Computer Vision
Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images
Tiffanie Godelaine, Manon Dausort, Karim El Khoury et al. (+3 more)
Automating the analysis of whole-slide images (WSIs), a key step in cancer diagnosis, has high clinical value, as it can reduce pathologist's workload while improving diagnosis accuracy. Recently,
vision-
language models have shown promising performance for patch-level classification without requiring any annotation, yet these zero-shot (ZS) predictions remain noisy on fine-grained tasks and must be further refined. A promising direction is to refine all predictions jointly, i.e., a transductive approach. However, most existing methods are not tailored to WSIs. We thus propose SlideTIM, an adaptation to WSIs of the recent transductive approach LC-TIM, which introduces a combined spatial–latent regularizer together with a prior on the patch class distribution. The former enforces spatially and semantically close patches to receive the same predictions, while the prior calibrates the predicted class proportions. Together, they address the complex spatial organization and the strong class imbalance of WSIs. Evaluated on four histology
datasets, SlideTIM consistently outperforms all TIM variants, improving the macro-F1 by +8.1pp over the best competing baseline at 1 shot. Compared to the ZS, it raises the macro-F1 by +19.4pp at 1 shot. The code will be made available after submission.
Read the full abstract ▾
All authors Tiffanie Godelaine, Manon Dausort, Karim El Khoury, Benoît Gérin, Benoît Macq, Christophe De Vleeschouwer
Cryptography and Security
MetaPermit: Scalable and Auditable Access Control for AI Agents via LLM-Inferred Meta-Attributes
Hanzhang Ma, Ali Hariri, Tianxiang Shen et al. (+9 more)
The rise of autonomous AI
agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to
adversarial manipulation through Indirect
Prompt Injection (IPI) attacks. In practice, deployed
agent systems such as OpenAI Codex and Claude Code protect tool invocations through a combination of coarse-grained permission rules and LLM-based judgments about individual proposed actions. Both components, however, have important limitations: static policies must anticipate possible user intents and therefore do not scale to open-ended tasks, while LLM-driven authorization supports dynamic decisions but produces inconsistent outcomes and remains vulnerable to targeted IPI attacks. To provide scalable and more consistent authorization, we propose MetaPermit, a policy-based tool access-control framework that decouples semantic inference from security enforcement. By analyzing
agent-user interactions, we derive a compact, task-independent set of meta-attributes that capture the relationships among the user's intent, the execution context, and the proposed tool call. These meta-attributes allow MetaPermit to authorize tool use without enumerating user intents. At runtime, an LLM infers the meta-attribute values for each proposed tool call, while a fixed policy evaluates these values to allow or deny the call, making each decision auditable through the inferred values and the applied policy rule. We evaluate MetaPermit on the AgentDojo and AgentDyn
benchmarks, across seven task suites and five attack methods, using two widely deployed open-weight LLMs. The results show that MetaPermit produces 31% more consistent authorization decisions than LLM-driven authorization and outperforms the state-of-the-art defenses CaMeL and IPIGuard in both task completion, with improvements of up to 109%, and robustness to IPI attacks, with no malicious tool calls executed.
Read the full abstract ▾
All authors Hanzhang Ma, Ali Hariri, Tianxiang Shen, Bohua Zou, Qianjun Zheng, Ji Wang, Li Yi, Ning Jia, Yutao Liu, Haibo Chen, Lin Wang, Debayan Roy
Machine Learning
Aurora-X: Built for Extreme Time Series Forecasting
Xingjian Wu, Chenjuan Guo, Xiangfei Qiu et al. (+6 more)
Time series foundation models (TSFMs) enable cross-domain
forecasting, but their development as general-purpose forecasters remains constrained by underexplored training potential and limited architectural versatility. To address these challenges, we introduce Aurora-X, a billion-scale TSFM with a progressive curriculum and a unified architecture. We first use channel-independent pretraining to learn temporal patterns, then introduce cross-variable dependencies, varied context and horizon lengths, and future
covariates if available during midtraining. Variable-resolution post-training further enables an adjustable temporal span per
token at inference. With fixed model weights, this supports longer histories under a fixed
token budget or fewer
tokens for the same history, enabling test-time scaling. With a versatile architecture, Aurora-X supports cross-variable modeling,
covariate conditioning, and parallel decoding of future patches for probabilistic
forecasting. These are supported by a novel pattern-guided mixture-of-experts that expands model capacity through sparse activation and uses shallow patch similarities to constrain deep-layer routing, guiding expert specialization across heterogeneous time series. Furthermore, we propose an implicit
quantile network head that predicts arbitrary
quantiles to characterize predictive distributions, enhancing probabilistic
forecasting flexibility. Comprehensive experiments on GIFT-Eval, TIME, FEV-Bench, TFB, and DAG-Bench demonstrate state-of-the-art
forecasting performance against pretrained TSFMs and task-specific supervised models.
Read the full abstract ▾
All authors Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
Fluid Dynamics
Goal-Oriented Weighting of Reynolds-Stress Data for Learning Turbulence Models in Complex Flows
Zhuolin Zhao, Haochen Wang, Youngwoo Kim et al. (+2 more)
Data-driven
turbulence models for the Reynolds-averaged Navier-Stokes (RANS) equations offer a promising route to improving predictions of complex flows. Such models, specifically the
turbulence constitutive relations, can be learned efficiently from high-fidelity Reynolds-stress data without evaluating the RANS equations during training. However, conventional losses weight all tensor-component and spatial errors equally, although their influence on a quantity of interest (QoI) can differ significantly; reducing the aggregate stress error therefore does not necessarily lead to an improved QoI prediction. Training against flow-level observations accounts for this dependence but requires repeated, potentially expensive RANS solutions. In canonical shear flows, physical
reasoning can identify the shear component as the only one relevant for the mean-flow prediction. Motivated by this example, we propose a goal-oriented method to select and weight Reynolds-stress training data for complex flows. For a specified QoI, a single offline adjoint evaluation quantifies its sensitivity to local perturbations of each Reynolds-stress component. These sensitivities are converted into fixed weights in the supervised loss, enabling training without further RANS solutions. We validate the weighting in square-duct and periodic-hill flows, then apply it to a film-cooling jet in crossflow, where it improves velocity and cooling-effectiveness predictions over uniformly weighted training despite using a velocity-only QoI. Beyond
turbulence modelling, this work suggests a broader strategy for aligning supervised learning with downstream prediction goals while preserving training efficiency.
Read the full abstract ▾
All authors Zhuolin Zhao, Haochen Wang, Youngwoo Kim, Solkeun Jee, Heng Xiao
Analysis of PDEs
Bio-inspired control model for snake locomotion based on Cosserat beam theory
Eliot Thys, Frédéric Boyer, Yacine Chitour et al. (+4 more)
This paper revisits from a mathematical perspective the modeling of locomotion in snake-like bodies in fluid environement as given in \cite{boyer2010poincare} and \cite{boyer2011macrocontinuous}. Using a Cosserat rod theory, we derive several systems of PDEs depending on the type of constraint and actuation.
Read the full abstract ▾
All authors Eliot Thys, Frédéric Boyer, Yacine Chitour, Petri Kokkonen, Vincent Lebastard, Swann Marx, Clément Moreau
Robotics
Compact Force Sensor for Dual-UAV Cable-Suspended Payload Transport with Tension-Aware Outer-Loop Control
Andrea Delbene, Giorgio Cannata, Giorgio Carlini et al. (+2 more)
Cooperative payload transportation using multiple Unmanned Aerial Vehicles (
UAVs) poses challenges in stability, coordination, and robustness, especially under external disturbances and unmodeled dynamics. This work proposes a dual-
UAV payload transportation framework supported by a compact, custom-designed force sensor measuring the interaction force at the
UAV cable anchor point. The sensor design and mathematical model are presented, and its performance is characterized through static and dynamic tests evaluating linearity, hysteresis, repeatability, and crossload. The control architecture follows a cascade structure: fast inner loops handle vehicle stabilization, while outer loops are designed to compensate for the measured forces. The approach is validated through simulations and indoor experiments under position uncertainty. Payload-drop and constrained-space tests assess the proposed sensing and control architecture against literature-based distributed references, showing improved stabilization, coordination, and disturbance rejection. A
video of the experiments is available at: https://youtu.be/rIw9-fvV8Qw.
Read the full abstract ▾
All authors Andrea Delbene, Giorgio Cannata, Giorgio Carlini, Filippo Sante, Marco Baglietto
General Topology
Whitney Properties and Whitney reversible properties of Cut and Non-Cut Points
Eiichi Matsuhashi
In this paper, we study several properties concerning cut points and non-cut points. First, we show that the property of being a continuum consisting entirely of shore points is preserved under refinable maps. Next, we show that having a block point, having a non-shore point, and having a strong center point are not Whitney-reversible properties. Consequently, \cite[Question 2.9]{nonweak} has a negative answer. Furthermore, we show that none of the classes of continua witnessing the failure of the sequential strong Whitney-reversible property for these three properties admits a common model. Finally, in connection with the fact that colocal connectedness is not a Whitney-reversible property, we show that the class of nonaposyndetic continua having a cut point and such that every positive Whitney level is colocally connected has no common model.
Read the full abstract ▾
Machine Learning
Robust Graph Clustering Network for Multiple Missing Data
Keyuan Qiu, Renda Han, Zhen Tang et al. (+6 more)
Clustering on graphs where both node attributes and structural links are partially missing remains a challenging task. Existing methods typically rely on imputation-then-clustering on single-view missingness incomplete graphs, which are vulnerable to cross-view error propagation and cluster-boundary blurring under simultaneous attribute and structure missingness. To address these limitations, we propose a Robust Graph Clustering Network for Multiple Missing Data (RGCN), which is designed to handle simultaneous node attribute and graph structure incompleteness. RGCN introduces three key innovations: First, we design a view-decoupled dual-branch imputation to mitigate interference and enable mutual enhancement in recovering missing data. Second, we employ a multi-hyperspherical mixture prior to enhance intra-cluster compactness and inter-cluster separability on a directional latent
manifold. Third, a boundary-aware contrastive enhancement objective mitigates the blurring of clusters caused by imputation bias. Extensive experiments on real-world
datasets demonstrate that RGCN consistently outperforms state-of-the-art baselines under various missing patterns.
Read the full abstract ▾
All authors Keyuan Qiu, Renda Han, Zhen Tang, Qiang He, Xingwei Wang, Wenxin Zhang, Guangzhen Yao, Junxin Chen, Qingjian Ni
Multimedia
TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks
Tianmeng Fang, Jiancheng Wang, Chen Wang et al. (+4 more)
Existing text-to-
video (T2V) jailbreak methods mainly seek more effective or stealthier attack candidates. In guarded T2V systems, however,
video generation and security evaluation are costly, so an attacker often cannot test a large candidate pool. We therefore formulate T2V jailbreak as a query-constrained candidate allocation and ranking problem and propose TempQ-Jail. The method combines heterogeneous attack mechanisms to expand candidate coverage, estimates each candidate's end-to-end attack value from security-gate passage, dangerous visual generation, preservation of the original intent, and temporal validity, and ranks candidates so that high-value attacks appear early in a limited query trajectory. We evaluate TempQ-Jail on CogVideoX-5B using 70 common viable intents derived from T2VSafetyBench and compare it with six representative T2V jailbreak methods under a unified protocol. TempQ-Jail achieves TP-ASR@5 and TP-ASR@10 of 48.9% and 65.4%, improving over the strongest baselines by 4.6 and 4.0 percentage points, respectively. It also obtains the highest AUC-TP (0.469) and the lowest AvgQ (6.3). Analyses of query trajectories, candidate allocation, failure attribution, and ablations show that TempQ-Jail more effectively identifies and prioritises candidates with complete attack potential under limited query budgets.
Read the full abstract ▾
All authors Tianmeng Fang, Jiancheng Wang, Chen Wang, Liming Wang, Wei Wang, Jiayang Liu, Xiaochun Cao
Machine Learning
Metacognitive Selective Ensemble for Mobile Systems
Sungmin Lee, Kichang Lee, Joonhee Lee et al. (+3 more)
Deep ensembles improve robustness in mobile sensing, but repeatedly executing many models over continuous sensor streams is costly. Selecting only a few members reduces this cost, yet adaptive selection often requires additional model execution to obtain reliable evidence about inactive candidates. We present MetaSE, an active ensemble framework that exploits short-term persistence in per-model reliability. MetaSE maintains a small active set across windows, uses post-execution evidence to reject unreliable members, and invokes lightweight routing only when replacement is needed. This stateful design accesses the diversity of a larger pool without repeated full-pool evaluation. Across four HAR
datasets and four model architectures, MetaSE consistently improves over a fixed three-model ensemble and achieves accuracy comparable to substantially more expensive adaptive and full-ensemble inference. On a Raspberry Pi 4B, MetaSE is 2.7x faster and uses 69% less
memory than full ten-model inference.
Read the full abstract ▾
All authors Sungmin Lee, Kichang Lee, Joonhee Lee, JaeYeon Park, Songkuk Kim, JeongGil Ko
Algebraic Topology
A derived Chouinard's theorem for infinite groups
Natàlia Castellana and Juan Omar Gómez
We establish a Chouinard-type
theorem for modules over
algebras of cochains on the classifying spaces of a broad class of infinite groups, allowing commutative ring spectra as coefficients. We then use this result to study finiteness properties of the integral
cohomology rings of certain infinite groups, as well as stratification of the corresponding module categories. In particular, we complete the (co)stratification of module categories associated to homotopical groups over fields of positive characteristic.
Read the full abstract ▾
Artificial Intelligence
Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance
Wesley Shu and Hsi-Ching Lin
Reasoning systems usually treat premise use as a question of relevance: if a fact is available and useful, it may be selected for inference. Authorization imposes a different constraint: a premise may be represented and logically usable but not permitted for a particular local transition. We formalize this distinction as Governed Deduction (GD), with a transition-local admission predicate admit(p, tau, S). From an independently produced RBAC-augmented Spider
benchmark, we construct 4,461 matched authorization pairs in which the same query premise and policy state support permitted and denied consuming transitions. An initial joint controller reaches 99.19% held-out accuracy, but a transition-only control reaches 100%, exposing a role-name shortcut. After a frozen, label-independent context-local role permutation removes that shortcut, premise/state-only, transition-only, and joint linear controllers all score exactly 50% on 1,856 held-out edges, while a symbolic policy oracle remains at 100%. The result is a controlled negative finding: the
benchmark instantiates policy-grounded authorization beyond relevance, but the frozen linear representation does not recover the relation. Matched one-sided controls and leakage audits are therefore essential for evaluating learned policy-sensitive
reasoning.
Read the full abstract ▾
Computer Vision
Refining Cytology Predictions with Conditional Random Fields
Manon Dausort, Tiffanie Godelaine, Karim El Khoury et al. (+3 more)
Vision-
language models (VLMs) achieve strong zero-shot (ZS) classification on histology images but do not perform as well on cytology, whose stains and
cell morphology differ markedly compared to histology. Conditional random fields (CRFs) can refine noisy VLM predictions by propagating information across patches, but existing CRF frameworks were designed for histopathology and do not transfer to cytology
datasets, released as independent patch pools spanning multiple staining protocols. We introduce CytoCRF, which adapts the pairwise terms to cytology by targeting chromatin and cytology-specific staining, and further enrich the neighborhood of each potential term by combining multiple backbones. Across ten cytology
datasets, CytoCRF outperforms existing CRF frameworks at every annotation budget, reaching +13.6 percentage points over the best baseline and +33.7 over ZS with only 50 annotations. Combining information from multiple backbones brings further gains, showing that the neighborhood
topology matters more than the pairwise potential computed over it.
Read the full abstract ▾
All authors Manon Dausort, Tiffanie Godelaine, Karim El Khoury, Maxime Zanella, Christophe De Vleeschouwer, Benoît Macq
Quantum Physics
When Can Quantum Extreme Learning Machines Replace Quantum Reservoirs?
Markus Baumann, Gerhard Stenzel, Jonas Stein et al. (+1 more)
Quantum reservoir computers (QRCs) retain information from earlier inputs, whereas reset-window
quantum extreme learning machines (QELMs) start afresh and receive only a recent input window. We establish when this window can replace the reservoir's
memory. Under our stated assumptions and with exact expectation values, sufficiently expressive QELMs can reproduce reservoir outputs arbitrarily accurately as their windows grow precisely when the influence of the omitted past becomes uniformly negligible. However, longer windows do not always solve the problem. We construct a simple two-
qubit reservoir that performs temporal recall exactly, while every fixed-window predictor faces the same positive worst-case error over unbounded delays, regardless of model capacity. Analytical
benchmarks and simulations distinguish missing history from limited features and finite measurements. The central conclusion is simple: better representations can improve how available information is used, but cannot recover a past the model never receives.
Read the full abstract ▾
All authors Markus Baumann, Gerhard Stenzel, Jonas Stein, Claudia Linnhoff-Popien
Combinatorics
Positivity Rigidity for Grossman-Larson Characters and the Kingman Face of the Hoffman Rooted-Tree Graph
Shengjun Zhang
We classify the real characters of the Grossman-Larson
Hopf algebra that are nonnegative on the rooted-tree basis. They vanish on trees with branching away from the root, and the normalized characters are parametrized by Kingman paintboxes. Two-sided Pieri states are mixtures of the normalized characters, with unique mixing measures. The corresponding laws form a proper exposed Bauer face of the simplex of central measures on the Hoffman rooted-tree graph. For the path-forest subgraph, the full and minimal Martin boundaries coincide and are homeomorphic to the Kingman simplex. The limiting ranked root-branch frequencies generate the completed central tail.
Read the full abstract ▾
Robotics
Precision at Speed: Sample-Efficient Online Model-Based Reinforcement Learning for Hydraulic Excavator Control
Claudio Canales, Fang Nan, Marco Hutter et al. (+1 more)
Precise, high-speed control remains challenging for
robots with complex actuation dynamics. Learning directly on hardware is further constrained by the cost of real-world interaction. We present an online model-based reinforcement learning framework that learns a probabilistic dynamics ensemble model from scratch for sampling-based model predictive control. A precision-gated contouring objective conditions the progress reward on path accuracy, prioritizing precision over speed. In a data-driven excavator simulator, the framework achieves higher sample efficiency than the evaluated model-based reinforcement learning baselines. We validate the framework by learning directly on an 11.5-ton Menzi Muck M445 hydraulic excavator, without demonstrations or simulation pretraining. After 20 minutes of interaction, the controller reaches tracking accuracy comparable to prior learned controllers trained on 100-150 minutes of data. After 40 minutes, it sustains sub-centimeter mean path error at high operating speeds.
Read the full abstract ▾
All authors Claudio Canales, Fang Nan, Marco Hutter, Javier Ruiz-del-Solar
Sound
Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search
Ben Hayes, Haokun Tian and Stefan Lattner
Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often difficult to optimize, while direct search requires rendering every candidate. We introduce Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data. At inference, candidate parameters are scored directly in this learned space, yielding a renderer-free objective whose audio geometry is shaped by parameter correspondences rather than generic audio similarity. We evaluate Synth-JEPA on Surge XT using held-out synthesizer sounds and out-of-domain NSynth and FSD50K targets, against inverse models, direct search, and learned proxy objectives. Synth-JEPA outperforms all baselines in-domain and remains competitive out-of-domain. Its matching quality continues to improve with additional test-time search, allowing compute to be traded for match quality. In pairwise listening tests, listeners preferred Synth-JEPA in 85% of trials overall. Together, these results show that an audio representation with a parameter-induced geometry allows synthesizer sound matching to be approached as an effective renderer-free search problem.
Read the full abstract ▾
Differential Geometry
Non-homogeneous curvature flows in a hemisphere
Hongyi Sheng, Weimin Sheng and Jiazhuo Yang
Let S^{n+1}_{+} be the open hemisphere of the unit sphere S^{n+1} centred at o. We study the non-homogeneous
curvature flow X_t=-f(r) sigma_k^{alpha} {nu} of smooth, closed, strictly convex hypersurfaces enclosing o, where r is the geodesic distance to o. We consider both the supercritical regime beta>1+k {alpha} and the critical regime beta=1+k{alpha}, where beta is the growth order of the profile at the origin, f(r) almost equals r^{beta} as r descends to 0. Under the structural condition that f^{1/(1+k{alpha})} is convex, we prove long-time existence and preservation of strict convexity. The normalized radial function converges smoothly and exponentially to a constant: to 1 and to R_{infty}>0, resp. in different two cases. Thus the normalized radial graphs become round, while the original hypersurfaces contract to o.
Read the full abstract ▾
Statistical Methodology
EARL: Exposure- and Allocation-Reweighted Linear Estimator for Bipartite Experiments with Partial Assignment
Alexey Kurennoy
Bipartite A/B tests are experiments in which treatment is randomised over one set of units, while outcomes are measured on another. For example, an online marketplace may test a new pricing
algorithm on a random subset of items, while the outcome of interest, say, purchase satisfaction, is measured on customers, each of whom interacts with many items. Existing methods for analysing bipartite experiments assume that every randomisation unit is assigned to treatment or control. In practice, often only a subset participates: platforms cap rollout risk, reserve holdout groups, and split their population across concurrent tests. Ignoring the unassigned units biases estimation, while including them requires care. We construct an unbiased linear
estimator for bipartite experiments with partial assignment. Observations must be reweighted not only by the (centred) share of treated connections among participating ones (the exposure) but also by the number of participating connections, each inverse-weighted by its participation propensity, so that units whose connections are well covered carry proportionally more weight. The resulting
estimator, EARL (Exposure- and Allocation-Reweighted Linear), is unbiased, consistent, and asymptotically normal; we devise two asymptotic variance
estimators and show that it has minimal variance in a natural class of linear
estimators. EARL remains unbiased regardless of the experience the unassigned units receive, as long as they contribute to expected outcomes additively; in particular, they can be allocated to other, non-overlapping tests. Our theory is complemented with a simulation study on two public
datasets, in which EARL attains up to six times lower error than the strongest existing baseline and, in some configurations, over an order of magnitude lower than Horvitz-Thompson-style alternatives.
Read the full abstract ▾
Rings and Algebras
Asymptotic completions of preordered semirings
Péter Vrana
The study of preordered semirings is motivated by applications in computer science, graph theory, and information theory, and provides tools for understanding the asymptotic preorder, which compares large powers of a pair of elements. This paper studies sequences which behave approximately as sequences of powers, but are not necessarily equivalent to
geometric sequences. Our main result is that preordered semirings admit completions where such sequences, that we call approximately
geometric, become equivalent to
geometric sequences, and that existing characterizations of the asymptotic preorder extend to the completion. We provide several classes of examples of approximately
geometric sequences in the semiring of tensors, and in the semiring of graphs. As a concrete application, we determine the strong converse exponent for binary hypothesis testing with composite Markov hypotheses.
Read the full abstract ▾
Plasma Physics
Bayesian inference of non-Maxwellian distribution functions from collective Thomson scattering spectra
Kentaro Sakai, ByungJun Kang, Akito Nakano et al. (+1 more)
We investigate
Bayesian inference of non-Maxwellian electron distribution functions from collective Thomson scattering (CTS) spectra. We represent distribution functions using multiple candidate models of different complexity and perform inference on synthetic spectra generated from known non-Maxwellian distribution functions. Our analysis demonstrates that a sufficiently flexible model can approximate the overall shape of the ground-truth distribution function. The most plausible model is identified based on model evidence, a statistical measure representing the probability to obtain the observed data given the model. When the candidates include the ground-truth model, the model evidence favors the ground-truth model. Without the ground-truth model as a candidate, the model evidence favors the candidate model with the fewest parameters that adequately approximates the data. The posterior probability density function of the most plausible model reveals the characteristic features and associated uncertainties of the underlying distribution function. The origin of the additional spectral peaks is attributed to a combination of modifications to the dispersion relation and reduced Landau damping. This enables the objective and data-driven identification of distribution functions directly from observed CTS spectra.
Read the full abstract ▾
All authors Kentaro Sakai, ByungJun Kang, Akito Nakano, Takeo Hoshi
Statistical Computation
Group recovery after trimming, and level-free flagging, in robust clusterwise regression
Samir Orujov
Trimming methods for robust clusterwise regression discard a fixed fraction of the data. Too low a level breaks the fit; too generous a level can trim away a small group. We first propose a group-recovery step that can follow any trimming or flagging method: it searches the discarded units for a line, tests whether those near it form a peak rather than a band, and restores the line as a group when the likelihood of Gaussian groups plus uniform noise improves by a margin like that of the
Bayesian information criterion. In simulations it repaired the failures of a generous TCLUST-REG level with unequal groups, but not with three or four groups. The second proposal, ESF (exact-subsample flagging), is a flagging procedure without a trimming level: it solves the clusterwise least-squares problem exactly on small subsamples, flags units far from the best fit, and draws later subsamples from the rest. Two constants stand in for the level: a subsample size, set from a lower bound on the smallest group proportion, and a cap on the flagged set. It is meant for data about whose contamination nothing is known: TCLUST-REG at the fixed level 0.30, followed by reweighting and the recovery step, was as accurate as ESF on average up to a fifth of outliers, and higher levels were more accurate beyond. The flagged fraction estimates the contamination only when the errors are close to Gaussian. On taxi fares with known tariffs, ESF found both in every sample.
Read the full abstract ▾
Distributed Computing
Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics
Minghui Liwang, Chenxi Xu, Wei Gong et al. (+5 more)
Model-parallel inference over dynamic edge systems requires scheduling decisions that account for not only instantaneous resources but also future resource contention and reliable service commitments. Existing edge-inference designs, however, predominantly optimize performance metrics based on current or short-term system states, without explicitly coupling current assignments with future commitment fulfillment. To address this issue, we propose PROMISE, a predictive rolling-horizon framework for commitment-aware model-parallel inference under spatio-temporal edge dynamics. PROMISE jointly models
stochastic task generation, mobility-induced communication variations,
privacy-aware model partitioning, and load-dependent edge computing capability. We introduce committed completion time (CCT) as an endogenous service decision and formulate joint SD–ES mapping and CCT determination to balance commitment fulfillment and service reward. To address cross-timeslot coupling, PROMISE estimates future task arrivals and computational workloads over an adaptive horizon and embeds them into certainty-equivalent ES-state rollout. A progress-aware surrogate then evaluates feasible current-stage mappings, while the corresponding CCTs are analytically recovered from predicted completion times. Only the first-stage decisions are committed, and the optimization is repeated with newly observed states in a receding-horizon manner. Numerical experiments demonstrate robust scheduling performance under diverse system scales and workload dynamics, while Raspberry-Pi-based experiments validate the practical feasibility and key system characteristics of model-parallel edge inference.
Read the full abstract ▾
All authors Minghui Liwang, Chenxi Xu, Wei Gong, Li Li, Wenbo Zhu, Xinlei Yi, Yuhan Su, Xianbin Wang
Systems and Control
Resource-Aware Rolling-Horizon Controller for Renewable-Based Virtual Power Plants Providing Automatic Frequency Restoration Reserves
Marco Vinicio Avendaño-Caiza, Juan Diego Rios-Peñaloza, Javier Roldán-Pérez et al. (+2 more)
Virtual power plants (VPPs) are an effective solution for increasing the penetration of renewable energy sources (RES) in power systems. Moreover, VPPs can provide ancillary services if generators and loads are closely connected and properly coordinated. This aspect has been addressed in several studies, yet they mostly focus on the dispatch optimisation level, leaving real-time operation aspects unresolved. To close this gap, a central controller for VPPs based on a rolling-horizon optimisation is proposed in this work. Its main objective is to maximise revenues while delivering frequency restoration services. A day-ahead optimisation firstly defines the power setpoint and the upward and downward reserves of the VPP. Then, the rolling-horizon optimiser, executed every minute, distributes the power and reserve references between the VPP units to achieve their close tracking while taking into account resource availability (wind speed, irradiance, etc.), operational constraints and battery degradation. The effectiveness of the controller is tested using a two-area interconnected power system under different RES generation and demand profiles. The simulations are performed in MATLAB/Simulink and include detailed dynamic models of the VPP elements, demonstrating the applicability of the
algorithm to real systems. The day-ahead and the rolling-horizon optimisation problems are modelled using YALMIP and solved using Gurobi. The obtained results demonstrate the VPP supporting grid frequency restoration by optimally allocating its resources, even under the presence of forecast uncertainty.
Read the full abstract ▾
All authors Marco Vinicio Avendaño-Caiza, Juan Diego Rios-Peñaloza, Javier Roldán-Pérez, José Luis Rodríguez-Amenedo, Milan Prodanovic
Machine Learning
Robust Successor Features
Erik Nikulski, Yamen Habib, Vicenç Gomez et al. (+3 more)
Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the
agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based
benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel.
Read the full abstract ▾
All authors Erik Nikulski, Yamen Habib, Vicenç Gomez, Anders Jonsson, Rubén Moreno-Bote, Javier Segovia-Aguas
Materials Science
Binary magnetism and directional magnon transport in alkali-doped CrI$_3$
Cihan Bacaksiz, Maarten Soenen, Denis Sabani et al. (+2 more)
The recent realization of two-dimensional (2D) magnets, with CrI$_3$ as a pioneering example, has opened new avenues in the fields of 2D materials and magnetism. This breakthrough has been followed by extensive efforts to manipulate and exploit their
magnetic properties. In this work, we investigate the adsorption of alkali-metal atoms as a route to control the
magnetic behavior of monolayer CrI$_3$. We show that, upon adsorption, alkali-metal atoms donate an electron to the CrI$_3$ layer, leading to the formation of inequivalent Cr sites, with one Cr atom exhibiting an enhanced
magnetic moment of $4~\mu_B$, while the other retains its typical $3~\mu_B$ moment. These modifications significantly alter the
magnetic exchange interactions, including the emergence of anisotropic exchange and Dzyaloshinskii–Moriya interactions (DMI). Consequently, the doped systems exhibit non-collinear
magnetic ground states, modified temperature-dependent magnetism, and anisotropic
spin-wave propagation, with a preferred propagation direction that becomes increasingly pronounced with increasing dopant size. Furthermore, an asymmetry between
spin-wave propagation in opposite directions is observed, giving rise to a diode-like effect, particularly for heavier dopants. This behavior is attributed to the enhanced DMI, which breaks the
symmetry of the
magnon dispersion. These results demonstrate that alkali-metal doping provides an effective route to tune anisotropic and nonreciprocal magnonic properties in two-dimensional
magnetic materials.
Read the full abstract ▾
All authors Cihan Bacaksiz, Maarten Soenen, Denis Sabani, Rai Maciel de Menezes, Milorad V. Milosevic
Robotics
Co-design of trajectory and morphology for a vertical jump-climbing robot
Christopher Y. Xu and Elliot W. Hawkes
Animals such as squirrels and even bears have adapted to rapidly climb up trees and other complex vertical terrain, but achieving comparable agility has been a challenge for climbing
robots. Existing
robots often use walking gaits and move conservatively to stay in contact with the surface, which limits the range of dynamic maneuvers. In this paper we present a 290 g
robot that, to our knowledge, is the first to climb vertically by bounding (with an aerial phase). We leverage a co-design workflow, in which the morphology and trajectory are jointly optimized for fast locomotion, subject to adhesion force limitations seen in spined grippers. The resulting trajectory includes a rapid maneuver that launches the
robot vertically, and an aerial reorientation that brings the front grippers back to the surface using the rear leg as an inertial tail. We evaluate the resulting jump forces in 2D force space and demonstrate that the optimized morphology is capable of continuous climbing at a speed of 0.375 m/s (1.97 body lengths/s), and can also achieve ground locomotion and transition to a vertical surface. Our work proposes design insights for the jump-climbing maneuver and serves as an important step toward creating climbing
robots with agility on par with that of animals.
Read the full abstract ▾
Artificial Intelligence
Same Text, Different Numbers: The Divergence of LLM-Based Measures
Hamid Boustanifar and Sasan Mansouri
Researchers increasingly use generative large
language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which LLM-based textual measures are invariant to model choice using thirteen measures, including sentiment, management clarity, uncertainty, answer specificity, and
climate and political risk. Seven LLMs from different providers score earnings call transcripts of S&P 500 companies on these constructs. Cross-model rank correlations average only 0.52, and transcript-level differences common across providers account for only 34% of total score variation. Cross-model disagreement does not predict subsequent analyst or
market disagreement, consistent with a substantial model-specific component rather than common ambiguity in the underlying disclosure. Model choice significantly affects downstream inference, with coefficient magnitudes, signs, and statistical significance varying substantially across models. Averaging across providers makes transcript rankings more stable for most constructs, but score levels remain sensitive to the models included in the ensemble. LLM-generated variables should therefore be treated as model-contingent measurements and validated across providers.
Read the full abstract ▾
Cryptography and Security
Breaking the Black Box: Byte-Level Boundary Inference of Real-World Antivirus Systems
Jieshuai Yang, Zhi Wang, Yan Jia et al. (+6 more)
Existing approaches for understanding the detection logic of real-world antivirus (AV) software infer only binary malware/benign decisions from black-box queries, providing limited insight into the fine-grained decision-critical regions that govern AV detection. In this paper, we present AVHunter, the first framework for inferring byte-level decision-critical regions of real-world AV products under a black-box threat model. AVHunter constructs the first large-scale Byte-Level AV Boundary
Dataset (BABD) by systematically probing 11 real-world AV products, revealing that modern AV detections are largely associated with a small number of compact decision-critical byte regions. Leveraging BABD, AVHunter trains AV-specific models that not only reproduce binary AV decisions, but also localize the decision-critical byte regions underlying these decisions, achieving an average boundary prediction recall of 85.07% while maintaining 97.43% detection agreement with the target AVs. We further validate that the predicted regions capture genuine AV decision knowledge through boundary-guided malware evasion, false-positive induction on benign executables, and a seven-month longitudinal study demonstrating that the inferred regions remain largely stable as AV products evolve. Overall, AVHunter moves beyond conventional binary-label AV modeling by enabling fine-grained boundary-region localization and revealing a new form of AV knowledge leakage with important implications for malware analysis, AV security, and boundary-aware defenses.
Read the full abstract ▾
All authors Jieshuai Yang, Zhi Wang, Yan Jia, Zhenhua Wu, Jianfei Tang, Chenbin Su, Jingwei Ye, Jianwen Tian, Wanpeng Li
Networking
Dynamic Task and Resource Scheduling Towards Space-Air-Ground-Sea Integrated Network
Yufei Ye, Shijian Gao, Xinhu Zheng et al. (+1 more)
In the context of 6G ubiquitous connectivity, the space-air-ground-sea integrated network (SAGSIN) emerges as a new paradigm for pervasive service provisioning. To support expanding maritime activities in infrastructure-scarce ocean areas, we propose an innovative dynamic task and resource scheduling approach for SAGSIN to deliver computing services for vessels. It integrates broad-coverage satellites, relay-capable high-altitude platform (HAP), energy-sufficient coastal base station (BS), and flexibly deployed uncrewed aerial vehicles (
UAVs) to accommodate wide-area, highly mobile, and sustained maritime services. To address the challenge of task scheduling across four layers, a dynamic task offloading
algorithm is developed. It steers task flows toward servers with light loads, strong computing capabilities, and high-rate links based on real-time system states to reduce task execution delay, integrating an anticipatory satellite handover strategy to mitigate post-handover congestion and improving satellite resource utilization. Considering the limited endurance of
UAVs, we impose residual energy constraints to ensure task backlog handover and safe return. Furthermore, the
UAV-BS bandwidth allocation,
UAV trajectories, and computing resource allocation are jointly optimized to enhance the connectivity among low-altitude devices and accelerate task completion. Simulation results validate the proposed method's superior adaptability to system resource variations during task execution in complex maritime environments, achieving at least a 23% reduction in average task delay over
benchmarks.
Read the full abstract ▾
All authors Yufei Ye, Shijian Gao, Xinhu Zheng, Liuqing Yang