Artificial Intelligence
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Monday 17 August
Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures. However, since unstructured terrain lacks explicit difficulty ordering for curriculum design, existing methods resort to heuristic curricula over parameterized terrains. This abstraction limits generalization, as policies can overadapt to near-fixed perceptual patterns. To address this, we propose \textbf{\ourname{}}, an Trajectory-level Automatic Curriculum Learning framework that generates training tasks directly from unstructured terrain maps. At each curriculum update, the evaluator learns a difficulty function for the current policy that maps a given trajectory task to a difficulty score. The sampler then proposes new trajectories guided by the learned evaluator as the curriculum for the next policy update. This forms a closed loop in which the curriculum is iteratively matched to the evolving policy. Quantitative and qualitative experiments show that \ourname{} continuously provides effective curricula on unstructured terrain, improving trajectory success rate by \(56.3\%\) over direct training without curriculum. Compared with handcrafted curriculum learning, our method improves success rate by \(18.5\%\) on the hardest terrain tasks and by up to \(39.74\%\) when evaluating traversal from diverse approach directions on the same obstacle type.
Sound
ACE-Cap: Active Evidence Acquisition via Agentic Co-Evolution for Long-Paragraph Fine-Grained Audio Captioning
Long-paragraph fine-grained audio captioning requires models to recover diverse acoustic facts while avoiding omissions and unsupported details. However, prevailing captioners remain passive one-shot generators: once a detail is overlooked, they cannot identify the evidence gap, query the audio for targeted information, or decide when sufficient evidence has been collected. We formulate this task as active evidence acquisition and introduce Agentic Co-Evolution for Captioning (ACE-Cap). The framework uses multi-turn interaction between a Composer and an Instruct model to form a closed evidence-acquisition loop. A Captioner first produces an initial description. Conditioned on this description and the interaction history, a text-only Composer asks targeted questions about unresolved acoustic attributes, while an audio-conditioned Instruct model provides grounded answers. The Composer then decides when to terminate and synthesizes the accumulated evidence into a final caption. ACE-Cap trains these roles through a unified gold-to-prediction reward derived from fixed, gold-grounded multiple-choice questions and a frozen caption-only judge. For credit assignment in variable-length interactions, LOOP-GRPO replaces the trajectory-wide scalar advantage with span-aligned signals: leave-one-out contributions of individual questions to the accumulated evidence, a quality-cost utility for stopping, and an evidence-preservation utility for final synthesis. Role-wise warm-up followed by alternating Composer and Instruct optimization keeps each update a well-defined single-policy problem while allowing the roles to co-evolve. ACE-Cap thus turns captioning from passive one-shot generation into an adaptive process that learns what evidence to acquire, when to stop, and how to preserve it in a long-paragraph caption.
Read the full abstract
Information Retrieval
Domain-Specific Text Embedding Models for Entity Resolution
General-purpose text embedding models are designed to capture semantic similarity but are not optimised for distinguishing entity records that represent the same real-world business or person. This limitation affects applications such as entity resolution and duplicate record retrieval, where small textual differences may either preserve or change identity. This paper investigates whether domain-specific triplet fine-tuning can adapt pretrained embedding models for identity-sensitive retrieval. A synthetic dataset of business and person records was created with identity-preserving variations and challenging non-matching examples. Two widely used embedding models were evaluated before and after fine-tuning using a margin-based similarity evaluation. The results show substantial improvements in separating true matches from highly similar non-matches, demonstrating that domain-specific triplet training can effectively reshape general-purpose embedding spaces for entity retrieval. These findings suggest that targeted fine-tuning provides a practical approach for improving embedding models in data quality management and information retrieval applications.
Read the full abstract
Cryptography and Security
A Calibrated and Explainable Bimodal Machine Learning Framework for Hybrid Intrusion Detection
Modern communication systems face critical gaps in detecting unknown attacks and rare threat classes due to extreme data imbalance and black-box decision logic. We propose a bimodal framework of calibrated and explainable machine learning (ML) for network security, unifying known-class precision with open-set generalization without the complexity of deep learning. Our framework introduces security-oriented feature extraction to enhance signal-to-noise ratio, hybrid resampling (ADASYN + manual boosting) to reduce class imbalance, isotonic calibration and adaptive thresholding ($\tau=0.30$ for XSS) to recover recall for rare attacks, and SHAP-based explainability to validate domain-aligned decision logic. Evaluated on the CIC-IDS2017 dataset and compared with prior ML models and studies, our framework achieves significant accuracy on known attacks (Macro F1 = 0.8626) and detects unknown classes at 1% FPR with TPR up to 90.17% (DoS slowloris), and 77.04% (Web-XSS). The SHAP analysis confirms decisions are driven by security-relevant features, not model artifacts. Our work bridges the gap between theoretical models and operational IDS by delivering calibrated, explainable, and open-set-capable attack detection and prevention in a single, reproducible framework. Keywords: intrusion detection, cybersecurity and privacy, explainable AI, machine learning
Read the full abstract
Cryptography and Security
Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies
Digital Twins (DTs) are increasingly used to monitor and analyze Cyber Physical Systems (CPS). However, in adversarial environments, the fidelity of a DT cannot be assumed. Communication delays, data manipulation, sensor degradation, or partial information loss may cause the DT state to diverge from the physical process it represents. Such divergence creates temporal inconsistencies that may reveal cyber physical attacks. This paper proposes a detection framework that monitors temporal consistency between the physical system and a potentially degraded DT view. A DT predictor is trained exclusively on normal system behavior to model short-term system dynamics. During operation, discrepancies between predicted and observed states are transformed into multi-horizon temporal features capturing the magnitude, persistence, and evolution of prediction residuals. An unsupervised density model characterizes normal consistency patterns, while a sequential change detection mechanism identifies sustained deviations indicative of attacks. The approach is evaluated on three widely used Industrial Control System (ICS) datasets, SWaT, HAI, and BATADAL, under multiple DT degradation scenarios, including time desynchronization and partial observability loss. Results show that temporal inconsistency patterns enable reliable event-level attack detection with bounded false alarm rates and low detection latency. The proposed method achieves up to 98% detection reliability on SWaT and false alarm rates below 2%. Unlike conventional anomaly detection methods, the proposed framework does not require attack signatures or labeled attack data and remains effective even when the DT view is degraded. These results suggest that DT degradation, often treated as a limitation, can instead serve as a useful signal for cyber physical security monitoring.
Read the full abstract
Machine Learning
A Tree-Structured Approach for Phishing Template and Attacker Attribution Analysis
Phishing remains a persistent and evolving cybersecurity threat, with attack volumes reaching record levels. This growth is driven by the industrialization of phishing through widely available phishing kits and reusable templates, which enable cybercriminals to rapidly generate and deploy large numbers of fraudulent webpages. Although surface-level attributes may differ across these websites, their underlying structures often exhibit significant similarities. However, most existing defenses rely on reactive blocklists or supervised classification models that focus on individual phishing instances, limiting their ability to identify structural reuse and detect coordinated phishing campaigns. To address this limitation, this study investigates whether HTML structure can serve as a robust fingerprint for identifying phishing template reuse. We model webpages as Document Object Model (DOM) trees and extract structural features, optionally enriched with HTML tag-based content information. These representations are then clustered using unsupervised learning methods to group structurally similar webpages. Three clustering algorithms are evaluated and compared, while also analyzing how the depth of the extracted DOM-tree affects cluster formation and overall clustering performance. Finally, cluster quality is also evaluated both quantitatively and qualitatively, including a novel level-wise Jaccard Distance Score and manual inspection supported by visualization tools. Results demonstrate that structural representations of webpages can effectively reveal hidden similarities across phishing sites, enabling the detection of emerging and zero-day templates and supporting the analysis of coordinated phishing threats
Read the full abstract
Distributed Computing
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the full serving stack, including model layout and loading, expert residency, CPU–GPU execution, agentic state reuse, and runtime memory management, around two realities of local AI: agent workloads continuously change their execution pattern, and edge hardware exposes heterogeneous resources whose balance differs from machine to machine. Rather than committing to a fixed offloading strategy, FreeToken continuously maps computation and model state onto the resources actually available. FreeToken supports more than 20 MoE models and real coding and tool-using agents across hardware ranging from an 8GB laptop GPU to a single workstation GPU. More importantly, it changes what these machines can practically serve, from a 35B model on a laptop to a 284B model on a gaming desktop and the 753B GLM-5.2 on a single workstation GPU. FreeToken turns open weights into deployable local software, making the machines users already own a practical platform for frontier-scale intelligence. We release the system at flashml.ai.
Read the full abstract
Artificial Intelligence
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approaches either rely on process evaluators, which incur annotation and inference costs, or derive step-level credit from successful trajectories. However, successful trajectories are extremely scarce during early-stage reinforcement learning, substantially weakening anchor-based methods. We propose Transition-wise Rubric Credit Assignment (TRCA), which derives step-level supervision directly from action-induced transitions without learned evaluators or successful anchors. TRCA evaluates each transition using Evidence, Execution, and Invalidity rubrics to capture task-relevant information acquisition, valid task execution, and invalid or regressive behavior. From these judgments, Foundational Rubric Reward measures local transition quality, while Breakthrough Rubric Reward tracks newly covered Evidence and Execution conditions to reward incremental task progress. Combined with terminal outcomes, these signals produce fine-grained step-level advantages for policy optimization. Experiments on ALFWorld, WebShop, and seven search-augmented question-answering benchmarks show consistent improvements over the evaluated baselines. With Qwen2.5-7B-Instruct, TRCA improves the WebShop score by 6.0%-12.6%; with Qwen2.5-3B-Instruct, it improves the average SearchQA score by 1.9%-18.3%. These results demonstrate the effectiveness of transition-wise rubric credit assignment for long-horizon tasks with sparse successful anchors.
Read the full abstract
Machine Learning
REFLEX: Reflexive Equilibrium Fixed-point Learning for Endogenous eXchanges
In over-the-counter corporate bond markets, dealers compete for client trades by quoting bid and ask prices. Tighter quotes attract more business, but also informed customers more likely to trade ahead of adverse price moves, leaving the dealer holding the risk. As dealers increasingly use machine learning to set quotes, they retrain these models on the trades their own quotes attract, creating a feedback loop in which each model reshapes the market that generates its next training data. The question is therefore not only whether a quoting model performs well, but whether the market it creates stays stable as the model learns from it. Existing performative prediction theory gives a sharp stability condition, yet expresses it through abstract properties of the learning objective a trading desk cannot measure before deployment. We introduce REFLEX, a framework that replaces those unobservable quantities with three measurable features of dealer behavior: how strongly trading volume responds to tighter quotes, how sharply the dealer's objective bends around its optimum, and how quickly informed flow increases as spreads narrow. REFLEX combines these into a single retraining modulus, a pre-deployment stability margin estimated from a desk's own quote and execution history that predicts whether repeated retraining will converge or amplify itself. In simulation, predicted and measured stability agree within 8%, and competing dealers increase instability by 1.74x with two and 3.16x with three, as predicted. Where ordinary retraining becomes unstable at modulus 1.21, a structurally anchored correction converges as blind retraining collapses. Calibrated over 36 years of public market data, stability headroom falls roughly 4.4x for investment grade and 4.3x for high yield from calm to crisis regimes. Ultimately, REFLEX turns an abstract convergence theorem into a market-level safety margin.
Read the full abstract
Computer Vision
KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generation
Identity-preserving video generation (IPVG) requires synthesizing videos that are faithful to both reference subjects and text prompts. Existing methods are often hindered by high tuning costs or limited input-level enhancements, struggling to maintain rigid identity consistency during complex, long-sequence actions. To address these limitations, we propose KeyID, a training-free IPVG framework that decouples the synthesis of video dynamics from the injection of identity. Specifically, KeyID comprises two components: (1) Reference-Aware Video Generation, which produces an identity-agnostic video draft aligned with multiple references, and (2) Identity-Preserved Keyframe Editing, which integrates the target identity via sparse keyframe correction and subsequent motion interpolation. By shifting from dense frame-level supervision to sparse keyframe-level refinement, KeyID effectively resolves the capacity conflict between prompt adherence and identity fidelity. Crucially, our modular design allows seamless extension to multi-subject references and complex sequential action generation without additional training. KeyID outperforms prior works and is validated by automatic and human evaluations on the official challenge benchmark, ultimately securing the runner-up position in the Track 2 (Sequential Action) of the ACM Multimedia 2026 IPVG Grand Challenge. Source code is available at https://github.com/WISLab-GDUT/KeyID.
Read the full abstract
Robotics
Unified Condition-Action Modeling for Accurate One-Step Action Generation
Robot manipulation requires policies that are both accurate and efficient, as robot control must respond to changing observations under tight latency constraints. Recent diffusion and flow policies are promising, but they often treat conditions as auxiliary signals rather than jointly evolving them with action trajectories. We find that this limitation can be effectively mitigated by a simple yet effective unified condition-action modeling design that represents conditions and actions in a shared token space, allowing a compact model to achieve high performance while improving both inference speed and accuracy. Therefore, we propose UCA-Flow, a unified condition-action modeling framework for accurate one-step action generation. Our method unifies observation conditions, timestep conditions, interval conditions, and action tokens into a single sequence, and processes them with a Unified Condition-Action Transformer for joint condition-action representation learning. As a result, condition representations are dynamically reconstructed according to the current generation stage, highlighting information most relevant for action refinement. Furthermore, we introduce an improved dual-pass supervision scheme over $u$ and $v$ for stronger optimization of unified condition-action modeling. UCA-Flow achieves an average success rate of 86.4%, improving over the strongest baseline by 7.5 percentage points, with a task-averaged inference latency of $3.0$ ms. It achieves $43.9\times$ and $32.2\times$ speedups over DP3 and Simple DP3, and remains $4.2\times$ and $2.2\times$ faster than one-step FlowPolicy and MP1, respectively. Project page: https://uca-policy.github.io/UCA.github.io/
Read the full abstract
Numerical Analysis
Asymptotics-guided learning and symbolic regression for dispersive resonances
We study resonance prediction in dispersive media, formulated as nonlinear spectral problems for volume integral operators. The main idea is to use asymptotic analysis not only as a baseline approximation, but also as a guide for constructing predictive correction models. We learn the residual between asymptotic and reference resonances using features suggested by the subwavelength expansion, including the logarithmic scales specific to two dimensions. The resulting corrections substantially improve single-resonator and dimer predictions, and symbolic regression produces compact formulas for the learned residual. The results show that asymptotic analysis can be used not only to approximate resonances, but also to design the feature space in which data-driven corrections become accurate, low-dimensional, and interpretable.
Read the full abstract
Computational Complexity
Convex Networks Remain Hard to Certify: Dimension-Accuracy Barriers for Lipschitz Constants
Input-convex neural networks permit globally tractable minimization over their inputs, so one might expect their global regularity to be tractable in low input dimension. We prove exact and accuracy-sensitive barriers to this expectation. Given a bias-free one-hidden-layer ReLU network $f(x)=\sum_{r=1}^n \mathrm{ReLU}(a_r^\top x)$ with unit positive output weights, deciding whether its global Euclidean Lipschitz constant is at least a rational threshold is NP-complete and W[1]-hard when parameterized by the input dimension $d$. The same holds on the unit ball and with integral first-layer weights having at most nine nonzeros. More sharply, no deterministic multiplicative approximation scheme runs in $g(d)\mathrm{poly}(\mathcal B,1/\varepsilon)$ time unless FPT equals W[1]. Under the Exponential Time Hypothesis, no such algorithm runs in $g(d)(\mathcal B+1/\varepsilon)^{o(d/\log d)}$ time. Thus accuracy cannot have a polynomial dependence separated from dimension. The exact result resolves the Euclidean case of an open problem posed at COLT 2025 and left open by the ICLR 2026 parameterized hardness theory for general two-layer networks. The approximation barrier is specific to generator-presented zonotopes, complementing known $(1/\varepsilon)^{O(d)}$-time schemes and an analogous barrier for halfspace-presented polytopes. Our lifted-selector reduction has an inverse-polynomial radial gap, proved through a quantitative theorem for rational cyclic zonogons. Equivalently, the results apply to Euclidean zonotope radius and positive-semidefinite binary quadratic maximization parameterized by rank. Convexity makes minimization easy, but it does not make global sensitivity fixed-parameter tractable or permit a dimension-separated fully polynomial accuracy guarantee.
Read the full abstract
Artificial Intelligence
FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection
Multi-view multi-label feature selection aims to identify a compact and informative feature subset from heterogeneous views while preserving discriminative information for multiple labels. Existing methods are generally developed from specific modeling perspectives and incorporate mechanisms tailored to particular data characteristics. Designing suitable feature selection algorithms across datasets with diverse and heterogeneous characteristics still relies heavily on expert knowledge and substantial manual effort, imposing considerable time and labor costs that severely hinder the practical adoption of feature selection. To address this problem, we propose FeatureHospital, a Skill-driven multi-agent framework for automated multi-view multi-label feature selection algorithm design. FeatureHospital first diagnoses the target dataset to identify its feature selection issues. Based on the diagnosis, specialist agents equipped with domain Skills then prescribe corresponding optimization strategies and Loss terms for different issues. After that, the resulting prescriptions are reconciled to remove overlaps and resolve conflicts before being integrated into a compact dataset-specific objective. Finally, the constructed objective is optimized to select the final feature subset. Experimental results demonstrate that FeatureHospital can construct effective feature selection algorithms for different datasets based on their individual characteristics.
Read the full abstract
Artificial Intelligence
When Single-Dataset Conclusions Fail: A 45-Task Study of Threshold Tuning and Resampling for Imbalanced Classification
Class-imbalance handling is routinely evaluated on a single benchmark dataset, and the resulting conclusions are reported as if they were properties of the method. We show this practice is unsafe. On the public Kaggle credit-card fraud dataset, under a leakage-free nested cross-validation protocol in which the decision threshold is selected on a held-out inner validation fold, a plain Random Forest at the default 0.5 threshold attains F1 = 0.861 +/- 0.021, and threshold tuning yields it no benefit (delta-F1 = -0.002). Read alone, this supports an appealing conclusion: for a well-calibrated ensemble, imbalance handling is unnecessary. We then apply the identical protocol to 45 binary tasks spanning imbalance ratios from 1:1.5 to 1:178 (2,025 model fits, four model families). The conclusion reverses. Random Forest benefits most from threshold tuning across the suite (delta-F1 = +0.101 +/- 0.134), not least, while three other families replicate their fraud-dataset behaviour almost exactly. SMOTE likewise harms the fraud dataset but helps across the suite (mean delta-F1 = +0.076; 138 wins, 39 losses; Wilcoxon p = 2.7e-17). Two further results. Threshold-tuning benefit is non-monotonic in the imbalance ratio: near zero below 1:5, peaking at +0.120 in the 1:15-1:40 band, declining to +0.045 beyond 1:100 - explaining why the fraud dataset, at 1:577, is an unrepresentative place to study the question. And we reject an intuitive heuristic: validation-set calibration error does not predict tuning benefit (expected calibration error r = -0.087; Brier r = +0.137), so calibration diagnostics cannot tell a practitioner whether tuning is worthwhile. We release the protocol, the 45-task harness, and all per-run metrics.
Read the full abstract
Computer Vision
The Right Prior for the Right Deformation: Rethinking Continuous Deformable Image Registration
Deformable image registration models implicitly encode deformation priors through their parametrization and optimization. In this work, we conduct a validation study on continuous registration methods to examine how these implicit priors affect performance across different registration tasks. Classic B-Spline transformations impose locality, smoothness, and scale through their control-point structure, whereas recent INR-based methods impose different priors through neural parameterization and optimization. We compare INR-Dense (IDIR), which directly models a dense displacement field using a SIREN-based INR; INR-BSCP (SINR), which predicts B-Spline control points with an INR; D-BSCP, which directly optimizes single-scale B-Spline control points; and MR-D-BSCP, which adds a multiresolution coarse-to-fine scheme. Experiments on inter-subject brain MR registration (OASIS) and intra-subject exhale-to-inhale lung CT registration (DIR-LAB 4DCT) reveal different behavior across deformation regimes. On OASIS, where deformations are moderate but locally complex, D-BSCP matches or slightly outperforms INR-BSCP, suggesting that the B-Spline parameterization accounts for much of INR-BSCP's effectiveness. On DIR-LAB 4DCT, where respiratory motion is larger and more coherent, single-scale B-Spline methods (D-BSCP and INR-BSCP) are less suitable, while INR-Dense and MR-D-BSCP are more effective. Across both tasks, MR-D-BSCP achieves the best performance among the tested continuous parameterizations. These findings highlight that registration accuracy depends strongly on matching the induced deformation prior to the target motion pattern, and support prior-deformation matching as a practical design principle for medical image registration. Our code will be available at https://github.com/HengjieLiu/RightPriorDIR.
Read the full abstract
Information Theory · Cross-listed from math.PR
Central limit theorem in Rényi divergence for lattice random variables
Let $\{X_i\}_{i=1}^n$ be independent, identically distributed lattice random variables with zero mean, unit variance, and maximal span $h>0$. Let $S_n=(X_1+\cdots+X_n)/\sqrt n$. Let $Z_n$ denote the quantization of a standard Gaussian random variable on the support lattice of $S_n$. We show that the Rényi divergence $D_\alpha(S_n\|Z_n)$ of order $1<\alpha<\infty$ tends to 0 as $n\to\infty$ if and only if $D_\alpha(S_{n_0}\| Z_{n_0})<\infty$ for some integer $n_0$ and a sub-Gaussian condition holds. Furthermore, we derive an Edgeworth-type asymptotic expansion of the divergence to arbitrary order. We also show that the Rényi divergence $D_\infty(S_n\|Z_n)$ of infinite order tends to 0 as $n\to\infty$ if and only if a sub-Gaussian condition, a curvature condition, and a uniform separation condition hold. These results constitute lattice counterparts of Rényi entropic central limit theorems for continuous random variables obtained by Bobkov, Chistyakov and Götze (Ann. Probab. 47 (2019), 270–323) and Bobkov and Götze (Ann. Probab. 53 (2025), 453–477). Uniform separation is an additional assumption beyond the sub-Gaussian and curvature conditions used in the continuous setting. The failure of uniform separation may cause an exponentially tilted version of $X_1$ to concentrate on a sublattice of max span $kh$ for some integer $k>1$, which yields the lower bound $D_\infty(S_n\|Z_n)\ge\log k$, and hence a failure of the entropic central limit theorem.
Read the full abstract
Graphics
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any animation data. While existing audio-driven 3D speech animation methods rely on character-specific training data or laborious rigging/re-meshing, AnyTalk circumvents these limitations by leveraging recent video diffusion models trained on extensive video datasets. We first adapt a pre-trained video diffusion model to a target character through our Character-specific Fine-tuning (CsF) technique. By fine-tuning on rendered images of the 3D character paired with zeroed-out audio embeddings (representing "no motion"), we eliminate the need for animation data while preserving the motion prior of large-scale video diffusion model. We then uplift the resulting talking-head video into a 3D speech animation by estimating blendshape parameters through a proposed optimization process. AnyTalk enables lip-synced animations across diverse face meshes and blendshape configurations, significantly reducing manual effort and data requirements. We further enhance usability by distilling AnyTalk into a streamlined network, $\text{AnyTalk}_{RT}$, thereby enabling real-time performance. By leveraging talking-head video generation, our method broadens access to audio-driven speech animation technology for arbitrary characters. The code is publicly available at https://serin-yoon.github.io/projects/anytalk/.
Read the full abstract
Computer Vision
Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System
UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones. In this case, the vision-equipped UAV streams a video to a ground server where an operator assists its activities. The latency of video transmission has a profound impact on the effectiveness of the operator assistance. However, most techniques available for video transmission still incur significant latency costs. In this paper, we propose a graph convolutional neural network-assisted (GCN-Assisted A2C) deep reinforcement learning (DRL) system model to find the optimal pixel-correlated area of a suspicious object. We combine the Lagrangian dual form with gradient descent to prevent lack of convergence and over- and under-penalization constraint violation during latency optimization. The proposed system model sends a sub-group pixel-correlated area of the frame from the UAV to the server rather than the transmission of the whole video frame. The proposed framework utilizes the GCN model to explore hidden representations of feature-correlated groups of pixels. Moreover, the GCN supervises the A2C model, which selects a subgroup to enhance transmission latency, thus supervising the training of UAV actions in A2C. Experimental results show that GCN-assisted A2C reduces video frame transmission latency together with false detection rate in UAV vision systems over other DRL and state-of-the-art models.
Read the full abstract
Logic in Computer Science · Cross-listed from math.LO
Internal Reasoning and Consistency in Reflective Grounded Arithmetic
Reflective Grounded Arithmetic (RGA) is a paracomplete arithmetic allowing direct expression of any general-recursive computation. Every RGA term is a program and truth is grounded evaluation, with a proof certificate at each universal quantifier. This paper shows, in a machine-checked Isabelle/HOL development, that such a system is powerful enough to carry out its own metamathematics. A fuel-indexed decider of RGA's grounded semantics and checkers for RGA's proofs are compiled primitive-recursive RGA terms. RGA proves internally that its decider never affirms 0 = 1, and that every well-formed term it affirms has an RGA proof accepted by a transparent test. RGA proves that, for each valid RGA proof, its conclusion is true. RGA proves that each grounded-true well-formed term is provable. RGA proves that no proof in either of two decided classes of RGA proofs derives 0 = 1. RGA's truth predicate also serves as a medium for proof by reflection, of the kind that adds nothing to the system. RGA derives disquotation for quantifier-free formulas as rules in every context, at a free variable, and proves, as one sentence, that whenever its normalizer for polynomials in one variable gives two terms the same normal form, the equation between them is true at every value of the variable. Each such polynomial identity then follows from that sentence by closed evaluation and disquotation, with no reflection rule. A companion paper proves Gödel's incompleteness theorems for RGA and its extensions.
Read the full abstract
Numerical Analysis
A Reconstructed-Laplacian Method for the Surface Biharmonic Equation on Parametric Meshes
We develop and analyze a continuous/discontinuous Galerkin (CDG) method based on reconstructed surface Laplacians for the biharmonic equation on a smooth closed surface. Continuous mapped finite elements of degree $k\ge2$ are used on fitted parametric meshes of degree $r\ge1$, while a discontinuous degree-$(k-2)$ lifting corrects the broken Laplace-Beltrami operator for two-sided conormal-flux jumps. The resulting completed-square form is coercive on the mean-zero space for every fixed $\beta>0$, without requiring a sufficiently large penalty parameter. Under the standard geometric assumptions, we prove that the energy and reconstructed-Laplacian errors are $\mathcal O(h^{k-1}+h^r)$, and the $L^2$-error is $\mathcal O(h^{q_k}+h^{r+1})$, where $q_2=2$ and $q_k=k+1$ for $k\ge3$. Benchmark computations support these rates, while a surface Swift-Hohenberg experiment illustrates the extension of the method to nonlinear Laplacian-dominated models.
Read the full abstract
Systems and Control
Improving Observability of Relative Orbit Estimation Using Bearing Measurements and Light Curves
Relative orbit estimation using optical observations is a key technology for on-orbit servicing missions. In the far-range phase, the target appears as an unresolved point source, providing only bearing angles (azimuth and elevation) from the servicing satellite. Angles-only navigation is inherently challenging due to the weak observability of the relative range. To address this limitation, this study investigates the effectiveness of an estimation scheme that fuses photometric light curve data with bearing measurements. Since the light intensity depends on the relative distance, fusing light curves enhances the observability of the relative state. The Ashikhmin-Shirley model is used as the optical reflectance model, and observability analysis is conducted with the Fisher information matrix. Numerical simulations involving different target geometries, a flat plate and a box-wing satellite, demonstrate that integrating light curve measurements significantly enhances observability and enables faster convergence compared to conventional state estimation methods.
Read the full abstract
Machine Learning
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges. Hypergraphs can improve transferability by capturing higher-order sample relationships, yet existing hypergraph-based methods for online emotion recognition neglect the cross-day benefits of Riemannian geometry widely adopted in EEG transfer learning. To bridge this gap, we propose the Multi-feature Riemannian Hypergraph (MRieHy), a framework tailored for online test-time adaptation in MI-BCI decoding that leverages Riemannian geometry to strengthen cross-day transferability. MRieHy first computes Riemannian means of covariance matrices from cross-day training data to align multi-day distributions. It then constructs a hypergraph over covariance matrices using Riemannian distance, complemented by a second hypergraph over deep features built with cosine similarity. The two hypergraphs are fused via adaptively learned combination weights, jointly optimized with the label projection matrices. During online testing, MRieHy maintains a first-in-first-out buffer of recent samples, performs Riemannian alignment on the buffered data, and decodes with the learned hypergraph. Extensive experiments on a private four-class ECoG dataset and two public four-class EEG datasets validate that MRieHy achieves notable performance gains over state-of-the-art baselines.
Read the full abstract
Numerical Analysis
An adjoint-free integral feedback method for a parabolic inverse source problem with conditional stability
We study an inverse source problem for a linear non-autonomous parabolic equation with additive source term $f(t)+\zeta(t,x)$, where the unknown component depends only on time and is recovered from an integral observation of the solution. After reducing the problem to an equivalent linear inverse problem, we establish existence and uniqueness of the Tikhonov-regularized solution and derive a first-order optimality condition. We show that the forward operator admits a Volterra representation in time, yielding a weak-norm stability estimate in $H^{-1}(0,T)$ and, under an a priori $H^r(0,T)$ bound on the source, a conditional Hölder stability estimate in $L^2(0,T)$. Motivated by this Volterra structure, we introduce an adjoint-free integral feedback method that reconstructs the source using only forward solves. We analyze the feedback iteration by establishing its well-definedness and fixed-point properties, convergence for exact data, and finite-iteration stability with respect to noisy data. We further show that, with an appropriate noise-dependent stopping rule, the method constitutes an iterative regularization scheme. Numerical experiments for smooth and piecewise constant sources, supplemented by temporal regularization and automatic parameter selection, demonstrate accurate and stable reconstructions in the presence of noise.
Read the full abstract
Game Theory
Incorporating Bounded Rationality into Electric Vehicle Highway Charging Decisions: A Bayesian Game Analysis
Electric vehicles (EVs) represent a critical intelligent terminal within the Internet of Things (IoT). Despite the year-on-year growth in EV penetration, the highway driving experience still requires improvement. Accurate prediction of EV highway charging behavior is crucial to addressing this issue. This paper introduces a novel bounded rationality framework to analyze highway charging decisions. Specifically, we utilize prospect theory to capture the tendency of drivers to reserve more electricity than theoretically necessary. We then propose a Bayesian game in which EV drivers, unaware of others' decisions, aim to minimize costs, including range anxiety, charging fees, and queuing time. To gain insights into the game, we prove the existence and uniqueness of the Bayesian Nash Equilibrium in two practical scenarios. Our numerical experiments, based on real-life data, demonstrate that drivers' risk aversion tendency significantly influence EV charging decisions, charging demand, queuing lengths at charging stations, and the departure rate on the highway network. Furthermore, our strategy reduces cumulative EV cost and CSs' charging costs compared to other benchmarks.
Read the full abstract
Computers and Society
Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation
This study evaluates the effectiveness of utilising large language models (LLMs) to retrieve targeted segments from delivered video recordings to answer student questions in introductory programming environments. By restricting AI to identifying existing, educator-verified media rather than generating open-ended text, this approach aims to mitigate common pedagogical risks such as generative hallucinations and cognitive bypassing. We benchmarked three distinct models, two proprietary (Gemini 3.1 Pro and GPT 5.4 Pro) and one open-weight (Qwen3.5 397B), against a human lecturer's manual video selections. An automated judging framework subsequently assessed the outputs for relevance, sufficiency, redundancy, and the presence of extraneous material. While the AI-retrieved timestamps rarely shared exact overlaps with the human baseline, the proprietary models achieved near-parity with the expert in delivering sufficient and highly relevant answers. Furthermore, a pilot deployment of this retrieval system in a large C programming cohort (n~=900) demonstrated strong user engagement, with students primarily utilising the tool to review foundational concepts. By leveraging AI to retrieve established lecture material, this approach shows potential for a reliable, high-fidelity pathway for safely integrating LLMs into novice computing courses.
Read the full abstract
Game Theory
On the Incompatibility of Weighted PROPX and Pareto Optimality for Indivisible Chores
Proportionality (PROP) is one of the simplest fairness criteria for allocating items among agents with additive preferences. With indivisible chores, however, PROP is not always satisfiable. We study proportionality up to any item (PROPX), which requires every agent to satisfy proportionality after any chore is removed from her bundle. Under strictly positive costs, we settle the weighted compatibility question negatively: weighted PROPX and Pareto optimality are incompatible already for two agents and four chores. Moreover, for every $n\geq3$, we give an $n$-agent, $(n+1)$-chore counterexample whose shares can be arbitrarily close to equal. These counterexamples are item-minimal: under strictly positive costs, weighted PROPX and Pareto optimality are always compatible when the number of chores is at most the number of agents, and they are compatible for two agents with at most three chores. Our impossibility result contrasts with the compatibility theorem of Mahara (2026) for weighted envy-freeness up to one item (EF1) and Pareto optimality .
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Coded Hankel Polynomial Chaos: Spectral Identification of Dominant Polynomial-Chaos Modes
Identification of dominant polynomial-chaos modes is usually formulated as a sparse-regression problem on a sampled multivariate polynomial dictionary. We develop coded Hankel polynomial chaos (CH-PC), a complementary spectral formulation for dominant-mode identification. A finite generating transform converts PCE coefficients into a coefficient-generating polynomial, and evaluation along a geometric phase orbit produces a finite exponential sum. Its model order and spectral nodes are encoded by low-rank Hankel matrices, while coordinate phase shifts attach root-of-unity labels from which the full polynomial multi-indices are recovered. Coordinate-shifted probes are combined as common-node snapshots, and independent phase encodings provide redundant representations when a single spectral encoding is poorly conditioned. For finite observations, population, finite-data, and observed probes are kept distinct: sampling or quadrature error and observation error enter as separate Hankel perturbations, which are then connected to spectral stability, discrete decoding, and phase voting. For tensor-product candidate sets, the generating kernel factorizes into one-dimensional sums and can be evaluated without assembling the full multivariate PCE design matrix. Numerical experiments on sparse Legendre benchmarks and a stochastic Darcy problem illustrate exact recovery, noise stabilization, unknown-order identification by phase persistence, and dominant-mode recovery for a PDE-generated quantity of interest.
Read the full abstract
Data Structures and Algorithms
A Simple Las Vegas Algorithm for Sparse Nonnegative Convolution
Let $A, B \in \mathbb{Z}_{\ge 0}^n$ be nonnegative vectors and let $t = |\operatorname{supp}(A \star B)|$. We give a Las Vegas algorithm that computes $A \star B$ in $O(t \log t)$ expected time. More generally, for every $0 < \delta \le \frac{1}{2}$, the algorithm terminates within $O(t \log t \log \frac{1}{\delta})$ time with probability at least $1 - \delta$. The algorithm uses dense convolution, linear hashing, and the length reduction of \cite{BFN22}. Its main ingredient is a carry-free representation of the indices as vectors of constant dimension $d$ whose coordinates have size $O(t / \log t)$. We can then take our hash function to be the inner product with a random element of $\mathbb{F}_p^d$ for a prime $p$ of size $\Omega(t / \log t)$: this preserves addition and gives collision probability exactly $1/p$, while identities regarding the moments of the vectors identify and recover the isolated terms as in \cite{BFN22}. Our expected running time matches that of Jin and Xu~\cite{JX24} while using substantially different tools and yielding a simpler algorithm. Note that their algorithm also terminates within $O(t \log t)$ time with probability at least $1 - \frac{1}{t}$, while our tail bound is weaker.
Read the full abstract
Computer Vision
TokenSTFormer: A Tokenized Spatial-temporal Attention Model for Holistic Motion Analysis in Adolescent Idiopathic Scoliosis Screening
Adolescent Idiopathic Scoliosis (AIS) is a prevalent spinal deformity in adolescents that, if left untreated, can result in severe health outcomes. Traditional screening methods are limited by subjective interpretation, reliance on professional expertise and low scalability. To address these challenges, we present ScoliGait dataset, which comprises 1,516 gait video clips paired with corresponding X-ray records. We also introduce TokenSTFormer, a novel model that tokenizes spatial and temporal semantics to enhance feature representation and convergence. Our model achieves state-of-the-art performance, surpassing vanilla Vision Transformer encoder across key metrics, including accuracy of 0.79. This study highlights the potential of leveraging holistic motion features derived from gait video and attention-based models for scalable, cost-effective AIS screening, paving the way for future clinical applications in scoliosis detection.