Peer Revenue Returns subject to peer review

Papers

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

All of arXiv

Tuesday 1 September

Computer Vision

ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives

We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised vision transformer pretraining to improve representation quality. Our approach is thoroughly benchmarked on ImageNet and transfer learning, image retrieval, copy detection, and image, video segmentation tasks. Notably, our proposed negatives give rise to emergent properties, where learned representations contain explicit information about the semantic content of an image and serve as excellent classifiers (up to +11.3% over baselines). ViTAMINS achieves these benefits through simple modifications to existing contrastive frameworks and outperforms competing methods while being more resource efficient, e.g., our ViT-B surpasses V-JEPA with ViT-L. Our findings motivate reconsidering contrastive learning as a simpler yet powerful alternative to dominant generative and self-distillation approaches.
Read the full abstract

All authors Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos, Tania Stathaki

Computers and Society

Causal Evidentiary Governance for High-Risk Machine Learning Systems

Machine learning systems deployed for credit, hiring, and resource distribution are increasingly subject to regulatory oversight from policies such as the EU AI Act and GDPR. Current fairness governance practices rely on observational fairness metrics, post-hoc explainability, and immutable audit logs, but provide limited support for causal attribution and efficient evidentiary verification. We introduce Causal Evidentiary Governance (CEG), a framework in which regulated institutions commit to a versioned directed acyclic graph (DAG) that partitions causal pathways into allowable and disallowed groups. The Causal Harm Rate measures prediction variation attributable to disallowed causal pathways. Each decision is accompanied by a signed Decision-Evidence Packet (DEP), cryptographically binding the prediction to a digest of the published DAG and path-specific attributions. DEP digests can be appended to a Merkle tree to enable logarithmic-cost inclusion proofs. We validate CEG through a two-layer empirical methodology using demographic summaries from four years of PMA credit supervisory data to construct 10,000 synthetic credit applicants across four strategic DAG counterfactuals. Causal Harm Rate isolates injected causal effects more clearly than demographic parity or equalized odds. Cross-model validation and ablation studies assess robustness. Evaluation on the German Credit dataset shows that harm associated with specific causal pathways can be substantially understated by associational fairness metrics. Finally, a proof-of-concept implementation demonstrates operationally plausible throughput and highlights relevant performance tradeoffs.
Read the full abstract

High Energy Physics (Theory)

Logarithmic corrections to the entropy of near-extremal rotating black holes

An interesting feature of quantum corrections to the Bekenstein–Hawking entropy is the appearance of logarithmic area terms, whose coefficients are governed by the spectrum of massless fields. For near-extremal black holes, the entropy also receives a logarithmic temperature correction, whose coefficient is determined by the zero modes of the corresponding extremal black holes. In this paper, we study near-extremal rotating black holes in three, four, and five dimensions with an important focus on rotational zero modes. For three-dimensional BTZ black holes, our results are in agreement with the microscopic description. Furthermore, by treating the cosmological constant scale \(\ell\) as an independent parameter, we find an additional \(\log \ell\) correction to the entropy at extremality. For the five-dimensional BMPV black hole, we explicitly construct all the extremal zero modes and use them to evaluate the log temperature corrections to the entropy.
Read the full abstract

Artificial Intelligence

Data-Driven Persona-Conditioned Agents for A/B Test Simulation

A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our agents are constructed from anonymized behavioral data - activity patterns, engagement signals, and inferred demographics - enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75-0.80 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening.
Read the full abstract

All authors Ziyad Benomar, Weronika Łajewska, Leonardo Perelli, Saab Mansour

Programming Languages

A Dynamic Intermediate Representation for Hybrid Quantum-Classical Programs

Quantum compilers typically follow the circuit model, representing programs as fixed sequences of gates. This static view breaks down in hybrid quantum-classical applications, where gate choices depend on runtime data or measurement results. We introduce a new Intermediate Representation (IR) that elevates gates to first-class values, enabling their dynamic creation, composition, and control. This unified representation allows classical computation to steer quantum behaviour, capturing phenomena including stochastic gate selection, adaptive error correction, and measurement-driven computation within a single framework. Case studies in noise modelling, randomised compilation, error correction, and measurement-based quantum computing show that our IR expresses these programs compactly and supports optimisations that were not possible in the circuit model. Evaluation on a benchmark suite of hybrid quantum-classical programs indicates that our IR represents programs compactly and facilitates compiler analysis and transformation.
Read the full abstract

Cryptography and Security

MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset

A lack of suitable datasets has limited the research into the privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and lidar. Given the number of unsubstantiated privacy claims and their potential widespread deployment into many people's everyday life, understanding the privacy risks of these sensors – in isolation and in like-for-like comparisons – is crucial. With MultiGait, we collected the first multi-sensor, multi-perspective, multi-session gait-focused dataset, for the corresponding, and additional more far-reaching investigations. The dataset, validated with multiple state-of-the-art recognition systems, comprises various walking modes and annotated personal attributes for 199 individuals, to ensure the benefit for advanced studies including cross-sensor recognition and anonymization at the edge. MultiGait represents a foundation for rigorous privacy investigations, demonstrated through an extensive identity inference benchmark across eight sensors, four perspectives, and three recording sessions. Our benchmark incidentally reveals that sensors often assumed to be privacy-friendly do still entail considerable identity inference risks, while the poor cross-session generalization of existing methods underscores an important research gap.
Read the full abstract

All authors Julian Todt, Felix Morsbach, Philip Dissert, Thorsten Strufe

Artificial Intelligence

Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees

Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, in which a selected branch crosses an irreversible-action boundary. Progressive Risk Vesting (PRV) holds a trajectory-level risk budget in escrow and debits it as branches are activated. We prove an anytime harm bound for adaptively generated trees. Branch outcomes may be dependent, but each local certificate needs to remain valid conditional on the full pre-activation history, including the information used to select the request. When activation gates, branch charges, and compute constraints are held fixed, delayed vesting preserves every policy available under irrevocable spawn charging. Marginal risk estimates can still fail after branch selection. In a stylized branching model, trajectory harm changes as the authority reproduction number $\mathcal{R}_A$ crosses one. As local risk $p$ approaches zero, trajectory harm is proportional to $p$ below criticality, proportional to $\sqrt{p}$ at criticality, and retains a positive floor above it. A finite-type occupancy model yields risk and compute shadow prices. For nested fanout modes with decreasing marginal value per unit risk, these prices produce a threshold rule. Branching calculations and a split-sample experiment illustrate the results. These synthetic studies do not estimate safety in deployed agents. The analysis suggests a design rule: search broadly in the sandbox and grant recursive authority sparingly, with an explicit risk charge.
Read the full abstract

Machine Learning

The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow

The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning, However, its derivation is heuristic. We propose a perturbative regime in which the central flow is the limit of gradient descent: we assume that the loss decomposes as $f = g + \varepsilon h$; in the limit $\varepsilon \to 0$, the dynamics of gradient descent with learning rate $\eta$ converge to the gradient flow of $h$ constrained to the minimizers of $g$ of sharpness at most $2/\eta$. Our approach is formal rather than rigorous; it treats gradient descent as a singularly perturbed dynamical system in $\varepsilon$. Three timescales emerge: a fast timescale of oscillations along the sharpest direction, an intermediate timescale of the self-stabilization mechanism, and a slow timescale of the dynamics along the minimizers of $g$-the central flow. Using the method of multiple scales, a classical formal method from singular perturbation theory, we derive the expansion of the dynamics in $\varepsilon$: the central flow emerges as the leading-order term in the expansion, while the self-stabilization mechanism appears in the next-order term. We study this mechanism beyond previous analyses: with a single eigenvalue at the edge of stability, we compute the slow drift of the energy of the fluctuations; with several eigenvalues at the edge of stability, we derive the self-stabilization system and explain why fluctuations persist.
Read the full abstract

Solar and Stellar Astrophysics

Fundamental effective temperature measurements for eclipsing binary stars - IX. Characterisation of 5 solar-type sclipsing binaries with M-dwarf companions

Large-scale spectroscopic surveys will need suitable benchmark stars that can be used to verify the performance of automatic pipelines. A promising type of object for this purpose is the detached eclipsing binary (DEB) containing an FG-star and a low temperature companion. For flux ratios $\lesssim1$~per~cent, the spectra obtained for the binary will be almost identical to a single star. As the methods for obtaining accurate parameters for binaries are well established, they would be excellent benchmark candidates. We analyse a group of DEBs with M-dwarf companions using TESS light curves and high resolution spectroscopy from NIRPS and HARPS on the ESO 3.6-m telescope. We obtain accurate fundamental parameters for the stellar components. The secondary component is visible with cross-correlation, allowing them to be characterised as well. With the stellar parameters obtained from the analysis, we can measure precise effective temperatures from Gaia parallaxes and archival magnitude data. Chemical compositions of the primary stars are also extracted from the stellar spectra. In this analysis, the secondary components have minimal impact on determined spectroscopic parameters. Our radii and masses are characterised to within sub per~cent precision as well as our primary effective temperatures. Beyond a new set of stellar benchmarks, the secondary components analysed in this work represent a well characterised sample of M-dwarf stars which will be useful to improve our understanding of low mass structure and evolution.
Read the full abstract

All authors Axel Hahlin, Pierre F.L. Maxted, Ivanna Hernandez-Araya, Natasha Adshead, Claudia Aguilera-Gomez

Logic in Computer Science

On Synthesis of Metric Interval Temporal Logics

Automated mining of formal specifications is vital for verifying real-time systems. However, existing passive learning approaches remain restricted to deterministic specifications or limited fragments of Timed Regular Expressions (TRE). To our knowledge, this paper presents the first framework to tackle precise passive learning for an expressive timed logic, Metric Interval Temporal Logic (MITL) without relying on predefined templates or restricted logic fragments. Our approach formally reduces the timed learning problem into a scalable untimed one. By identifying quantitative timing differences between positive and negative traces, we synthesise precise timed constraints and inject them as new Boolean atomic propositions. This embeds timing into the alphabet, delegating the complex formula evaluation to highly optimised, off-the-shelf untimed LTL tools. Crucially, our framework is complete, guaranteeing a separating specification can always be found. We evaluate our implementation across several benchmarks, demonstrating the effectiveness of our approach.
Read the full abstract

Numerical Analysis

Randomized inexact block triangular preconditioners for double saddle-point systems in PDE-constrained optimization

We develop a new class of inexact block triangular preconditioners for double saddle-point systems arising from PDE-constrained optimization. The proposed preconditioners are constructed through matrix factorization techniques while preserving the inherent block structure of the original systems. A comprehensive spectral analysis of the preconditioned matrices is provided, yielding explicit bounds for both real and nonreal eigenvalues. To enable efficient construction of the inexact preconditioners, randomized strategies are introduced to select the required subblocks. We establish high-probability bounds for the expected approximation error, with the error estimates explicitly characterized in terms of the eigenvalues of the associated matrices. Numerical experiments demonstrate the effectiveness, robustness, and scalability of the proposed preconditioners, and validate the efficiency of the randomized construction strategies.
Read the full abstract

Information Retrieval

Web Price Extraction: State of the Art and an Adaptive Browserless Implementation

Price extraction from websites is a key task for market monitoring, price comparison, and business analytics in e-commerce. Existing approaches can be broadly divided into four groups, and understanding their trade-offs in accuracy and scalability is essential for selecting suitable extraction strategies. Classical methods rely on manually written wrappers and rule induction from labeled pages, offering high accuracy but adapting poorly to structural changes and requiring considerable maintenance effort. Browser-based methods, using tools such as Selenium and Puppeteer, handle dynamic JavaScript content but consume large computational resources and scale poorly. Browserless approaches retrieve HTML directly via HTTP requests, offering significant gains in speed and cost, but rely on rules calibrated for specific sites. Methods based on machine learning and large language models offer adaptability but require training data and substantial computation. Our main contribution is an adaptive browserless price extraction system that improves robustness to structural differences between websites. We implemented a baseline architecture combining HTML page fragmentation with syntactic, semantic, and frequency rules, and extended it in two ways: a Bayesian approach that dynamically updates rule weights, and a genetic algorithm that optimizes the system's global parameters. This hybrid scheme increased precision from 77.2% to 87.3% and reduced average per-page processing time by approximately 14% relative to the baseline, confirming it as a competitive alternative to manually tuned browserless solutions and to more resource-intensive browser- or LLM-based methods, offering high extraction accuracy at low computational cost.
Read the full abstract

Quantum Physics

Tangent fermions can restore vacuum stability of discrete-time Dirac models

The Dirac quantum walk (a 1+1 dimensional space-time discretization of the Dirac equation) has a $2\mu$ mass gap both at the center and at the corner of the quasi-energy-momentum Brillouin zone. Gupta and Short recently noted [Quantum 9, 1845 (2025)] that the Dirac vacuum can create a particle-hole pair at the zone corner with the release of an energy $2\mu$ to the environment. They removed this vacuum instability at the expense of fermion doubling, the appearance of a second low-energy Dirac cone. Here we show that an alternative discretization scheme, with a tangent rather than a sine dispersion relation, offers stability while retaining a single Dirac cone. The key step is the Cayley transformation from the unit circle of Floquet eigenvalues $e^{-i\varepsilon}$ to the real line of unbounded energies $E=2\tan(\varepsilon/2)$. We compute the Schwinger effect (particle-hole pair creation in a uniform electric field) for tangent fermions and show that the pair-production rate agrees with the continuum result for a single Dirac cone. The zone corner is exactly decoupled if the scalar potential is coupled through the Hermitian generator of the quantum map. If it is coupled as a split operator, in order to preserve exact gauge invariance on the lattice, the corner does contribute - with a weight that vanishes quadratically with the lattice constants, in contrast to the Dirac quantum walk where the zone-corner instability survives the continuum limit.
Read the full abstract

Human-Computer Interaction

Beyond Technological Solutionism: Rethinking XR in Healthcare

The healthcare industry's enthusiastic adoption of Extended Reality (XR) technologies obscures a concerning reality: we were building increasingly sophisticated ways to perpetuate fundamentally broken healthcare systems. Through three deeply personal narratives - a rural patient cut off from care infrastructure, an urban professional navigating fragmented services, and a first-generation immigrant confronting cultural barriers - this provocation paper exposes how our obsession with technological innovation often worsens rather than resolves healthcare disparities. By applying the SEIPS 3.0 model to examine diabetes-CVD care coordination, we identify an "innovation paradox" where advanced technology creates new barriers to effective care. Our care interdependencies framework reveals that healthcare outcomes are shaped primarily by human relationships (50-60%), organizational coordination (25-30%), and sociocultural factors (15-20%), not technological sophistication. This research challenges the HCI community to confront its role in perpetuating healthcare inequities, demands a fundamental rethinking and proposes a new framework for healthcare innovation that prioritizes human relationships over technical capability, systemic change over feature sets, and actual care delivery over technological ambition. For healthcare providers, technology developers, and policymakers, our findings suggest that effective care coordination requires us to step back from our techno-solutionist mindset and engage
Read the full abstract

All authors Md Haseen Akhtar, Cecilia Landa-Avila, Shital Desai, Claire Warden, Andrew Morris, Mark Anderson, Thomas Cochrane, Janakarajan Ramkumar

2609.01028 · 1 Sep · 5 pages, 1 figure, Accepted paper at the Interactive Health workshop In Proceedings of CHI 25 Workshop on Envisioning the Future of Interactive Health, April 27th, 2025, Yokohama, Japan, ACM, New York, NY, USA, 2 pages

Computer Vision

Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set

Out-of-distribution (OOD) detection predicts whether a test image belongs to none of the predefined classes. To evaluate this task, benchmarks need images from outside the in-distribution (ID) data; typically, these are defined or collected in an ad hoc fashion. Since no ground truth is perfect, ID-labeled datasets themselves contain a natural source of OOD images. We exploit such annotation errors and present Fi-ImageNet-1k, an OOD dataset built from ImageNet-1k validation images that the recent ReImageNet reannotation effort assigned to no ImageNet-1k class. Each image was examined by expert human annotators supported by evidence from MLLMs, VLMs, and reverse image search, comparing it against all visually similar ID classes. We keep only images that could be assigned a specific class outside the ImageNet-1k label space. The resulting Fi-ImageNet-1k, with 655 images from 522 classes, is substantially more challenging than any commonly used OOD dataset. No evaluated combination of classifier and OOD detector achieves a false positive rate below 51% at 95% true positive rate (FPR@95). Compared to the recent NINCO, our dataset is 3.8x more challenging in the FPR@95 metric for state-of-the-art supervised OOD detection methods.
Read the full abstract

All authors Ruslan Rozumnyi, Matěj Suchánek, Tomáš Vojíř, Klára Janoušková, Jiří Matas

Differential Geometry

Quantitative avoidance for free boundary flows and applications

In this article, we introduce a new distance function between hypersurfaces with free boundary. We show that our new quantity, which we call twisted Fermi distance, is monotone under mean curvature flow with free boundary. This overcomes the stumbling block that monotonicity of the usual distance function can fail for non-convex domains, and has several applications. Most importantly, we generalize the avoidance principle for free boundary Brakke flows, recently established by the first author for convex domains, to arbitrary domains. Using this, we then show that all results from our recent joint work, including the mean-convex neighborhood theorem and the uniqueness theorem for free boundary flows through cylindrical singularities, can be generalized to arbitrary domains without any convexity assumptions as well.
Read the full abstract

Distributed Computing

MakoXC: Rearchitecting DFT Exchange-Correlation with Matrix-Aligned and Knowledge-Organized Sparsity

Density Functional Theory (DFT) is indispensable for materials science and drug discovery, yet the exchange–correlation (XC) evaluation remains a major bottleneck due to its cubic scaling. Although linear-scaling methods exploit electronic nearsightedness to reduce asymptotic complexity, they produce irregular sparse workloads that hide implicit sparsity and prevent efficient use of modern AI accelerators. We present MakoXC, a modular matrix-aligned XC evaluation engine that rearchitects nearsightedness-induced sparsity into regular, accelerator-friendly computations. MakoXC co-designs three key techniques: (1) Matrix-Aligned Cells reorganize nearsightedness-induced interactions into dense, accelerator-aligned data clusters; (2) Sparsity-Guided Activation translates deeper implicit sparsity into numerically correct structured execution for practical linear scaling; and (3) Kernel-Fused Pipeline consolidates fragmented workloads into a unified, compute-intensive execution path that fully unleashes accelerator throughput. Extensive evaluations show that MakoXC achieves average speedups of 67.8$\times$ speedup over standard XC evaluation and 4.7$\times$ over state-of-the-art linear-scaling methods. When integrated into a production-grade commercial DFT package, MakoXC scales XC evaluation to ubiquitin (1,231 atoms, def2-SVP) on 64 GPUs, enabling the end-to-end DFT calculation to complete in under five minutes. By restructuring XC evaluation into a unified, structured computation, MakoXC demonstrates how scientific workloads can achieve genuine low complexity while maximizing parallel efficiency on AI accelerators.
Read the full abstract

All authors Haozhi Han, Fusong Ju, Jing Bai, Ruge Zhang, Xiang Zhao, Liang Yuan, Yunquan Zhang, Ting Cao, Liu Yunxin, Yifeng Chen, Kun Li

Computation and Language

PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition

Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrained by the rigid, whole-expert abstraction. Existing frameworks manage, schedule, or prune experts as atomic execution units, which fixes the optimization boundary too early and leaves fine-grained intra-expert computational redundancy underexplored. In this work, we present PCoMoE, a path-compositional execution framework that shifts MoE inference from coarse-grained expert selection to fine-grained path composition. PCoMoE incorporates a path-level formulation of expert computation, a compatibility-aware layer-wise pruning strategy to suppress low-value path combinations, and a hardware-friendly execution engine to exploit reusable sub-expert structures under strictly bounded overheads. Experimental results demonstrate that PCoMoE achieves up to a 1.31x end-to-end inference speedup while enhancing model accuracy by 10%. The code is available at https://github.com/gzyyy0/PCoMoE
Read the full abstract

All authors Ziyan Gan, Fangxin Liu, Chenyang Guan, Junjie Wang, Ning Yang, Haomin Li, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Zongwu Wang, Li Jiang, Haibing Guan

Cryptography and Security

AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs

We present AKRASIA, a stealthy, inference-time backdoor attack against reasoning-based Code LLMs. AKRASIA aims to achieve a backdoor target (e.g., malicious code execution) in reasoning LLMs while evading automated defenses and human inspection. To achieve this, AKRASIA probes the victim LLM to construct a code-level backdoor trigger. It then employs in-context learning for backdoor learning, and model unfaithfulness to conceal the backdoor trigger, and generate plausible reasoning. We evaluate AKRASIA using four backdoor targets six (6) reasoning LLMs, three coding tasks/datasets and three defense methods. AKRASIA has up to 99.34% average attack success rate on SOTA LLMs and mantains up to 97.23% average accuracy. AKRASIA evades the SOTA defense, retaining up to 98.82% average ASR in most (14/18) defense settings. It evades human inspection, successfully hiding the backdoor trigger and reasoning steps in up to 80% of settings. Our findings motivate the need to defend LLMs against reasoning backdoors.
Read the full abstract

All authors Chua Jin Chou, Sarang Nambiar, Murali Srinivasan, Ezekiel Soremekun

Nuclear Theory

Superfluidity and Vortex Dynamics in Neutron Stars

Neutron stars contain several forms of quantum condensed matter whose microscopic properties control macroscopic rotational dynamics and magnetic behavior of these fascinating objects. This review surveys superfluidity and superconductivity in compact stars, with emphasis on phenomena associated with quantized vorticity and magnetic-flux structures, and the possible connections to observed phenomena. We first summarize the microphysics of nucleonic pairing, including spin-singlet $^1S_0$ neutron pairing in the inner crust, proton superconductivity in the outer core, and spin-triplet $^3P_2$–$^3F_2$ neutron pairing at higher densities, together with the principal many-body uncertainties affecting the corresponding pairing gaps. We then discuss the dynamics of neutron vortices, including pinning, vortex creep, and dissipative motion, and the role of vortex dynamics in angular-momentum exchange between the superfluid and the observable crustal component. We give special attention to proton flux tubes in type-II superconducting cores, the possible realization of type-I superconductivity, and vortex–flux-tube interactions. We also review collective rotational phenomena, including Tkachenko oscillations of the vortex lattice and free precession, and their possible relation to long-term variability in pulsar timing. Finally, we discuss the possible deconfinement of hadronic matter into quark matter, the formation of color-superconducting phases, and the topological defects associated with these phases, together with their possible observational consequences. Throughout the review, we identify key open questions connecting microscopic pairing, mesoscopic defect dynamics, and observable neutron-star phenomena.
Read the full abstract

Data Structures and Algorithms

Kernelization of 2-Club Cluster Edge Deletion on Interval Graphs

The \emph{$s$-Club Cluster Edge Deletion} problem asks whether, given a graph $G$ and an integer $k$, one can delete at most $k$ edges so that every remaining connected component has diameter at most~$s$. This generalizes the classical Cluster Edge Deletion problem by permitting components of bounded diameter instead of requiring cliques. On general graphs, $2$-Club Cluster Edge Deletion is known to be fixed-parameter tractable when parameterized by $k$, but it remains open whether it admits a polynomial kernel, as posed in~\cite{ABUKHZAM2023113864}. Motivated by this question, we study the problem on interval graphs and obtain a polynomial vertex kernel of size $\mathcal{O}(k^{5})$. As a complementary result, we also show that the \emph{$s$-Club Cluster Edge Deletion} problem is polynomial time solvable on unit interval graphs. We also show that $2$-Club Cluster Edge Deletion is NP-hard even on split graphs.
Read the full abstract

Algebraic Geometry

Euler obstructions and Verdier specializations

To establish a basis of the sheaf theoretical study of the Milnor fibers and monodromies of complete intersection varieties, we clarify the structures of the Verdier specialization sheaves associated to them. Assuming the Thom condition in a direction, some basic results on them will be obtained. Then we apply them to obtain formulas for the Euler obstructions of complete intersection varieties having non-isolated singular points.
Read the full abstract

Quantum Physics

Photonic fusion operations transform partial distinguishability

Photonic fusion operations are a central primitive in photonic quantum information processing and are commonly characterized by their success probability and resource cost. Here, we identify an additional way in which different implementations of fusion operations differ, namely in how they transform partial distinguishability. We consider distinguishability originating both from imperfect entangled resource states and from imperfect single photons. We find that different successful fusion events can induce markedly different distinguishability transformations depending on the fusion protocol, heralding outcome, and error model. Under a collective resource-state error model, we identify a modification to an existing fusion protocol that improves the fidelity of the remaining state on average. Generally, however, these transformations adversely affect distinguishability, and many successful fusion outcomes are accompanied by distinguishability degradation. Our results show that partial distinguishability is dynamically shaped by interference and measurements and should be considered alongside overall fusion success probability when evaluating photonic fusion protocols.
Read the full abstract

Medical Physics

PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation

Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction network (RepVGG-U-Net). We addressed the DoseRAD2026 proton dose-prediction task with PyDoseRT Proton, a GPU-accelerated engine implemented in PyTorch and augmented by a learned residual toward Monte Carlo (MC) accuracy. A double-Gaussian PB kernel was calibrated to GATE/Geant4 integrated depth doses in water in two stages: a classical per-energy curve fit, then a gradient-based fit of the full 3-D dose through the PyTorch physics engine as it retains a differentiable execution path for gradient-based optimization of dose-dependent objectives. The engine computes each beamlet on a beam's-eye-view (BEV) lattice with variance-preserving Gaussian splitting, an analytic nuclear halo, and a Fermi-Eyges heterogeneity term, then rotates the result into the patient frame. Additionally, a compact residual U-Net predicts an additive correction in BEV space. It is conditioned on voxelwise material-label embeddings, a discrete energy embedding and spot size. The same model was used for all anatomical sites (thoracic and abdominal). It was trained with a patient-space L1 objective emphasizing the scored high-dose region and multi-scale BEV deep supervision. The submitted CT configuration obtained preliminary-test beamlet MAE 0.0066, image-z IDD distance 0.0025, plan MAE 0.0049, 98.30% gamma pass rate (1%/1 mm), and DVH error 0.460.
Read the full abstract

All authors Lukas Zimmermann, Hermann Fuchs, Attila Simkó, Gerd Heilemann

Quantum Physics

Nonlocal wavefront shaping through complex media

Wavefront shaping is a key technique for mitigating scattering in complex media, enabling advanced imaging and optical communication. Yet existing approaches are inherently local, requiring active correction elements - such as spatial light modulators or deformable mirrors - to lie directly in the optical path of the scattered light, which limits their integration into compact imaging systems. Here, we experimentally demonstrate nonlocal wavefront shaping using spatially entangled photon pairs. By applying a phase correction to a photon that never interacts with the scattering medium, we compensate for the distortions experienced by its entangled partner and restore their initial spatial correlations. Our approach physically decouples the wavefront correction from the scattering medium, paving the way for imaging through complex media in compact and otherwise inaccessible systems.
Read the full abstract

All authors Yanis Trouyet, Neelan Gounden, Pedro Ornelas, Patrick Cameron, Andrew Forbes, Hugo Defienne

Computation and Language

Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech

Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to be spoken with the primary language's accent rather than its native one. We propose Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech. LCG replaces the single language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own language. To choose where to apply this localized guidance, we propose a self-attention probing technique that finds the phrase boundaries without external alignments. Together, these components generate speech in which each region carries the accent of its own language, requiring no fine-tuning or auxiliary models. Across diverse language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness.
Read the full abstract

All authors Che Hyun Lee, Sangkwon Park, Donghun Kang, Dongwook Lee, Youngho Cho, Heeseung Kim, Sungroh Yoon

Social and Information Networks

A Network Science Perspective on Evaluating Deep Graph Generative Models

Traditional network models from network science, such as the Erdos-Renyi and configuration models, generate random networks that reproduce few selected topological properties observed in real-world networks. Deep graph generative models emerge as a data-driven approach, leveraging deep neural network architectures to learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks. Because real social contact networks cannot be shared due to privacy risks, synthetic networks serve as an alternative for developing and evaluating epidemic mitigation strategies. In this work, we evaluate deep graph generative models as well as the configuration from a network science perspective by assessing both the topological similarity between generated and real-world networks and their utility in identifying effective node immunization strategies to sup- press epidemic/misinformation spreading. It is found that two deep graph generative models produce synthetic networks that closely resemble the structural properties of real-world networks, enabling them to identify effective immunization strategies.
Read the full abstract

All authors Tianrui Mao, Abele Malan, Megha Khosla, Lydia Chen, Huijuan Wang

Computer Vision

Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints

Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of training data for large-scale models. While recent face recognition (FR) models perform well on high-quality (HQ) imagery, their accuracy drops significantly on LQ images with extremely low signal-to-noise ratio (SNR). Moreover, fine-tuning HQ-pretrained models on LQ data often improves LQ recognition at the expense of HQ generalization. This trade-off becomes more pronounced in modern evaluation settings spanning multiple datasets with varying image quality levels. To address these limitations, we propose a unified framework that combines three main components: (1) Local Probability Margin (LPM), which estimates per-sample difficulty directly from the model's discriminative landscape; (2) Nested Attention Module (NAM), a new low-rank adapter module that embeds a self-attention mechanism within selected transformer layers; and (3) Quality Gating Protocol (QGP), where an off-the-shelf image quality estimator modulates the adapter contribution at test time, enabling a single model to handle the full quality spectrum without sacrificing HQ performance. Experiments on surveillance (TinyFace, SurvFace) and standard (IJB-B, IJB-C) face recognition benchmarks demonstrate consistent gains in both identification and verification. Code and models will be released at github.com/candllq/nam.
Read the full abstract

Earth and Planetary Astrophysics

Exoplanets in star clusters

The field of exoplanetary research is rapidly evolving, thanks to TESS and Kepler/K2. With the latest data release, Gaia DR3, Gaia has transformed the study of star clusters. By combining the known properties of exoplanets and those of star clusters, in which they are found, it is possible to study the planets in greater detail and test theories of planetary evolution. We aim to create a catalogue of Gaia IDs for known exoplanets and use it to link the planets to a catalogue of star clusters. We utilised the NASA Exoplanet Archive and the Extrasolar Planets Encyclopaedia to compile a catalogue of known exoplanets. We then cross-matched the data with Gaia DR3 sources to obtain the Gaia IDs of the exoplanets. Using this information, we inferred the potential association of these exoplanets with star clusters. We described the statistical properties of these exoplanets. We compiled a catalogue of Gaia IDs for known exoplanets and identified those associated with star clusters. This resource facilitates detailed studies of exoplanet properties and their evolutionary contexts within stellar clusters.
Read the full abstract

General Relativity and Quantum Cosmology

Charging higher-dimensional spacetimes with a generalized Kerr-Schild transformation

We explore the construction of higher-dimensional Einstein-Maxwell(-Chern-Simons) solutions from vacuum seeds by means of a generalized Kerr-Schild transformation along a geodesic null vector field $\mathbf{k}$. Assuming the vector potential $\mathbf{A}$ to be aligned with $\mathbf{k}$, and $\mathbf{k}$ to be a Weyl aligned null direction satisfying the “optical constraint”, we arrive at three distinct branches of solutions. If $\mathbf{k}$ is expanding and twisting, then its shear must vanish – this branch includes certain charged Taub-NUT metrics. If $\mathbf{k}$ is expanding and twistfree, one finds two subfamilies: Robinson-Trautman electrovac solutions with a non-null Maxwell field if the shear is zero, or shearing solutions with a null field. Finally, the case when $\mathbf{k}$ is non-expanding reduces to a subset of the known Kundt solutions. In all cases, the Chern-Simons term turns out to be identically zero on-shell. In passing, by relaxing the alignment assumption on $\mathbf{A}$, we also obtain a six-dimensional extension of a charged Taub-NUT metric for which the magnetic part of the field strength is a linear combination of two distinct Kähler 2-forms, as opposed to the previously known examples in more than four dimensions.
Read the full abstract