Peer Revenue Now accepting positions

Papers

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

All of arXiv

Friday 6 November

Sound

AudioSphere: Towards Self-Supervised Spatial Audio Representation Models

Recent audio embedding models learn representations that transfer across clip- and frame-level tasks, yet they operate almost exclusively on single-channel signals and are blind to spatial structure. Spatial audio models capture that structure but rely on clip-level supervision or contrastive objectives, yielding embeddings unsuitable for frame-level tasks like sound event detection and localization (SELD). We argue this dichotomy is not fundamental: patch-level spatial self-supervision can jointly learn acoustic and spatial features at both temporal granularities. We introduce AudioSphere, a multi-channel masked autoencoder trained on Ambisonics recordings that reconstructs both spectral content and directional cues via a joint spatiotemporal masking strategy that masks both time-frequency patches and intensity vectors. AudioSphere supports frame-level predictions while producing strong clip-level representations via aggregation. Alongside the model, we release RealSELD, a standardized benchmark for evaluating frozen backbones on real-world multi-channel SELD. AudioSphere enables, for the first time, SELD with a frozen self-supervised backbone, while matching or exceeding prior self-supervised audio embedding models on clip-level classification tasks spanning environmental sound, speech, and music, and on frame-level sound event detection. All code and data are available at https://github.com/labhamlet/AudioSphere and https://huggingface.co/labhamlet.
Read the full abstract

Machine Learning

FondueQA: A Benchmark for Evaluating Parametric Compensation in Multi-Hop QA

Large Language Models (LLMs) show remarkable performance based on parametric knowledge, i.e., their ability to recall facts and associations internalized in a model's weights. However, studying this capability on established multi-hop benchmarks may be complicated by benchmark contamination, as many of these benchmarks have been publicly available long enough to plausibly appear in modern pretraining corpora. As a result, correct answers under missing evidence may reflect either general parametric knowledge or memorization of benchmark-specific instances. To study how models use internal knowledge when retrieval evidence is incomplete, we introduce FondueQA, in which every required multi-hop fact is uniquely localized to a designated evidence document. This enables controlled document-level evidence ablations to study parametric compensation under incomplete retrieval. Our empirical evaluation reveals that parametric compensation strongly depends on both entity popularity and the structural role of missing evidence. Generally, models compensate more successfully for facts involving popular entities. On FondueQA, we show that bridging evidence can be more useful than the answer-bearing document itself. Moreover, models may recall a missing fact in isolation but fail to use it under partial evidence, particularly when the context contains plausible competing entities, which can reduce Exact Match by up to 15 percentage points.
Read the full abstract

All authors Laurin Schmid, Suman Navaratnarajah, Koel Dutta Chowdhury, Steffen Eger, Josif Grabocka, Christian Frey

Artificial Intelligence

PHISHREV+: An ASP-Based Post-Hoc Defeasible Machine Learning Framework for Phishing Detection

Phishing website detection remains a critical cybersecurity challenge. Although machine learning classifiers achieve high accuracy on benchmark datasets, they suffer from a fundamental limitation: once trained, their decision boundaries are fixed and cannot incorporate new contextual evidence without retraining the model. This work presents PHISHREV+, a hybrid framework that instantiates the notion of post-hoc defeasible machine learning. This framework does not replace the classifier. It treats the initial classifier predictions as defeasible beliefs and revises them through an Answer Set Programming based non-monotonic reasoning(NMR) layer. The framework operates in two phases. In the machine learning phase, four classifiers (SVM, KNN, DT and RF) are trained on the 87 feature benchmark dataset. In the post-hoc NMR phase, four defeasible rules derived from exploratory data analysis of the training set, and validated through Chi-square and Mann-Whitney U tests, formally revise initial predictions. The proposed framework achieves consistent false positive reduction across all our classifiers SVM (41$\rightarrow$39), KNN (47$\rightarrow$46), DT (62$\rightarrow$61), and RF (52$\rightarrow$51) while maintaining complete false negative parity with zero increase overhead. A comprehensive ablation studies across seven rule configurations confirms that the hierarchical combination of all four defeasible rules is necessary to achieve this optimal balance. Instance level explainability is provided through eXplainable ASP (XASP), which generates formal derivation graphs showing which defeasible rules fired and why the initial belief was retracted, a capability absent from all existing phishing detection approaches.
Read the full abstract

Robotics

Task-Driven Closed-Loop Design Optimization of Passively Morphing Quadrotors for Contact-Mediated Narrow Gap Traversal

Aerial robots operating in cluttered environments may encounter openings narrower than their nominal width. Existing passively morphing drones reduce their width upon traversal, but they typically involve human-made designs, which can struggle to find the right balance among folding ratio, flight efficiency, and control tracking performance. We introduce a closed-loop design method that jointly optimizes quadrotor geometry and the torque-deflection response of two passively folding arms driven by the success rate in simulation for contact-mediated gap traversal. An optimization algorithm samples candidate designs that are evaluated in a contact-based simulation of the traversal task, where the task success rate is used as a feedback signal to sample progressively better designs over time. The resulting prototype passively reduces its width from 31.3 to 14.1 cm and traverses a 15 cm wide opening at a 2 m/s reference speed. It also tolerates gap approach-angle errors of up to 30 degrees and folds through a 40 cm long confined passage. Compared to a rigid twin, the soft configuration adds only 2 mm of position RMSE and less than 1% electrical power during contact-free flight. These results show that task-driven closed-loop design optimization can produce passively morphing airframes that are compact under contact, tolerant to approach error, and effectively rigid during nominal flight.
Read the full abstract

All authors Etor Arza, Luca Girardi, Gabriel Maquignaz, Javier Paez, Stefan Leutenegger, Stefano Mintchev, Kostas Alexis

Artificial Intelligence

Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games

Weight-space programming sets every weight of a feed-forward network by hand, from an explicit specification of the desired computation, with no gradient descent and no training data anywhere in the construction. We ask how far a large language model can carry this practice, zero-shot, across games of deliberately increasing difficulty. We design a four-rung ladder (Nim, tic-tac-toe, two sizes of Connect Four, and a chess endgame) spanning four axes of difficulty, and build a second, independent network at each rung, using a structurally unrelated game at matched difficulty, to separate what a rung's finding says about the difficulty level from what it says about the one game used to measure it. Ten networks are built and independently verified. Six admit a complete, non-statistical proof of correctness against an independent oracle. The chess-endgame rung is exact where correctness is cheap, move legality and, in one network, an exact one-ply mate detector, and collapses where it is expensive, composing a multi-move mating plan, from 84.1-100% success at the one-ply tactics it was built to get right down to 0.57-9.13% in full adversarial play; its replicate shows this collapse is an order of magnitude less severe under a shorter required plan and exact rather than heuristic safety checks. The standard-sized rung confirms, by holding hand-set evaluation weights fixed and adding only shallow search, that the remaining gap is an architectural ceiling rather than a matter of engineering effort, and this exact collapse reproduces across two structurally unrelated games. We release all ten networks, their independent oracles, construction-cost measurements, and a cold-prompt protocol for a future cross-model comparison
Read the full abstract

Robotics

EGT: Execution-Grounded Traversability through Learned Closed-Loop Trajectory Distributions

Rough terrain traversability is often estimated through point-wise roll, pitch, or force-angle margins along a planned path. However, these metrics are often inaccurate and overly conservative because they ignore how terrain disturbances and low-level controller corrections can affect the vehicle's motions. To overcome these limitations, we introduce Execution-Grounded Traversability (EGT), defined as the probability that a vehicle-controller pair can execute a candidate path while meeting trajectory-level tracking and progress requirements. We estimate EGT by predicting the distribution of closed-loop trajectories using a latent-space flow matching (FM) model conditioned on multi-resolution terrain features and 3D vehicle attitude and wheel-ground contact points prior. Across 650 simulated trials on unseen terrains, EGT reduces safe-path rejection to 2.2% (versus 11.4%-39.5% for pose-margin and force-angle baselines) and unsafe acceptance to 7.7%. Integrated into a receding-horizon sampling-based planner, EGT reduces navigation failure rates by 24-42 and 30-44 percentage points over [1] and [2], respectively, while cutting goal-reaching time by up to 20.5% and 45%. Finally, we demonstrate zero-shot transfer of our simulation-trained model to real-world outdoor experiments.
Read the full abstract

Human-Computer Interaction

Thinking Twice: A Sequential Approach to Nudge Towards Reflective Judgment in GenAI-Assisted Decision Making

Humans increasingly use generative AI (GenAI) for decision-making assistance, yet tend to engage in such situations using quick, intuitive (System 1) rather than deliberate, analytical assessment (System 2) as reflected in Dual Process Theory. Such engagement reduces the effectiveness of human-GenAI interactions and increases associated risks. Our research investigates how to design human-GenAI interactions that promote the transition from System 1 to System 2 thinking in decision-making. Based on the Three-Stage-Model, which suggests humans switch to System 2 when conflicts are detected, we conducted an experiment (n=130) testing sequential human-GenAI interaction as a cognitive forcing nudge during problem-solving tasks. This approach, where humans decide first before receiving AI assistance, enables detection of conflicting decisions. Compared to non-sequential settings (concurrent or no AI assistance), results show the sequential condition significantly enhanced both decision performance and GenAI prompt utilization, providing valuable insights for designing more reflective and thus effective human-GenAI interactions.
Read the full abstract

2611.09269 · 6 Nov · Full paper accepted and presented at the 20th International Conference on Wirtschaftsinformatik (WI 2025), Münster, Germany. To appear in the conference proceedings (Lecture Notes in Information Systems and Organisation, Springer). This version is the submitted manuscript prior to peer review

Quantum Physics

Correlation-Enhanced Quantum Reservoir Processing for Two-Qutrit Steering: From Generalization to Discovery

Quantum reservoir processing (QRP) has been applied to entanglement quantification, yet its potential for generalizable steering detection and the discovery of high-dimensional quantum correlations remains largely unexplored. Here, we introduce correlation-enhanced QRP (CEQRP), extending QRP to two-qutrit systems with two-body spin-correlation readouts. Some CEQRP-based classifiers substantially improve cross-family generalization, with logistic regression trained on full-information CEQRP features achieving approximately $96\%$ accuracy on unseen Werner states and over $97\%$ accuracy on unseen isotropic states at both \(m=4\) and \(m=5\). Independently, we establish two interconnected steering criteria for mixed two-qutrit states: a necessary-and-sufficient all-versus-nothing criterion for states admitting three linearly independent pure conditional states, and an asymptotic sufficient criterion, with the two criteria linked through invertible local filtering. These criteria provide rigorously certified steerable samples for training-set augmentation. Combining CEQRP-based classification with these theory-certified samples enables the discovery of new Alice-to-Bob steerable partially entangled states, including states at \(p=0.45\) whose steerability is independently confirmed by semidefinite programming (SDP) using seven projective measurement settings. The trained classifiers further guide finite-setting searches for steering boundaries. Our results establish a pathway from generalizable classification to the discovery of high-dimensional quantum steering.
Read the full abstract

All authors Pu Wang, Zhongyan Li, Huixian Meng, Yutao Xin. Ziqi Zhi, Zhihua Guo, Huaixin Cao

Data Structures and Algorithms

Load Balancing with Item Fragmentation and More Bins than Items: Linear-Time and Exact

We study a fundamental load-balancing problem in which $N$ items of strictly positive integer sizes with total size $W$ must be assigned to $B$ bins, with items allowed to be divided into integer-size fragments across bins. Each bin must receive a load of either $\lfloor W/B \rfloor$ or $\lceil W/B \rceil$, ensuring that the loads of any two bins differ by at most one unit. Under this constraint, the objective is to minimize the maximum number of distinct item fragments placed into any single bin. This problem is NP-hard and there exists an $(\mathrm{OPT}+1)$-approximation algorithm that runs in $O(N \log N + B)$ time [Kobert et al., 2014]. The existing algorithm is employed by several widely used production codes for phylogenetic reconstruction. Here, we focus on the case $B \ge N$, that is, bins are at least as numerous as items. This setting arises pervasively in modern parallel and distributed systems, as well as in iterative algorithms that rebalance their workload at every step. In this context, bins are machines or machine cores, and items represent computational tasks (jobs). Our central contribution is a remarkably simple $O(N)$-time algorithm that computes an optimal assignment in this setting; this assignment is encoded using $O(N)$ space. In particular, we prove that an optimum always exists in which every bin receives at most two fragments and provide a characterization of when one fragment per bin suffices. Our result strictly improves the $(\mathrm{OPT}+1)$-approximation of Kobert et al. in the many-bins setting and, together with it, yields a strongly polynomial-time $(\mathrm{OPT}+1)$-approximation algorithm for the general setting, as it removes the dependency on the number $B$ of bins.
Read the full abstract

All authors Ben Bals, Tomáš Flouri, Kassian Kobert, Solon P. Pissis, Leen Stougie

Robotics

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

Scaling up visual humanoid loco-manipulation skill acquisition requires reducing the human effort needed as tasks and spatial configurations expand, particularly in demonstration collection and task-specific training design. We present SUGARv2, a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. To obtain diverse references at low cost, we adapt reusable task templates to different spatial configurations, synthesizing coordinated robot and object motions. To reduce task-specific reward design and training effort, we use reference-based imitation as a common learning objective across tasks. We first train privileged teachers to execute these references, then train visual policies through teacher distillation and reinforcement learning with the same reference-based mimic rewards, using diverse object instances and visual domain randomization to support visual generalization and sim-to-real transfer. Across five humanoid loco-manipulation tasks, SUGARv2 achieves a mean success rate of 91.0% in simulation. Deployment on a real humanoid robot further demonstrates successful sim-to-real transfer for whole-body manipulation. These results demonstrate the framework's potential for learning diverse visual humanoid loco-manipulation skills.
Read the full abstract

All authors Tianshu Wu, Tianxiang Gui, Yue Chen, Tingxu Liu, Ziye Peng, Guangjie Yang, Xiangqi Kong, Ye Shi, Jingya Wang, Hao Dong

Systems and Control

Reconciling European Electricity Data with Diffusion Priors Learned from Observations Alone

The ENTSO-E Transparency Platform publishes generation, load, and cross-border power flows for European bidding zones. The values carry undocumented errors and violate energy conservation, and data reconciliation consists in correcting them to satisfy that balance. In this work, we formulate data reconciliation as Bayesian inference. Classical methods implicitly take a uniform prior, which we replace with a diffusion model estimated from the observations alone by empirical-Bayes expectation-maximization. The resulting posterior is sampled with a guided process whose projection step makes every sample satisfy the balance exactly. On synthetic systems of six to thirty-five bidding zones, built from ENTSO-E resource-adequacy data, the diffusion prior gives the most accurate reconciliation, increasingly so as the system grows. Its credible intervals are calibrated or conservative, and it remains the most accurate under a misspecified noise covariance. Finally, when the generation of entire zones goes unreported, the classical methods fail while the learned prior recovers it from cross-zone structure.
Read the full abstract

All authors Matthias Pirlet, Adrien Bolland, Gilles Louppe, Damien Ernst

Artificial Intelligence

Nudging Decision Models: Do Digital Nudges Steer Fast, Generation-Free AI Agents?

LLM-based agents increasingly automate business and consumer tasks but are slow and expensive. Decision models, a new class that chooses among options without generating text, are far faster and less costly. Developers call them "System One models," referencing dual process theory. We ask whether such models can be steered by digital nudges online and whether, as the theory predicts, automatic nudges affect them more than reflective ones. We adapted an online shopping experiment, previously run with humans and LLM agents, to three decision models (Jev, Decision-1, d1). Across 600 runs per model, they chose a preselected default in 97.5-99.9% and a product with social influence information in 75-96% of choices, versus 47-49% in the control. All responded more strongly to the automatic nudge, the opposite of what has been reported for reasoning-capable LLM agents. We provide first evidence that non-generative decision models are susceptible to digital nudges in a System 1 pattern, implying agent-type-specific nudge effects.
Read the full abstract

All authors Sascha Kaltenpoth, Haya Halimeh, Kevin Bösch, Oliver Müller

Artificial Intelligence

Model-based learning for DoA estimation and array calibration via continuous sparse recovery

Direction of arrival (DoA) estimation, a classical signal processing problem, has experienced renewed interest with the advent of integrated sensing and communication (ISAC). While decades of research have yielded highly accurate DoA estimators, hardware impairments have frequently been neglected, despite degrading both DoA estimation accuracy and downstream communication performance in ISAC systems. This work introduces a joint array calibration and DoA estimation method based on the simultaneous orthogonal matching pursuit (SOMP) algorithm, following the model-based machine learning paradigm. The proposed method enables the calibration of antenna arrays subject to severe gain-phase and antenna location impairments through projected gradient descent (PGD), with either supervised or unsupervised objectives. Additionally, DoA estimation is enhanced by extending SOMP to continuous dictionaries via PGD refinement steps. Simulation results demonstrate that the proposed method enables efficient hardware impairment compensation, even without labeled samples, while outperforming conventional sparse recovery and subspace-based DoA estimation baselines.
Read the full abstract

All authors Baptiste Chatelier, José Miguel Mateos-Ramos, Vincent Corlay, Matthieu Crussière, Christian Häger, Henk Wymeersch, Nir Shlezinger, Luc Le Magoarou

Computational Complexity

Path Isolation and Reachability in Surface-Embedded Graphs with Restricted Cycle and Cut Structure

We study the reachability problem in directed surface-embedded graphs under two structural restrictions, using isolating weight assignments. First, we consider graphs whose underlying undirected embeddings contain at most polynomially many simple surface non-separating cycles. We develop a polynomially bounded, logspace-computable skew-symmetric edge-weight assignment with nonzero circulation around every simple cycle. This yields an unambiguous logspace (UL) upper bound for directed reachability. The construction also gives an SPL upper bound for bipartite perfect matching in the corresponding undirected graph class. Second, for $g$-genus directed graphs admitting a balanced hierarchical genus decomposition with $O(\log n)$ crossing edges at every partition, we obtain an unambiguous $O(\log g \cdot \log n)$-space bound for reachability. Our approach combines path-isolating weights for lower-genus subgraphs using polynomially bounded FKS hashing refinements at successive merging levels.
Read the full abstract

Optimization and Control

Tracking of a Moving Target on a Hyperboloid and its Extension to Leader-follower Formation Controller

This paper proposes a novel controller for a double-integrator agent to track a moving target with bounded velocity on a hyperboloid $\mathbb{H}^n$. The control law uses the intrinsic Riemannian structure of the hyperboloid, including the logarithm map, covariant derivative, and parallel transport, to make all its terms coordinate-free. Such formulation eases the implementation of the proposed tracking controller in the ambient Minkowski space without doing any additional chart computations. We use Barbalat's lemma for the hyperboloid to establish the convergence proof. Later, the proposed tracking controller is extended to a leader-follower formation control, where each agent reaches at a desired position around a moving leader in $\mathbb{H}^n$. We validate the results with numerical simulations considering two different target trajectories, geodesic and spiral, as examples.
Read the full abstract

All authors Ashish Shukla, Sanad Shaha, Kashyap Rajeevsarathy, Arijit Sen

Software Engineering

Navigating Complexity: A User-Centered Evaluation of Project Management Tools

In the age of digital transformation, companies are increasingly relying on specialized software to manage the complexity of projects. However, when selecting tools, features and costs often take precedence over user experience (UX), leading to low adoption rates, user frustration, and project delays. This study empirically evaluates the user experience of leading project management tools (Jira, Trello, Monday.com, Asana, and Microsoft Project) across various project scales using a mixed methods approach. The System Usability Scale (SUS) was used as the primary quantitative instrument, with data collected from 141 experienced professionals via online questionnaires. The results reveal a significant trade-off between functionality and usability. Trello achieved the highest SUS score (77.5), indicating a superior user experience for small projects and agile teams, while Microsoft Project scored the lowest (51.2), suggesting significant usability challenges despite its robust features. Jira demonstrated a balanced profile, offering powerful features with manageable complexity. Statistical analyses confirmed that the choice of the optimal tool is highly context dependent, with team size and project complexity influencing UX outcomes. The findings underscore that UX is not a secondary feature but a critical success factor for software acceptance and project effectiveness. This study provides an evidence-based framework for aligning tool selection with the project context, offers practitioners actionable insights, and identifies design opportunities for software developers.
Read the full abstract

Artificial Intelligence

Forecasting cumulative intraoperative hypotension burden: patient-disjoint evaluation of quantile boosting and alert policies

Background: Binary hypotension forecasts do not describe the depth and duration of future low pressure. Burden forecasts may support graded early warning, but better forecast scores need not yield more useful alerts. Objective: To evaluate conditional quantiles of the next 15-minute mean arterial pressure (MAP) deficit below 65 mmHg and distinguish forecasting performance from episode-warning performance. Methods: Public VitalDB numeric arterial MAP was reduced to 10-second medians without forward filling. Subject-disjoint training, validation and test splits included 70,402, 14,270 and 15,575 labeled windows. We compared climatology, calibrated persistence, last-MAP-only boosting, and direct and residual quantile boosting, with and without additional MAP-history features. Patient-weighted pinball loss and subject-bootstrap intervals evaluated forecasting. Validation selected alert thresholds before a hash-recorded test evaluation. Results: In the test split, the prespecified residual-versus-persistence comparison at the 90th percentile yielded losses of 2.256 and 2.900 mmHg-min, respectively (difference -0.644; 95% interval -0.814 to -0.487). Direct prediction achieved 2.196, and direct prediction with additional MAP features achieved 2.193. Episode-warning results were sensitive to the alert rule and operating threshold. Conclusions: This retrospective benchmark separates burden-forecast skill from warning-policy performance. Findings support further study of direct burden estimation; they do not establish patient benefit, prospective reliability or transportability beyond the source hospital.
Read the full abstract

Materials Science

Non-trivial topological spin-polarized surface states induced nonreciprocal transport in the hourglass semimetal

Quantum materials such as topological semimetals have gained consummate interest due to their exotic band crossings and protected surface states. In particular, Ta$_3$GeTe$_6$ has emerged as a prototypical hourglass Dirac semimetal, as confirmed by both experimental and theoretical analysis. The ARPES confirms the topological hourglass-type band dispersions and Rashba-type band, while Hall measurements reveal a high hole carrier concentration and nonreciprocal transport behavior. These findings are further supported by a phenomenological toy model, which predicts a nonreciprocal resistance, consistent with the observed direction-dependent magnetoresistance. Furthermore, the Raman spectroscopy uncovers two-fold and four-fold phonon symmetries drag of highly anisotropic phonons, which establishes symmetry-dependent resistance. DFT calculations reveal Dirac-like and hourglass Dirac band crossings near the Fermi level for the bulk, with Rashba-type spin splitting induced by the surface inversion-symmetry breaking, leading to spin-polarized surface states. The combined experimental and theoretical results demonstrate that Ta$_3$GeTe$_6$ hosts a non-trivial electronic topology, with the inversion-symmetry breaking at the surface as the driver of this nonreciprocal transport behavior.
Read the full abstract

All authors Zahir Muhammad, Ghulam Hussain, Zia ur Rehaman, Rajibul Islam, Igor Antoniazzi, Muhammad Ismail Khan, Carmine Autieri, Maciej R. Molas, Xiaoguang Li, Xiaoyang Lina Azizur Rahmana, Weisheng Zhaoa

Differential Geometry

A splitting theorem for Einstein manifolds with symmetries

We prove that every negative-Einstein manifold with cocompact symmetries splits isometrically as a Riemannian product $H \times K$ with $H$ homogeneous and $K$ compact. This confirms a conjecture due to Böhm and Lafuente. As a consequence, we obtain a new proof of the 1975 Alekseevskii conjecture.
Read the full abstract

Artificial Intelligence

Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception

Cooperative perception enables an ego agent to acquire information from collaborators beyond its own sensors' reach. Yet, the most beneficial messages are often the hardest to verify from local observations. Pretend Benign (PB) exploits this asymmetry by targeting regions with weak local verifiability and applying multi-objective perturbations, making harmful feature changes appear to be benign assistance. However, PB is victim-dependent: selecting regions and optimizing perturbations require the victim model's architecture, parameters, and gradients, limiting transfer to unseen victims. A transferable attack must capture properties shared across cooperative detection models rather than those specific to one network. We address this by building a victim-agnostic attack from a heterogeneous ensemble of surrogate models and encoding its capabilities in a reusable dictionary to reduce per-message generation cost. Specifically, Transferable Pretend Benign (TrPB) transfers PB's region selection criterion and multi-objective perturbation strategy across heterogeneous surrogates to construct an offline attack. We further propose RT-TrPB, which encodes transferable regions and perturbation patterns into a region predictor and reusable perturbation dictionary, amortizing per-message attack generation. Experiments on widely used cooperative perception benchmarks show that RT-TrPB bypasses the consensus-based defenses ROBOSAC and FLD with success rates approaching 100% and generates each perturbation in under 56 ms. To counter PB-style attacks masquerading as benign collaboration, we also propose STTrust, which verifies received messages using spatial and temporal consistency and incorporates identity-level trust. STTrust detects over 90% of PB-style attacks and restores perception performance to near the attack-free level.
Read the full abstract

All authors Hongwei Lin, Xun Huang, Chenglu Wen, Cheng Wang

Materials Science

A Compact High-Repetition-Rate Intense THz Source for Atomic-Scale Materials Characterization

High-intensity terahertz (THz) sources combining high repetition rates, strong field amplitudes, and long-term stability are key enabling technologies for next-generation ultrafast photonics. However, simultaneously achieving these characteristics in a compact and practical architecture remains a major challenge. Here, we report a high-performance tabletop THz source delivering intense single-cycle pulses at 100 kHz, generated by optical rectification in lithium niobate using an optimized echelon-based tilted-pulse-front scheme and driven by an industrial-grade ytterbium laser. The source achieves optical-to-THz conversion efficiencies exceeding 0.13% at room temperature, peak electric fields of several hundred kV/cm, and excellent long-term stability, establishing a robust platform for high-average-power strong-field THz applications. As a proof of concept, the source was integrated into an atom probe tomography (APT) instrument. APT reconstructs the three-dimensional chemical composition of materials through field-induced ion emission from a sharp nanotip. While THz-assisted ion emission has been shown to improve analytical performance by reducing thermal effects, previous demonstrations were limited to low-repetition-rate THz sources, restricting throughput and accessible analysis volumes. Using an aluminum nanotip, we demonstrate efficient THz-assisted APT at 100 kHz and benchmark its performance against conventional voltage- and laser-assisted operation. The high repetition rate enables rapid large-volume acquisition while improving mass resolving power, reducing thermal tailing, and preserving high-quality three-dimensional reconstructions. Beyond APT, this work establishes a compact and scalable high-repetition-rate THz platform for strong-field physics, nonlinear THz photonics, ultrafast spectroscopy, and material characterization at the nanoscale.
Read the full abstract

All authors Léo Guiramand, Florant Exertier, Alexandre Fahy, Anna Martinez, Matteo de Tullio, Saïd Idlahcen, Jonathan Houard, Gerald da Costa, Thomas Godin, Xavier Ropagnol, Domenico Paparo, François Blanchard, Angela Vella, Ammar Hideur

Hardware Architecture

TwinHash: Two-Sided Object Identity Management for Time- and Energy-Efficient Agentic Workflows

Agentic artificial intelligence (AI) services interleave large language model (LLM) generation with external tool execution, and increasingly rely on search-based workflows that repeatedly revisit shared reasoning states and computations. These patterns create substantial redundancy across tool outputs, LLM responses, and key-value (KV) prefixes, yet existing serving systems primarily optimize shared prompt prefixes, while naive input-keyed caching is unsafe when identical requests produce different outputs. We present TwinHash, a unified object management architecture that assigns each object an input-side hash key to recognize repeated requests and an output-side content fingerprint to validate and locate stored state, complemented by type-specific reuse guards that preserve correctness and response diversity. A software object identity table maintains reusable objects across requests and trajectories, while a hardware object placement table tracks their residency across hierarchical memory tiers so that evicted state can be retrieved rather than recomputed. Across seven agent frameworks and five benchmark suites, reuse follows workflow structure more than benchmark identity. TwinHash serves up to 81% of tool outputs wherever deterministic tool reads recur, and up to 92% of LLM responses in search-based frameworks. Retrieving an evicted KV-prefix from DRAM reduces TTFT by up to 5.6x on Qwen3-32B, with greater gains projected for larger dense models. Under search-based frameworks, TwinHash reduces end-to-end wall-clock time by up to 87% and measured task energy by up to 81% over a prefix-cached baseline, while a per-key serving cap controls the quality-reuse trade-off in adaptive search. These results demonstrate that unified identity, safety, and placement management can convert structural redundancy in emerging agentic workflows into substantial serving-efficiency gains.
Read the full abstract

All authors Sangbu Yun, Jung Gyu Min, Jin Hyun, Jeonghwan Ahn, Youngjoo Lee

Quantum Physics

Evaluation of Quantum Machine Learning Models for Network Anomaly Detection

The proliferation of Internet-connected devices has intensified the risk of large-scale network intrusions, necessitating more advanced detection methodologies for the post quantum era. This work presents, to the best of our knowledge, a com- prehensive investigation of quantum machine learning (QML) for anomaly detection on the BoT-IoT dataset, a widely adopted benchmark for IoT security. Leveraging feature-engineered rep- resentations, we implement and evaluate four representative quantum classifiers: Quantum Support Vector Classification (QSVC), Quantum Neural Networks (QNN), and Variational Quantum Classifiers (VQC).
Read the full abstract

Machine Learning

Rethinking MoE Load Balancing as Feedback Control

Mixture-of-Experts (MoE) training is often not stationary: the data mixture changes at curriculum boundaries, when a model is continually pretrained into a new domain, or when the corpus is refreshed. Routing is learned against the current mixture, so each such change disrupts the per-expert load the router had converged to, and existing balancing methods have only been evaluated on stationary data. We rethink load balancing as a feedback control problem, in which the deviation of each expert's load from its fair share is the control error and the per-expert routing bias is the control input, and define a family of controllers, the PID-Balancer, from the proportional, integral, and derivative terms of classical PID control. Two widely used methods belong to this family: the auxiliary balancing loss behaves like a proportional controller, and the loss-free bias update is an integral controller acting on the sign of the error. Reading the router as a static map with a one-step delay, we show that the integral term is the only one that both removes persistent imbalance and averages out the step-to-step fluctuation of the measured load, whereas the proportional and derivative terms pass or amplify that fluctuation into the routing bias. We therefore adopt PID (I), the pure-integral member of the family with a single gain. Two settings are evaluated: (i) training an OLMoE backbone from scratch with 16 to 64 experts per layer, through a mid-run mixture switch, and (ii) continual pretraining of the released OLMoE-1B-7B on a new corpus. PID (I) holds balance before the shift and restores it more tightly afterwards than either the auxiliary loss or loss-free balancing, at comparable perplexity.
Read the full abstract

Distributed Computing

Green500: Adventure in Qualifying a Cluster

Energy effciency has become a key metric for evaluating High Performance Computing (HPC) systems, as reflected by the Green500 ranking. However, energy effciency alone does not capture the full environmental impact of an HPC cluster. Using the Kuma cluster at EPFL, we report on two Green500 measurement campaigns at Level 2 and Level 3, and extend this analysis to a full carbon footprint assessment using the MITSI life-cycle based methodology. GPU power capping experiments show that energy effciency peaks at 450 W, achieving an 11% performance loss offset by a 20% reduction in energy consumption. When embodied emissions are accounted for, the optimal power cap for carbon effciency shifts to 500 W under Switzerland's low-carbon electrical grid, revealing a tension between minimizing usage and embodied contributions. We discuss the challenges of generalizing this approach into a broader carbon-based HPC ranking, and argue that moving beyond energy effciency is both necessary and feasible.
Read the full abstract

All authors Nicolas Richart, Xavier Ouvrard, Julia Paolini, Manuel Cubero-Castan, Gilles Fourestey

Optics

Redetermination of the second-order nonlinear optical coefficients of BaMgF4

BaMgF4 (BMF) has the potential to serve as a platform material for vacuum-ultraviolet (VUV) nonlinear optics owing to its ferroelectricity and high UV transparency down to 130 nm. However, the second-order nonlinear optical coefficients reported for BMF span approximately one order of magnitude, hindering a reliable assessment of its potential for nonlinear optical applications. Here, we redetermined these coefficients by combining Maker fringe, wedge, and single-pass second-harmonic-generation measurements at a fundamental wavelength of 1064 nm. Our results establish that all the second-order nonlinear optical coefficients of BMF lie in the range of 0.01-0.04 pm/V. We determined d31 to be 0.035 pm/V, which is among the largest coefficients of BMF, while it has been underestimated relative to the other coefficients in previous studies. Although d31 is not the largest coefficient, the use of its long corresponding coherence length is beneficial for quasi-phase matching, particularly for VUV generation, where the fabrication of lower-order quasi-phase-matching structures is crucial.
Read the full abstract

All authors Shoichi Ui, Simon J. Herr, Gaetano G.M. Bonetti, Ingo Breunig, Fraunk Kühnemann, Matthias Bickermann, Hiroki Tanaka

General Relativity and Quantum Cosmology

Optical Geometry of a Lorentz-Violating BTZ-Like Black Hole: Reflection Double and Dirac Scattering

We analyze the optical geometry of a static BTZ-like black-hole metric with a Lorentz-violating radial factor, distinguishing the one-sided black-hole exterior from the reflection double constructed from its optical spatial section. The optical metric is ultrastatic and has constant negative Gaussian curvature. The reflection double is smooth and complete, with a minimal circle; it is a geometric completion, not a demonstrated solution of the Einstein–bumblebee equations. We derive exact criteria for null-geodesic crossing and return, evaluate the corresponding angular sweeps, and determine the finite domain of a Euclidean surface-of-revolution embedding. Two inequivalent magnetic configurations are specified as external test fields on the embeddable patch. For a continuum graphene analogue on the doubled geometry, we derive the covariant massless Dirac operator and reduce its radial equation to Scarf-II partner equations. The full-line connection problem yields flux-normalized complex scattering amplitudes and probabilities, the resonance-pole lattice and its gamma-function residues, spectral widths and quality factors, the digamma Wigner delay, and conditional pole contributions to packet dynamics. We compare the analytic amplitudes with direct numerical integration of the radial partner equation, including their complex phases. We further separate fixed-$\ell$ from fixed-$\Lambda_e$ parameter protocols and audit the optical effective-mass degeneracy using Lorentzian curvature invariants, timelike geodesics, and a massive Klein–Gordon probe. Throughout, the gravitational completion, prescribed fields, and continuum scattering results are interpreted only within the scope of their respective constructions. Device-level graphene transport and a self-consistent gravitational wormhole require additional physical input.
Read the full abstract

Machine Learning

Topology as a Design Variable: Joint Architecture-Sizing Optimization for SRAM

SRAM's power-performance-area-stability trade-off depends on bitcell topology, a discrete architectural choice that interacts non-separably with continuous transistor sizing. However, no open-source SRAM tool treats topology as an optimizable variable. OpenRAM generates SRAM layouts but performs no optimization, while OpenYield supports high-fidelity evaluation but restricts optimization to scalar sizing of a fixed 6T cell. OpenYieldV2 closes this gap through three integrated contributions. First, a fully parameterized compiler generates complete 6T and 10T SRAM macros with peripheral circuits and replica-bitline self-timing, enabling topology comparison under identical simulation conditions. Second, a few-shot TabPFN surrogate learns topology-dependent PPA responses with limited full-macro SPICE samples. Third, a coarse-to-refined multi-objective optimizer combines global exploration of discrete architectural choices with local refinement of continuous transistor sizes. Experiments across varying design conditions reveal a topology decision boundary that shifts with operating constraints rather than following a fixed design rule. Jointly optimizing across this boundary improves hypervolume by up to 17.3% over the strongest single-topology baseline. OpenYieldV2 is open-source to support reproducible SRAM design research.
Read the full abstract

All authors Can Wang, Junhao Ma, Yikai Wang, Shan Shen, Wei W. Xing

Machine Learning

Practical Non-Stationary Graph Gaussian Processes

Gaussian processes on graphs provide a principled framework for prediction and uncertainty estimation, but modelling heterogeneous networks often requires balancing flexibility against parameter complexity. Variability at a node may reflect useful signal that should propagate through the network, unreliable measurements whose influence should be suppressed, or a mixture of both. We introduce Variance-Coupled Gaussian Processes (VCGPs), which use a positive auxiliary signal to modulate graph interactions through a single learned coupling exponent. The exponent controls how strongly high-variability nodes propagate or attenuate information, while a cluster-wise extension accommodates different regimes within the same graph. Under stated structural assumptions, we characterize the unique stationary-rescaling point of the basic family, where correlations match those of a stationary graph kernel while node-dependent variances remain. Experiments on traffic, air-quality and weather datasets show competitive prediction and uncertainty estimation relative to stationary and per-node non-stationary baselines, with the largest gains on networks requiring multiple coupling regimes. Stationary correlations after variance rescaling remain sufficient on some data, and performance depends on the auxiliary signal and model selection.
Read the full abstract

Nuclear Theory

Quasi-hydrodynamics beyond the conventional paradigm

Quasi-hydrodynamics extends hydrodynamics by promoting slowly relaxing variables to additional degrees of freedom. For such a framework to be rigorously defined and parametrically controlled, the effective theory is usually assumed to retain all the slow modes of the underlying microscopic dynamics, which must be parametrically separated from the rest of the microscopic spectrum and typically arise from weakly broken symmetries. Here, we show that none of these assumptions is essential. Using the effective field theory of quasi-hydrodynamics recently derived from kinetic theory, we study three models that challenge the need for, respectively, parametric scale separation, retaining every slow mode, and a weakly broken symmetry. In all cases, the quasi-hydrodynamic expansion remains fully controlled and can be made arbitrarily accurate. This is possible because the applicability of quasi-hydrodynamics is determined not by the microscopic origin of the slow dynamics, but by the spectral properties of the kinetic operator on a suitably chosen Hilbert space.
Read the full abstract