for the target robot. Experiments with bipedal and quadrupedal robots show reliable clip selection and improvements in separation quality and downstream task performance over baseline separators. These results demonstrate the feasibility of annotation-free adaptation without separately recorded ego-noise-only data or manual clip-level annotations.
Read the full abstract

All authors Koki Shoda, Jun Younes Louhi Kasahara, Aoba Koyanagi, Qi An, Atsushi Yamashita

Computer Vision

AFID: A Unified Open Framework for Automated Fingermark Identification, Quality Assessment and Feature Extraction

Automated fingermark identification is the foundation of forensic investigation, yet progress in the field is held back by fragmented, closed-source solutions trained on private or discontinued data. We present AFID, a unified open-source framework for friction ridge image processing that performs recognition, quality assessment, and feature extraction based on a single shared encoder, trained exclusively on publicly available data. At its core is a fixed-length representation learned for identity discrimination, trained under heavy augmentation. Despite applying essentially no preprocessing beyond resizing and padding at inference, AFID sets a new state of the art in fixed-length fingermark recognition, leading identification across NIST SD 27 (67.6% rank-1) , SD 302 (54.9% rank-1), and SD 303 (67.6% rank-1), surpassing a commercial matcher on fingermarks. From the same frozen backbone, a quality assessment module predicts recognition utility more accurately than any compared baseline and generalizes across independent matchers, while lightweight decoders recover minutiae, ridge orientation, and segmentation competitive with dedicated methods. The framework proves that a single, efficiently trained encoder can support the full fingermark processing pipeline, from recognition through quality assessment all the way to feature extraction. To accelerate research on fingermark analysis even further, we release the code, models, and annotations to the community.
Read the full abstract

General Topology

The answer about Itzkowitz's Problems on FSIN groups

A topological group is functionally balanced if every bounded real-valued left uniformly continuous function is right uniformly continuous. We prove that every Hausdorff functionally balanced group has coinciding left and right uniformities, giving an affirmative answer to the Itzkowitz problem. Consequently, the classes of SIN, SFSIN and FSIN groups coincide.
Read the full abstract

Numerical Analysis

A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE Solvers

Physics-informed neural networks (PINNs) represent a growing frontier in using artificial intelligence to solve partial differential equations (PDEs). Automatic differentiation (AD) plays a central role in this paradigm, which is mesh-free and replaces traditional iterative solvers with gradient-based optimization in continuous space. However, the inherent limitations of AD, particularly in handling higher-order derivatives and discontinuous solutions, pose significant challenges for complex problems. This has motivated a growing number of researchers to explore discretization-based constraints as an alternative path. Yet, the respective applicability of these two paradigms remains largely unexplored. In this work, we conduct systematic experiments across a wide spectrum of problems, from simple linear Poisson to high-Mach hypersonic flows with strong discontinuities. Through a rigorous decomposition of approximation, optimization, and truncation errors, we systematically elucidate the fundamental trade-offs and error-governing mechanisms of both paradigms, as well as two representative network architectures: multi-layer perceptron (MLP) and graph neural network (GNN). Our results reveal a consistent trend: as nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced, with smaller optimization errors compensating for the truncation errors. Moreover, the more complex the nonlinearity and boundary conditions, the greater the advantage of GNN over MLP. These insights offer a robust practical guideline for configuring neural PDE solvers in demanding engineering applications. Our source data and code are available at https://github.com/guoxing0809/neuropde_analysis.
Read the full abstract

All authors Xing Guo, Hongwei Tang, Zewei Meng, Yidong Zhang, Shaoqiu Xiao, Feng Liu

Analysis of PDEs

Fully discrete stochastic maximal regularity and $H^\infty$-calculus for second-order elliptic operators

This paper establishes the fully discrete stochastic maximal $L^p$-regularity and the accompanying sharp maximal estimate for numerical approximations of parabolic stochastic partial differential equations. We consider the spatial finite element discretization $A_h$ of a general second-order elliptic operator $A=-\nabla \cdot a\nabla +b\cdot \nabla +c$ with Dirichlet boundary conditions on a smooth, bounded, convex domain in $\mathbb{R}^3$, coupled with a broad class of temporal schemes, including rational approximations and the exponential Euler method. To obtain these optimal discrete regularity results, we establish a bounded $H^\infty$-calculus for the discrete spatial operator $A_h$, uniformly in the mesh size $h$. As a direct byproduct, we also establish the discrete-in-space stochastic maximal regularity for the corresponding spatial semi-discretizations. As an application, we establish the pathwise uniform convergence of a fully discrete approximation of the three-dimensional stochastic Allen–Cahn equation with variable diffusion coefficients and multiplicative noise.
Read the full abstract

Statistical Methodology

Quasi-randomization-based inference for multivariate Mann-Whitney effects under random missingness

Marginal Mann-Whitney effects are widely used across various fields of research, and extensions of this estimand have been developed in many directions in statistical methodology. In this paper, we focus on an extensions for repeated measurements and factorial designs subject to randomly missing data. In a previous work by Rubarth et al. (2022a), asymptotically correct tests were developed under the assumption of deterministic missing indicators. In contrast, the approach in the present paper accounts for the stochastic nature of missing values under realistic mechanisms. Thus, the involved covariance matrix incorporates the true variability of missing data. The combination with a quasi-randomization procedure using random permutations within each data point yields asymptotically exact tests and a generally improved type-I error control. Additionally, the tests control the type-I error for finite sample sizes in the special case of exchangeable sampling distributions. Simulations across a wide range of settings demonstrate the benefits of the proposed method in small samples, also for different missingness mechanisms. A real data analysis about school children learning math illustrates several practical aspects of the tests' application.
Read the full abstract

All authors Dennis Dobler, Jörg-Tobias Kuhn, Lubna Amro, Paavo Sattler

Artificial Intelligence

CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification

Natural-language Computer-Aided Design (CAD) code generation aims to turn design intent into executable and editable parametric programs. Large language models (LLMs) make this goal increasingly practical, but useful systems must preserve the construction process behind the rendered geometry. Existing benchmarks and methods mostly focus on how closely the generated CAD model matches the reference geometry, often using metrics such as Intersection over Union (IoU). Such metrics can miss errors in part decomposition, construction hierarchy, Boolean operations, sketch structure, and geometric relations. This gap calls for a representation that makes design intent explicit and lets a system check generated code against that intent. We propose CIT-CAD, a framework that infers a Constraint Intent Tree (CIT) from the input description to represent the intended entities, hierarchy, operations, and relations. The tree has two roles: it guides CAD code generation and defines expected constraints for verification. The framework extracts actual constraints from the generated program, compares them with the expected constraints, and uses mismatches to localize and repair design violations. Experiments show that the framework improves CAD generation performance, with larger gains on more complex multi-entity designs. By turning design intent into an explicit and checkable object, this work is the first attempt to move text-to-CAD generation beyond rendered-geometry matching toward construction-aware synthesis, verification, and repair.
Read the full abstract

All authors Yali Du, Hui Sun, San-Zhuo Xi, Ming Li

Systems and Control

Stochastic Model Predictive Control under AC Power-Flow Constraints Using Generative Learning

This paper proposes an end-to-end generative framework for efficiently solving multi-period and multi-scenario stochastic model predictive control (SMPC) problems under nonlinear AC power-flow constraints. Conventional deterministic neural surrogates rely on a single-shot prediction, which makes reliable feasibility difficult to achieve because one dispatch trajectory must simultaneously satisfy nonlinear constraints across all scenarios and time periods. To address this limitation, a conditional stochastic neural generator (CSNG) is developed to produce multiple candidate dispatch trajectories for each uncertainty instance, enabling the recovery of a feasible and economical solution through candidate selection. A feasibility-aware self-supervised distribution-shaping scheme is further introduced to promote constraint satisfaction, candidate diversity, and operating economy without requiring computationally expensive SMPC solution labels, while mitigating candidate collapse in generative ACOPF learning. To support efficient end-to-end training, a constraint-aware differentiable architecture is introduced. It employs a projection mechanism to exactly enforce box and ramping constraints while preserving informative gradients near active bounds, together with a differentiable equality-completion surrogate for efficient AC power-flow reconstruction. Case studies on the IEEE 14- and 118-bus systems demonstrate $100\%$ feasibility, optimality gaps below $2\%$, and computational efficiency suitable for intraday dispatch. The implementation is publicly available at https://github.com/JieZhu6/Generative_SMPC.
Read the full abstract

Machine Learning

Revisiting Thinning Methods for Kernel Learning Problems

Kernel methods are widely used because of their strong theoretical guarantees and empirical performance. However, their high computational cost limits their applicability to large-scale datasets. To address this shortcoming, several approaches use Maximum Mean Discrepancy to construct representative subsets that preserve the properties of the full dataset in a Reproducing Kernel Hilbert Space. We introduce Backward Kernel Herding, an algorithm that addresses this problem by iteratively removing points from the dataset, achieving results comparable to current state-of-the-art approaches while accelerating the subsampling process in realistic scenarios where the reduced size is less than half of the dataset. Moreover, we overcome a limitation of Kernel Thinning by proposing an extension that enables the construction of subsets of arbitrary size rather that restricting to successive halvings. Finally, we conduct an extensive experimental comparison focusing on the most relevant kernel learning procedures: Gaussian Processes and Kernel Support Vector Machines. The results show that Backward Kernel Herding consistently achieves competitive performance with the most favorable training-time efficiency, while the proposed Flexible Kernel Thinning frequently achieves the best predictive performance. These gains become especially pronounced for moderate compression ratios, highlighting the benefits of incorporating supervised information into the thinning process. In terms of memory consumption, Flexible Kernel Thinning is also competitive, whereas Backward Kernel Herding remains an alternative when computational efficiency is the primary objective. Overall, no single method dominates across all scenarios, underscoring the importance of selecting the reduction strategy according to the desired trade-off between predictive performance, training cost, and memory requirements.
Read the full abstract

All authors Blanca Cano-Camarero, Yago R. Aguado-Carrillo-de-Albornoz, Ángela Fernández-Pascual, José R. Dorronsoro