Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science

cs Watch Computer Science (sign in to use)

Tuesday 18 August

Machine Learning

Efficient Resource Optimization for Split Federated Learning

Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model splitting and resource allocation, resulting in a challenging mixed-integer problem. Consequently, prior optimization schemes for SFL are either heuristic or computationally inefficient, which cannot handle large-scale user populations. To address this limitation, this work establishes an efficient optimization framework for SFL under resource-constrained networks. Our framework jointly optimizes model splitting and resource allocation to minimize training cost, which is defined as the weighted sum of latency and energy costs. We first study the model splitting problem and develop a polynomial-time algorithm that achieves the global optimum. Then, we extend the approach to the joint model splitting and resource allocation problem. In this case, we formulate it as a two-dimensional master problem and develop an efficient approximation method with a $(1+\epsilon)$-approximation guarantee. Extensive experiments show that the proposed approach provides efficient solutions to strike the optimal energy–latency tradeoff.
Read the full abstract

Machine Learning

MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models

Geospatial Foundation Models (GFMs) are emerging as a powerful paradigm for learning semantically rich and geographically consistent visual and physical representations. However, their reliance on Earth-observation (EO) data leaves information about human activity largely underrepresented. Human mobility data reveals the functional and relational structure between regions that is missing from EO data, but is often limited only to the city where it is observed, making it challenging to use for transferable urban representation learning. We introduce MoRAX, a lightweight framework for augmenting geospatial embeddings with functional structure derived from human mobility. MoRAX preserves the coverage and consistency of a GFM while providing information about the functional connectivity among urban regions, permitting zero-shot deployment in unseen cities with or without available mobility data. Across four target cities spanning two countries, the MoRAX teacher model, which observes mobility, consistently outperforms GFMs and strong urban representation baselines in eight socioeconomic and environmental prediction tasks. Meanwhile, the student model, which never takes mobility data as input, approaches the teacher in performance on most tasks. Transfer results across countries further demonstrate that modulation conditioned on mobility flows provides a general mechanism for grounding geospatial foundations in the human dimension of cities.
Read the full abstract

All authors Ya Wen, Jixuan Cai, Yulun Zhou, Alec Kirkley

Numerical Analysis

Duality-Based $\textit{A Posteriori}$ Error Identities for Subgradient Flows Based on the Brézis-Ekeland-Nayroles Principle

We derive duality-based $\textit{a posteriori}$ error identities for a broad class of subgradient flows induced by time-dependent convex integral functionals. Starting from the Brézis-Ekeland-Nayroles principle, we identify an unsteady primal energy functional and derive its Fenchel dual formulation, including strong duality and the corresponding optimality system under general normal-integrand assumptions. This Fenchel duality framework is used to derive $\textit{a posteriori}$ error identities for subgradient flows. In doing so, we depart from the usual duality-based $\textit{a posteriori}$ error control framework in the unsteady setting, since the Brézis-Ekeland-Nayroles formulation reveals the following unsteady feature: the minimal primal value and the maximal dual value are both prescribed by the initial datum. This allows us to pass from a combined primal-dual gap identity to separate primal and dual gap identities. These identities quantify the primal and dual errors independently and admit representations in terms of generalized Bregman divergences and, under a spatial convex conjugation formula, as non-negative time-space integral quantities suitable for localization. The abstract framework is applied to a number of variational problems of physical interest, including the unsteady heat equation, the unsteady Stokes equations, the unsteady Navier-Lamé equations, the unsteady Bingham flow through a pipe, the unsteady obstacle problem, and the unsteady elasto-plastic torsion problem.
Read the full abstract

Numerical Analysis · Cross-listed from physics.comp-ph

Investigation of the Asymptotic Properties of Active Impedance in Large Finite Array Antennas

This paper presents an improved full-wave solver for finite array antennas, and uses this solver to examine asymptotic properties of active impedance for large regular arrays. The improved solver is based on a preconditioning scheme that has been adapted for use on more general finite geometries, and an improved data structure. These two improvements result in a fast and stable solver with a lower memory footprint. By investigating the active impedance of the center element in finite arrays it is found that, even for arrays with 1000 elements, asymptotic behavior may differ appreciably from infinite arrays. Tied to these properties, different predictors on how the active impedance of the center element in the array behaves are presented. The two best predictors work very well for the wideband arrays investigated, and may be used to decide when array approximations, such as unit cell methods, are appropriate, rather than general statements on array size.
Read the full abstract

Computation and Language

Decodable but Not Actionable: Auditing the Representation-Behavior Gap in Frozen LLMs for Geometric Constraints

Large language models (LLMs) perform well on structured reasoning tasks, but what they encode and whether encoded information guides their behavior remain unclear. We introduce a controlled auditing framework that uses parametric CAD to distinguish failures of encoding, expression, and activation-level control. Applied to eight pretrained models and matched randomly initialized controls, our framework reveals that pretraining contributes substantially more to linear decoding of local relations than to global constraint status, which is already highly decodable from random representations. Yet strong local decodability does not translate into the models' zero-shot predictions, which remain far below supervised probe performance. Restoring clean internal activations can repair probe predictions, whereas simple activation steering does not provide reliable targeted control. With only 400 labeled relation pairs, low-rank fine-tuning substantially improves generation on three representative models, showing that the representation–behavior gap can be reduced through adaptation. Together, these findings show why decodability alone is insufficient evidence that encoded information will be expressed or controllable in model behavior.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-case regret $\mathcal{R}_{K,T}$ and instability $\mathcal S_{K,T}$, defined as the largest standard deviation of a terminal pull count, for $K$ arms and $T$ rounds. We prove the finite-time lower bound $\mathcal R_{K,T}\mathcal S_{K,T}\ge C T^{3/2}$, where $C$ is independent of $K$ and $T$, under a finite-time regret condition and without the regularity assumptions imposed in the prior asymptotic analysis. We also introduce Stabilized Lower-Envelope UCB (\textup{SLE-UCB}), a new tunable algorithm combining a running lower-envelope index with a decreasing pull-count stabilizer. \textup{SLE-UCB} satisfies $\mathcal R_{K,T}\mathcal S_{K,T}=O(T^{3/2}\log K)$, with an implicit constant independent of $K$ and $T$, matching the lower bound exactly in $T$ and within a logarithmic factor in $K$. To prove the instability bound, we develop a new offline top-prefix representation that removes path dependence from online decisions. Together with single-reward perturbations and the Efron–Stein inequality, this representation controls pull-count variance. Thus, regret and instability depend reciprocally on $K$, while their product has no polynomial dependence on $K$. These results resolve the open question raised in the literature concerning the sharp arm-dependent regret–instability frontier.
Read the full abstract

Machine Learning

Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from the field of Knowledge Editing. Our choice is motivated by the observation that models edited with such schemes tend to assign unusually high prediction probabilities to the edit target, a property that is particularly advantageous when designing attacks. We modify the editing framework by incorporating as- sociative knowledge retrieved from the model, thereby extending constraint removal to an entire thematic category rather than being limited to prompts from a predefined dataset. Experiments with various archi- tectures demonstrate improved attack effectiveness over competing methods without dealing critical damage to general model performance.
Read the full abstract

All authors Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov

Data Structures and Algorithms

Parameterized complexity of $k$-Coloring in graphs with no long induced paths

We study the parameterized complexity of (List) $k$-Coloring in $H$-free graphs, where $H$ is a linear forest, that is, a disjoint union of paths. First, considering $k$ as the parameter, we establish the following: * For any $s \geq 0$, List $k$-Coloring in $(P_4+sP_1)$-free graphs is fixed-parameter tractable (FPT). * $k$-Coloring is W[1]-hard in $2P_2$-free graphs. The second result settles, in a strong form, a long-standing open problem posed by Hoàng, Kamiński, Lozin, Sawada, and Shu [Algorithmica, 2010]. Next, we prove that $k$-Coloring is NP-hard in $(P_4+P_2)$-free graphs. These three findings, together with known results from classical, non-parameterized complexity, yield a complete complexity classification of $k$-Coloring and List $k$-Coloring in $H$-free graphs, parameterized by $k$, into the cases: FPT, XP but W[1]-hard, and paraNP-hard. We also prove that $3$-Coloring is W[1]-hard in $P_t$-free graphs when parameterized by $t$. This answers a question of Golovach, Johnson, Paulusma, and Song [Journal of Graph Theory, 2017]. Finally, as a byproduct of our algorithm for List $k$-Coloring in $(P_4+sP_1)$-free graphs, we show that, for every fixed $s$ and $k$, there are only finitely many $(P_4+sP_1)$-free minimal obstructions to $k$-colorability. This settles a conjecture of Cameron, Hoàng, and Sawada [Disc. Appl. Math., 2022] and completes the dichotomy concerning the finiteness of the family of vertex-$k$-critical $H$-free graphs for every graph $H$ and every $k$.
Read the full abstract

Human-Computer Interaction

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding an agent's evolving reasoning and evidence, and steerability for redirecting low-value directions or deepening promising ones during execution. Existing interactive approaches improve process visibility and open intervention points, but they remain largely designed for discrete, turn-by-turn exchanges rather than the parallel branches and evolving decision structures of long-running agentic analysis. We study this need as interactive oversight in long-running agentic data analysis and present AdaLens, an interactive system for monitoring and steering ongoing runs. AdaLens combines a storyline-based representation that unifies analytical plans, execution progress, intermediate findings, and data-column involvement with steering interactions grounded in these analytical elements for directional guidance and execution control. We evaluate AdaLens through two case studies and a user study, examining how it supports analysts in monitoring and steering long-running agentic data analysis.
Read the full abstract

All authors Yangtian Liu, Yan Miao, Shuhan Liu, Yunfan Zhou, Dae Hyun Kim, Di Weng, Yingcai Wu

Graphics

Variational r-Adaptive Cloth Simulation

We present the first r-adaptive method for simulating cloth dynamics and statics with frictional contact in modern cloth pipelines. Thin cloth requires high effective spatial resolution to reproduce wrinkles, folds, buckling, and sharp contact features. However, applying existing variational r-adaptivity to piecewise-linear shells reveals two coupled failure modes. Discretized incremental-potential (IP) optimization can become trapped in poor local minima, yielding suboptimal physical configurations. It can also lower IP artificially by collapsing elements, invalidating the finite-element approximation on which the objective relies. We address both problems with degeneracy-activated quality regularization. The regularizer remains inactive for well-shaped elements, preserving anisotropic adaptation and local densification, but becomes strong near degeneracy. It suppresses spurious low-energy basins, improves escape from suboptimal physical minima, and prevents element bunching, a cloth-specific failure in which elements progressively collapse as cloth slides across sharp contact features. For practical performance, we introduce a dynamic nonlinear solver that exploits within-timestep coherence through accelerated derivative evaluation and dynamic IPC tolerance updates for r-adaptive iterative trust-region (ITR) solves. This yields a 3-6x speedup over prior optimal ITR. Experiments on challenging frictional-contact scenarios show that, under equal vertex-count and time-budget constraints, our method achieves higher visual fidelity than fixed meshes.
Read the full abstract

All authors Jiahao Wen, Zhen Chen, Jernej Barbič, Danny M. Kaufman

Computer Vision

GenRec: Knowing Where to Reconstruct and Where to Generate

Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction–generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach.
Read the full abstract

All authors Ata Çelen, Jaewoo Jung, Federico Tombari, Marc Pollefeys, Sunghwan Hong, Michael Niemeyer, Daniel Barath

Cryptography and Security

The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges

LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts alongside user queries creates an attack surface: adversarial inputs can induce models to disclose them. Prior probing studies suggest that leakage-related signals emerge in hidden states, yet the need to extract these states poses additional deployment challenges. In this paper, we explore whether this internal signal leaves a more accessible “tell” before decoding. We propose LeakGauge, which probes this response by appending a suffix that gauges leakage behavior and mapping its prefill token probabilities to an attack-risk score. While a direct gauge uses the initial tokens of confidential content, we find that a content-agnostic one that verbalizes leakage behavior yields more robust signals. Across 11 LLMs, including GLM-5.2 (753B) and Kimi-K3 (2.8T), LeakGauge reaches an AUROC range of 0.944–0.996 on unseen attacks. The signal remains stable when the content changes language or the attack shifts from verbatim to semantic disclosure. By activation-steering interventions, we further show that the risk score is sensitive to an internal leakage-related direction, relating the observable signal to the model's internal representation. In addition, LeakGauge enables an input detector with fewer than 0.5K extra parameters and added latency of 10.34 ms. Code: \href{https://github.com/yeasen-z/LeakGauge}.
Read the full abstract

All authors Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu

Computation and Language

From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector

Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily reflect English-language and US-centric settings, and often only evaluate task performance. In this paper, we present first results of MÖVE, a holistic evaluation framework for the German public sector, examining three rarely considered governance dimensions: energy consumption, provider transparency, and knowledge of German-party positions. Our results reveal significant trade-offs, with no single model excelling across all dimensions: estimated energy consumption varies more than 60-fold and is not explained by model size alone, information disclosure varies systematically across providers, and European models do not exhibit stronger knowledge of German party positions. Model selection for public institutions thus cannot rely on performance rankings alone. Instead, evaluations should also reflect the governance requirements of the deployment context.
Read the full abstract

All authors Camilla Dalerci, Thilo Michael, Robin Schaefer, Daniel Weinland

Distributed Computing

Bounded-State Restoration: Decoupling Local Restore Capacity from External LLM State

Hierarchical KV-cache systems can retain long-context LLM execution state beyond GPU memory, but retention capacity does not determine the local memory required to make that state executable again. We isolate this second resource as the restoration working set (RWS): the peak local staging state whose lifetimes overlap during restoration. In the pinned upstream LMCache whole-plan path, measured full-reuse points for 1.956, 7.823, and 15.646 GiB/rank states first succeed at 2, 8, and 16 GiB L1 rungs, with successful L1 peaks of 1.956, 7.824, and 15.648 GiB/rank. We introduce Bounded-State Restoration (BSR), which separates complete discovery from local residency. BSR probes the complete reusable prefix without materializing the whole hit in L1, then installs confirmed state through a reusable window of at most $W$ chunks. Under bounded auxiliary state, peak restoration capacity is $O(W)$ while total transfer and installation work remains $\Theta(|S|)$. Because reusable state spans heterogeneous allocator groups and tensor-parallel ranks, BSR uses a request-level commit rule: partial installation is never exposed as a valid reusable prefix; failures invalidate the advertised prefix and fall back to a lower valid tier or deterministic recomputation. On DeepSeek-V4-Flash with TP=2 across two DGX Spark nodes, a clean no-resume sweep grows external state from 1.956 to 31.277 GiB/rank while measured L1 RWS remains exactly 500.75 MiB/rank at $W=32$, a 63.959x largest-state external-to-live-staging ratio. A second fresh 524K-token run repeats the largest-state acceptance result. Evaluated tier and rank-asymmetric failures expose either complete reuse or zero external reuse before fallback. A matched SSD optimization reduces 512K restore TTFT from 43.1 to 17.6 seconds without changing RWS.
Read the full abstract

Software Engineering

Reshaping the SDLC for Data- and AI-Centric Systems

The traditional Software Development Lifecycle (SDLC) assumes that system behavior is determined primarily by source code, allowing correctness to be specified, implemented, and verified through code-centric practices. Data-intensive and AI-enabled systems challenge this assumption because their behavior emerges from the interaction of code, data, and learned models, while performance may degrade as real-world conditions drift from training data. This paper examines how integrating data engineering and software engineering practices, operationalized through DataOps, MLOps, and LLMOps, reshapes the SDLC for these systems. We make four contributions. First, we synthesize literature across software engineering, data management, machine learning systems, and human-centered computing into a phase-structured account of lifecycle transformation spanning requirements, architecture, development, testing, deployment, monitoring, governance, and organization. Second, we provide a lightweight formalization in which system behavior is defined over code, data, and model configurations; requirements become evaluation-led specifications with probabilistic acceptance regions; and promotion is controlled through statistically grounded validation gates. Third, we develop an adaptive five-layer lifecycle framework comprising artifact, contract, gate, control, and governance layers, positioning maintenance as a closed-loop control problem under configuration drift. Fourth, we propose a conceptual research model linking data engineering integration to measurable lifecycle outcomes and critically assess the evidence base. While the direction of transformation is increasingly established, its magnitude remains insufficiently quantified. We conclude with a research agenda for an empirically grounded, adaptive SDLC for data- and AI-centric systems.
Read the full abstract

Machine Learning

MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure

Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series feature windows, gathered across 153 simulator rides from 51 participants under No, Low, and High TP scenarios. Across each sequence, we capture 64 distinct attributes covering vehicle motion, rider control actions, spatial proximity, and rule compliance indicators. Using this dataset, we introduce MotoSafety, a new edge-AI framework built on the Learned Temporal Importance (LTI) concept. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems.
Read the full abstract

All authors Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil, Subasish Das

Machine Learning · Cross-listed from physics.soc-ph

Spatially explicit feature importance for building height estimation using research-access high-resolution SAR and optical sensors

Accurate building height information at the individual footprint scale is essential for material stock accounting and post-disaster damage assessments yet remains difficult to obtain at city scale in the Global South where airborne LiDAR coverage is rare and commercial very high-resolution imagery is cost-prohibitive or unavailable. While recent works have demonstrated building height estimation using freely available Sentinel imagery, the resolution ceiling of resulting products is still coarse for material stock analysis. This study incorporates products derived from data freely accessible under scientific research licenses, TerraSAR-X StripMap and PlanetScope, alongside Sentinel-1 to predict building heights in a large city in Brazil. To account for the spatial autocorrelation in the training set, features from all sources are integrated in a geographically weighted random forest model, returning an RMSE of 5.34 m and R2 of 0.756 against a LiDAR reference dataset. Local feature importance showed predictor dominance to vary consistently across intra-urban contexts, with footprint geometry dominating for low-rise buildings, shadow-derived height for taller and more isolated structures, and spectral reflectance for the tallest buildings in the set. Sentinel-1 backscatter and InSAR occupy complementary spatial niches, with no single sensor uniformly preferable across the set. Results provide optioneering guidance and insight over satellite-derived products predictive relevance in distinct contexts, which global machine learning or neural network models cannot offer.
Read the full abstract

Robotics

Effector-Centric NMPC of Tiltable-Multirotors for Offset-Free Omnidirectional Aerial Manipulation

Aerial manipulation extends robotic operations to previously inaccessible aerial environments. Unlike arm-equipped aerial systems, tiltable-multirotors can directly generate six-degree-of-freedom wrenches through their flight bases, enabling both efficient movement and omnidirectional operation by tilting the thrust direction. This work presents a design analysis and a wrench-based control framework for tiltable-multirotors in aerial manipulation. We show that a four-rotor tiltable configuration provides a balance between interference-free propeller sizing and hovering efficiency across different attitudes, and its null-space redundancy is crucial for traversing singular configurations under physical constraints. We further show that an upward end-effector placement yields a favorable trade-off between geometric clearance and available wrench. To address disturbances, we propose a dual strategy consisting of a modified integral term for model error and an acceleration-based estimator for external wrenches. Building on these insights, we develop an effector-centric nonlinear model predictive control (NMPC) framework that integrates design choices, singularity handling, and disturbance compensation into a unified formulation. The proposed framework runs fully onboard at 100 Hz on a custom-built tiltable-quadrotor. Real-world experiments, including a 90-deg step cartwheel rotation, whiteboard pushing, and continuous 360-deg valve turning, demonstrate the feasibility of wrench-based omnidirectional manipulation with singularity traversal on a one-DoF-per-arm tiltable-quadrotor.
Read the full abstract

All authors Jinjie Li, Yicheng Chen, Johannes Kübel, Haokun Liu, Junichiro Sugihara, Moju Zhao

Computational Complexity

Integer Quadratic Programming is W[1]-Hard Parameterized by the Number of Variables

We show that Integer Quadratic Programming is W[1]-hard parameterized by the number of variables. Thus, under standard complexity assumptions, Integer Quadratic Programming cannot be solved in f(n)|I|^{O(1)} time for any computable function f where |I| is the size of the encoding and n is the number of variables.
Read the full abstract

Multimedia

On computational approaches to Pop music culture

This overview article presents arguments why the computational study of Pop music culture needs to be conducted in a multi-modal way beyond mere audio analysis, gives a survey of already published quantitative work on analyzing Pop music at scale, and discusses challenges and promising research avenues for future work. We argue that Pop music culture is a rich tapestry of audio, visual, textual and cultural connotations and relations which needs to be studied in an integrative way as a multi-modal socio-cultural phenomenon. What is needed is an approach which is reminiscent of "distant reading", i.e. algorithmic analysis of thousands of books as a research tool in digital humanities. In addition to listening to audio, algorithms need to view album artwork and music videos, to read meta-information, lyrics, music magazines and books. Our review of already available work on distant reading/listening/viewing and multi-modal combinations thereof reveals two major open issues: a scarcity of truly multi-modal approaches and questionable external validity rooted in sampling practices when building music corpora. In trying to overcome these shortcomings we sketch three exemplary avenues for future research on Pop music culture: charting the topic universe of music lyrics, providing an iconography of album cover art, tracking retro cycles in music's timeline.
Read the full abstract

Computation and Language

Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses

The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive constructs. Challenging this assumption, we investigate whether the latent factors governing LLM performance carry the same substantive, human-interpretable meaning as the cognitive constructs governing human learners. Using responses from humans and six LLMs across quantitative reasoning and chemistry assessments, we conducted Exploratory Factor Analysis (EFA) separately for both groups. Subject-Matter Experts (SMEs) then blindly evaluated the resulting factor graphs to ascribe pedagogical meaning to the emerged constructs. SMEs successfully interpreted most of the human-derived factors. Conversely, they could not ascribe meaning to any LLM-derived factors in quantitative reasoning and interpreted only half of the LLM factors in chemistry. By combining data-driven EFA with blind expert interpretation, this framework shows that LLMs frequently operate on statistically opaque mechanisms distinct from human reasoning.
Read the full abstract

All authors Alona Strugatski, Licol Zeinfeld, Jason Cooper, Shelley Rap, Gil Schwarts, Giora Alexandron

Computation and Language

Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It

Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of this weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from what we call task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief. We provide evidence where chains of thought that explicitly fact-check show lower accuracy on false information than those that do not, and a single instruction can reverse the failure across verb families. Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods. Our findings clarify prior results and show how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs.
Read the full abstract

Neural and Evolutionary Computing · Cross-listed from physics.atom-ph

Optically Writable Atomic Vapor Memory as a Substrate for Optical Reservoir Computing

We present an optical random access memory (ORAM) based on warm cesium (Cs) atomic vapor and demonstrate its operation as the physical substrate of a reservoir computer. Information is stored in the hyperfine population distribution of a Cs ensemble via optical pumping and retrieved through differential probe absorption. Spatial multiplexing via acousto-optic deflection provides eight addressable memory rails able to store up to 3.8 bits of information per rail. Employing this platform as a temporally multiplexed reservoir, we achieve a kernel rank ($\mathrm{KR}= 8.8 \pm 0.4$), and a minimum bit error rate of $0.02 \pm 0.01$ on the Exclusive-or (XOR) benchmark. We find the limited memory lifetime constrains the achievable temporal depth, encouraging further research into fast addressable memories. This constitutes the first demonstration of a free-space, optically writable atomic RAM as a substrate in an optical reservoir computing system.
Read the full abstract

All authors Elizabeth Robertson, Mingwei Yang, Lina Jaurigue, Guillermo Gallego, Kathy Lüdge, Janik Wolters

Machine Learning

An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning

Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probes that miss endpoint changes, and a rubric reward that selects broad-topic answering with low semantic leakage under held-out evaluation.
Read the full abstract

Computer Vision

Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation

Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures.
Read the full abstract

Machine Learning

Fourth-Moment Geometry of Rademacher Sums

Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below. For the normalized Rademacher sum, we determine how its higher moments depend on the fourth-order mass. Combining a sharp fixed-q moment envelope with a separate argument below the convexity threshold gives the Gaussian stability inequality for the full range $p\geq4$ of this linear-in-q bound. The same fourth-order framework determines the sharp finite dimensional $L_p/L_4$ Khintchine constant for $p\geq5$, with the flat coefficient vector as the extremizer. These results settle the conjectures of Jakimiuk and of Barański, Murawski, Nayar, and Oleszkiewicz stated below. We also prove Jakimiuk's conjectured quadratic stability estimate at $p=3$. The resulting bounds retain information about sparsity and effective dimension, with applications to Rademacher random projections and randomly signed errors; those applications are not developed further here. Their Laplace-transform form also gives coefficient-sensitive tail bounds. The proofs are discovered with substantial assistance from ChatGPT 5.6 Sol.
Read the full abstract

Artificial Intelligence

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce StartupBench, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks.
Read the full abstract

All authors Liya Zhu, Xin Ma, Tao Liu, Haodong Wang, Ge Zhang, Jingzhe Ding, Qingshui Gu, Yongjie Zhong, Jinxiang Meng, Yuan Gao, Yunqiu Zhou, Hao Zhu, Jifeng He, Yongzhi Liao, Xinyi Zhang, Chaoxin Li, Yi Zhu, Xi Lin, Duju Zeng, Xiang Gao, Wen Zhang, Yunyang Wang, Duo Wang, Huan Zhou, Zuo Wang, Jin Chen, Kaiyuan Zhang, Chuqian Yu, Tianhao Yu, Longxiang Liu, Jianbo Xue, Huimin Che, Jiahao Wang, Yujia Qin, Jiaheng Liu, Shen Yan, Xiaolong Chang, Wenhao Huang

Computer Vision

Training with synthetic data for drone detection in thermal imagery

Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal contrast, and the scarcity of annotated data. This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data. We show that synthetic data provides an effective basis for learning initial object representations, while real in-domain thermal imagery is still essential for reliable deployment. Even small amounts of real IR data substantially reduce domain gaps. Our experiments indicate that dataset alignment has a stronger impact on performance than model scale. Finally, our analysis of the dataset suggests that semantic alignment in feature space is the strongest predictor of model performance, while radiometric properties such as entropy and dynamic range also contribute to detection robustness. This work provides a foundation for combining synthetic and real IR data for effective G2A drone detection.
Read the full abstract

All authors Tanel Liiv, Sander Soodla, Nzamba Bignoumba, Alma M. Liezenga, Toomas Pruuden

Cryptography and Security

Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models

Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness against adaptive adversaries. Detectors trained on hand-crafted attacks with fixed scaling multipliers degrade catastrophically (F1-score drops of about 47 percent to 100 percent, depending on scenario) when confronted with realistic, distribution-preserving samples. We propose Diff-DDoS, a three-phase framework for realistic attack synthesis and robust detection using tabular diffusion models. Phase 1 trains a baseline CNN cell-level detector on spatiotemporal grids from call detail records (CDRs). Phase 2 trains a tabular denoising diffusion probabilistic model (TabDDPM) on normal CDR aggregates to generate realistic attacks and expose detector vulnerabilities. Phase 3 introduces adversarial diffusion training (ADT), using inverse classifier guidance to generate hard yet distribution-preserving samples until the detector converges. On a Milano CDR dataset across SMS-flooding, silent-call, Internet-signaling, and blended scenarios, ResNet50 with ADT recovers F1-scores of 79.62 percent (silent-call), 100 percent (Internet), and 92.79 percent (blended). After validation-based threshold calibration, ADT reaches 100 percent SMS F1 versus 47.3 percent for CTGAN, and matches the strongest gradient-based adversarial-training baseline on silent-call. These results support tabular diffusion models for stress-testing and hardening intrusion detectors in data-scarce 5G cyber-physical deployments.
Read the full abstract

All authors Bilal Hussain, Xiao Tang, Qinghe Du, Tan Li, Muhammad Azhar, Danista Khan

Computation and Language

TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification

Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled candidate SQLs and assigning correctness scores to unseen queries, yet they still provide limited visibility into the signals behind each verification. To address this limitation, we propose TraceSQL, a lightweight and traceable verification model built on explicit diagnostic features. TraceSQL combines 67 features capturing question ambiguity, question requirements, question-schema-SQL consistency, SQL structure, and intent alignment. These signals remain available for examining which factors influence each prediction and for tracing decisions back to diagnostic evidence. On BIRD development databases, TraceSQL achieves 66.47% F1 and 64.48% ROC-AUC, compared with 61.87% F1 and 58.26% ROC-AUC for the GradeSQL-7B ORM baseline on the same generated-SQL evaluation. Feature attribution further shows that the model relies on both semantic grounding and deterministic SQL-structure signals. These results show that SQL verification can be performed with a lightweight learned model while retaining feature-level evidence for inspecting and diagnosing its predictions.
Read the full abstract

All authors Neelesh Kumar Shukla, Debasmita Panda, Srutanik Bhaduri, Aditya Banerjee, Vasu Rangarajan, Viji Krishnamurthy