Cryptography and Security
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Wednesday 19 August
Static Application Security Testing (SAST) tools are widely used in both industry and academia. Such tools often make design choices that sacrifice detection to achieve higher performance, i.e., increased precision, decreased runtime, or increased scalability. These design choices rely on certain assumptions regarding the target code or the analysis technique itself. Hence, the assumptions directly impact the detection outcome through the design choices they influence. This motivates a key question: do the sacrifices in the detection capabilities actually help tools achieve the expected performance gains? That is, are the underlying assumptions valid? This paper seeks to address this question by relying on a key observation that the assumptions made by these tools are generally of a causal nature. We propose CAUSEC, a causal analysis framework that makes SAST assumptions testable and explains why the performance changes given certain assumptions, beyond simple correlations. CAUSEC formalizes the assumptions of the SAST tool into the abstraction of a security assumption and combines assumption-driven causal modeling with effect estimation and validation to test its validity and investigate the factors affecting it. To understand what security assumptions generally entail, we perform a systematic literature review of SASTs that detect crypto-API misuse, leading to the discovery and qualitative analysis of 57 assumptions. We then demonstrate the utility and robustness of CAUSEC by testing a popular assumption in four highly relevant tools, using a manually labeled ground truth dataset consisting of 57,038 alerts. Our analysis leads to several key findings that represent insights regarding assumptions and causal effects, which we distill into 3 takeaways for future work.
Computational Geometry
Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
For $p \ge 1$, the $p$-Wasserstein distance measures the minimum cost of transporting probability mass between distributions, where moving unit mass between two points costs the $p$th power of their distance. For discrete distributions in one dimension, full transport is especially simple: after sorting, mass is matched in order along the line. By contrast, partial and unbalanced transport on the line remains much less understood. Recently, Chapel and Tavenard [ICLR'25] showed that, for $p=1$, all optimal partial transport plans between distributions supported on $n$ points, with uniform mass at each point, can be computed in $O(n\log n)$ time by exploiting the metric structure of the cost. For $p>1$, this structure no longer applies, and existing approaches require $\Omega(n^2)$ time. Our main contribution is an FFT-based data structure for balanced-interval transport queries, which bypasses this quadratic bottleneck and yields an $O(p\,n\log^2 n)$-time algorithm for computing all optimal partial transports on the line for every finite $p\ge 1$. We also provide an open-source C++ implementation that outperforms the state-of-the-art baseline on a range of synthetic instances. Finally, we establish a conditional lower bound for $p=\infty$: any subquadratic-time algorithm for computing all optimal partial transport plan costs on the line would violate the $(\min,+)$-Convolution Hypothesis. This separates the problem from full optimal transport, which is solvable in $O(n\log n)$.
Read the full abstract
Information Theory
Integrated Sensing and Communications over Hierarchical Cellular and Cell-Free MIMO Systems
This paper studies integrated sensing and communications (ISAC) over a hybrid system that seamlessly combines legacy cellular base stations with distributed cell-free (CF) access points (APs). We propose a hierarchical ISAC architecture where a central base station (CBS) serves its near users and simultaneously operates as a monostatic radar for aerial target detection, while distributed APs—many idle under user-centric clustering—act as cost-free bistatic receivers. The CBS jointly handles communication processing and multi-static sensing fusion, reducing fronthaul overhead compared to conventional cell-free ISAC. To achieve this, a five-phase time-division duplexing workflow with precise ISAC role assignment is specified. Closed-form expressions for spectral efficiency and multi-static sensing signal-to-noise ratio analytically characterize the communications–sensing Pareto frontier. Numerical results confirm that the proposed hierarchical design simultaneously achieves higher sum throughput and superior sensing accuracy than conventional cell-free ISAC.
Read the full abstract
Computational Engineering
Component-wise hyperreduction for nonlinear solid mechanics problems
Hyperreduced nonlinear solid-mechanics components can be generated offline and reused as transferable building blocks across different assemblies, boundary conditions, meshes, material parameters, and constitutive models. We use proper orthogonal decomposition (POD) and energy conserving sampling and weighting (ECSW) on the component level and connect the substructures by mortar mesh tying. The POD modes and the ECSW weights and elements are computed offline from simulations of single components and the finite rigid body motions are treated by 12 additional rigid body modes per substructure. The numerical examples demonstrate errors below 1 % for large quasi-static assemblies while evaluating less than 10 % of the elements. The same component bases and ECSW elements are successfully reused for finite-strain viscoelastic dynamics, although they were trained only on elastic Neo-Hookean component simulations. These results indicate that component-wise hyperreduction can provide reusable reduced building blocks for modular nonlinear solid-mechanics simulations.
Read the full abstract
Systems and Control
Deciding Relabeling Observation Consistency in Multi-Agent Discrete-Event Systems
Scalable supervisors for multi-agent discrete-event systems control groups of isomorphic agents through a common template. Under partial observation, such a supervisor is maximally permissive if the relabeling that maps the agents onto their template is relabeling observation consistent (ROC) and a local companion condition holds. Whether ROC is decidable was open. We show that it is PSPACE-complete: for nondeterministic plants with two observable and one unobservable event, and for deterministic plants with two observable and two unobservable events. On the tractable side, we characterize the relabelings that guarantee ROC for every plant, we give a polynomial-time algorithm for deterministic plants whose relabeling is injective on unobservable events, and we give sufficient conditions based on saturation and on simulation, with polynomial-time tests for both. We further show that ROC is compositional for components with pairwise disjoint templates, with equivalence if the alphabets are moreover pairwise disjoint, and that neither hypothesis can be dropped. Finally, we show that the structural condition proposed in the literature to guarantee ROC is incorrect, and repair the companion inclusion that the same proposition asserts.
Read the full abstract
Computer Vision
RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation
LiDAR scene flow estimates point-wise motion between two consecutive scans, referred to as the source and target. Leading self-supervised methods typically minimize the Chamfer loss, the nearest neighbor distance between the flow-compensated source and the target. However, nearest-neighbor search does not enforce motion rigidity, often leading to inconsistent flows within object instances. Existing approaches address this issue with additional regularization terms, but flow consistency among points remains limited, especially for large objects. We propose RVLoss, a self-supervised loss that incorporates motion rigidity by design through a runoff vote mechanism. Our key observation is that the point-wise motion, calculated from nearest neighbor search, can often be grouped into a small set of dominant flow candidates by voting (top-k voting). Furthermore, when compensating the source by these candidates, the flow that best represents the underlying rigid motion often yields the highest consensus after a second voting (top-1 voting). Based on this insight, we incorporate the two-stage runoff vote into loss design and create cluster-wise rigid flows and free-form flows as pseudo-labels for self-supervised learning. RVLoss can be seamlessly integrated into existing feedforward architectures. Experiments on the Argoverse2 2026 Challenge show that models trained with RVLoss achieve state-of-the-art performance among self-supervised approaches, outperforming baseline models trained with alternative loss designs by 20%. Moreover, cross-dataset evaluations demonstrate consistent performance improvements across four additional datasets. Code will be released upon acceptance.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration
We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model. Existing GP-UCB analyses in this setting typically require the exploration parameter to grow with the horizon to maintain uniform confidence bounds. Using per-round local confidence events, we show that GP-UCB can instead be run with a constant exploration parameter and obtain an expected-regret bound whose coefficient depends on the drift rate. We also derive a sharper time-varying maximum-information-gain bound. For the squared exponential kernel, it yields $\tilde\gamma_T/T=\widetilde{\mathcal O}(\epsilon^{1/2})$ and expected average regret $\widetilde{\mathcal O}(\epsilon^{1/4})$ in the persistent-drift regime. The same constant-exploration analysis also yields realized-regret guarantees. Simulations support the predicted logarithmic dependence of the bound-suggested exploration parameter on $1/\epsilon$.
Read the full abstract
Logic in Computer Science
Undecidability of Confluence for Binary Length-Reducing Cycle Rewriting
Confluence guarantees that diverging rewrite choices can always be rejoined. For finite terminating string- and term-rewriting systems, confluence is decidable by critical-pair analysis, and in polynomial time for length-reducing strings. For finite terminating (hyper)graph transformation systems, in contrast, confluence is undecidable. We show that undecidability already appears for words on a circle, that is, strings up to rotation. Confluence of finite cycle-rewriting systems over the fixed alphabet $\{0,1\}$ is undecidable, indeed $\Pi^0_1$-complete, even when every rule has a nonempty right-hand side and strictly reduces length. Under this restriction termination is syntactically evident, and derivations from a nonempty length-$n$ cycle have fewer than $n$ steps. The same holds over every fixed alphabet with at least two letters, while the one-letter case is decidable. Rotation alone separates cyclic from string rewriting. The proof compiles a deterministic verifier into a weighted cycle system with one controlled branch, then into a binary length-reducing system via a run-length code whose cleanup rules send every reducible malformed cycle to one error normal form.
Read the full abstract
Information Retrieval
Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval
Dense retrieval has become a cornerstone of modern local-lifestyle e-commerce search by encoding queries and items into semantic embedding spaces. While recent advancements have transitioned from BERT-based embedding models to Large Language Models (LLMs), most approaches still treat LLMs as static text encoders, neglecting their inherent reasoning capabilities. Furthermore, standard dense retrieval models remain query-centric, which is insufficient in e-commerce scenarios where sparse and ambiguous queries create an intent gap that can only be bridged by the rich context of user history. Meanwhile, existing personalized retrieval methods typically rely on implicit embedding interactions, which lack the reasoning capability to effectively disambiguate user intent from noisy historical behaviors. To address these challenges, we propose Think-to-Personalize (TTP), a novel framework that unifies explicit user-centric intent reasoning with dense retrieval. By reasoning over the user's historical purchase sequence, TTP explicitly deduces latent personalized needs and generates an intent-enhanced query, which is then encoded into a unified dense embedding. Specifically, we design a two-stage training paradigm: (1) a Supervised Fine-Tuning (SFT) stage that establishes cold-start capabilities; and (2) a Reinforcement Learning (RL) stage that aligns the reasoning process with retrieval utility using Group Relative Policy Optimization (GRPO). Extensive experiments on both proprietary and public benchmarks demonstrate that TTP significantly outperforms state-of-the-art baselines. Furthermore, in online A/B tests, it achieved a +0.46% lift in order volume, validating its practical effectiveness and establishing a new paradigm for reasoning-driven personalized dense retrieval.
Read the full abstract
Computational Complexity
Lower Bounds for Domination-Type Problems Parameterized by Rank-Width
For graphs of rank-width \(w\), the algorithms of Bui-Xuan, Telle, and Vatshelle (Theor. Comput. Sci., 2013) for fixed finite/cofinite \((\sigma,\rho)\)-problems and of Bergougnoux and Kanté (SIAM J. Discrete Math., 2021) for Connected Dominating Set run in \(2^{O(w^2)}n^{O(1)}\) time. Bergougnoux, Korhonen, and Nederlof (STACS 2023) proved a matching lower bound under the Exponential Time Hypothesis (ETH) for Weighted Dominating Set, but left the unweighted problem open. We prove that, unless ETH fails, Dominating Set admits no \(2^{o(w^2)}n^{O(1)}\)-time algorithm, even on split graphs and, separately, on bipartite graphs of diameter at most four, and even with a rank-decomposition or witnessing vertex order supplied. The proof replaces the earlier weights by a two-guard gadget and uses a low-rank equality gadget to carry \(k^2\) assignment bits through cuts of rank \(O(k)\). The construction also gives the same lower bound for Independent, Connected, and Total Dominating Set on restricted graph classes and applies to a broad family of \((\sigma,\rho)\)-set problems. This family includes cases in which \(\sigma\) is neither finite nor cofinite and contains the entire nontrivial cofinite–cofinite minimization regime. Every solution within the target budget has target size and corresponds bijectively to a satisfying assignment. Under the counting Exponential Time Hypothesis (\(\#\mathrm{ETH}\)), the same bounds therefore hold for counting solutions of size at most or exactly the target. Together with the known algorithms, our results show that the quadratic dependence on the rank-width \(w\) is optimal up to constant factors in the exponent for the classical problems above and throughout the covered finite/cofinite regime.
Read the full abstract
Artificial Intelligence
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which skill to read has thus become a decision the policy itself makes in the middle of an episode, yet no existing signal trains it. We show that the default remedy, outcome-rewarded RL over the candidate slate, cannot teach it, for a structural reason we identify and name selector credit starvation: under a broadcast, sequence-level advantage, the few tokens that name the chosen skill carry a vanishing share of the loss, and the credit they inherit is increasingly wrong-signed as trajectories lengthen. A correct choice is punished whenever the execution after it fails, even though the choice itself is among the most valuable decisions in the trajectory. Auditing a completed run's own training artifacts confirms all three properties, each worsening monotonically with horizon. SkillGate removes the failure by construction: it partitions the token support into two disjoint credit channels, outcome credit reaching only execution tokens, and a separate action-local advantage reaching exactly the skill-naming tokens, positive only when a trajectory's single read is the correct one. On five agentic benchmarks under a 16-candidate slate, SkillGate lifts a 9B policy from 40.8% to 53.2% trial success, well ahead of the identical budget spent on outcome reward alone, while cutting exposure to misleading candidates by two thirds and reading fewer skills.
Read the full abstract
Machine Learning
Multi-stage neural operator learning with application for convolutions
Convolution integrals widely exist in applications, and to enable fast and accurate computations, this paper introduces two general multi-stage neural operator learning frameworks. The first, Deep Collocation Neural Operator (DCNO), is a supervised approach that iteratively refines the operator approximation by learning residuals from input-output data pairs. The second, Deep Galerkin Neural Operator (DGNO), is an unsupervised framework applicable when the target operator can be represented by a PDE, leveraging the weak form of the PDE residual for training. Both methods progressively construct basis operators through multiple training stages to enrich the approximation space, leading to significantly improved accuracy over standard one-shot operator learning. We provide theoretical analysis for their approximation capabilities and implement them for learning convolutions. Extensive numerical experiments demonstrate that both DCNO and DGNO achieve high accuracy, approaching machine precision under single float for convolution problems, and offer substantial efficiency gains for numerous queries or parametric variations compared to traditional solvers. We also extend these frameworks to handle multi-input operator learning scenarios involving variations in both the density and kernel of a convolution.
Read the full abstract
Systems and Control
Comparing Controller Synthesis Methods with Deadline-Miss Awareness
This paper presents a comparative study of real-time controller design methods for dynamical control systems subject to deadline overruns. Numerous techniques have been proposed to handle missed deadlines, i.e., including models or information of possible deadline misses directly in the control design. These approaches substantially differ in their assumptions, supported execution semantics, required runtime information, and provided guarantees, making direct comparison challenging. We address this gap with a qualitative assessment of representative deadline-miss-aware control methods. We analyze the design space of such controllers and identify the critical assumptions on the real-time constraints, the control design criteria and implementation aspects. We expose how these different assumptions lead to the different trade-offs in applicability, and control performance and guarantees. We contribute a comparison tool enabling researchers to systematically benchmark new techniques against the state of the art. The study is supported by simulations on two case studies: a Furuta pendulum and an electric motor to illustrate the practical behavior of the different approaches under missed-deadline conditions.
Read the full abstract
Machine Learning
GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models
Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (Generative Expansion and Real Anchoring), a modular two-stage framework that distills TFMs into lightweight MLP or tree-based predictors that can be deployed on commodity CPUs. Stage 1 uses synthetic covariates solely as teacher-query locations and trains the student on soft TFM targets, expanding coverage beyond observed rows. Stage 2 re-anchors the student to the target distribution using real labels and out-of-fold teacher predictions, whitch avoids self-labeling leakage. We further derive a risk certificate characterizing the trade-off between generated-query volume and generator fidelity. Experiments on TALENT and TabArena demonstrate the broad applicability of GEAR. Two-stage MLPs outperform supervised MLPs by 1.81–2.00 AUC points on binary tasks and 1.19–1.35 points on multiclass tasks, with additional gains over real-data-only distillation of 1.76–2.19 and 2.09–2.40 points, respectively. On binary tasks, the gains also transfer to LightGBM and XGBoost, and all three student families outperform CatBoost, the strongest non-TFM baseline, in mean AUC. Ablations show gains beyond longer training or alternative warm starts, greater stability from staged than mixed optimization, and generator-dependent diminishing returns as query volume increases. Finally, GEAR reduces median inference time by 57–2866 times and peak prediction memory by 1.9–3.3 times, while retaining higher AUC than matched supervised baselines.
Read the full abstract
Artificial Intelligence
ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery
Last-mile delivery aims to handle dynamically arriving orders with couriers while modeling complex spatial and temporal correlations. Recent learning-based methods model spatiotemporal dependencies among orders to predict courier service sequences, but leave next-order decision making unexplained. Describing the current delivery state in language allows LLMs to reason explicitly about the spatial, temporal, and behavioral cues behind an individual decision. As direct predictors, however, LLMs remain sensitive to task presentation and often produce unreliable decisions. To address these challenges, we introduce ORBITER, an agentic Order Arbiter for next-order decision-making in last-mile delivery. ORBITER models courier service through decision points, each containing the courier's spatiotemporal state and visible orders and exposing local trade-offs for modeling and verification. Fixed proposers rank the candidates, and a structured report identifies where their rankings disagree. The LLM uses task-specific tools to gather evidence on the leading alternatives, while an independent critic checks the resulting decision against that evidence. We conduct extensive evaluations on data in four cities, where ORBITER outperforms existing state-of-the-art baselines by up to 9.2% on average showing its effectiveness.
Read the full abstract
Systems and Control
Robust Joint Planning of EV and eBus Charging Infrastructure with PV Self-Consumption under Demand Uncertainty
This paper presents a mixed-integer linear programming (MILP) framework for joint electric vehicle (EV) and electric bus (eBus) charging-infrastructure planning with photovoltaic (PV) self-consumption. The model co-optimizes charger siting, sizing, technology selection, eBus-to-depot assignment, and hourly charging schedules. A deterministic MILP is first formulated as a nominal benchmark and then extended to a scenario-based robust min–max formulation under vehicle energy-demand uncertainty. The robust model uses shared first-stage infrastructure decisions and scenario-specific operating decisions, and minimizes infrastructure cost plus the worst-case scenario operating cost through an epigraph reformulation. Soft-feasibility penalties quantify unmet charging energy, terminal state-of-charge (SOC) shortfall, and capacity violations under stressed scenarios. A 50-node case study shows that route-segment eBus demand and PV weighting alter charger deployment, technology mix, and grid import, while V2G enables hard-feasible robust operation at sufficiently large penalty weights. These results highlight that effective long-term infrastructure planning must simultaneously account for diverse vehicle fleets, operational strategies that adapt to different scenarios, and node-level constraints on charging capacity.
Read the full abstract
Cryptography and Security · Cross-listed from quant-ph
Decisional Monogamy-of-Entanglement for Coset States and Applications to Unclonable Cryptography with Correlated Challenges
A main application of quantum information in cryptography is copy-protection, where we encode a functionality (such as a decryption key or software) into a reusable quantum state so that it cannot be split into two adversaries (called freeloaders) that both remain useful. Previous works have only shown security for independently sampled challenges for the two adversaries. A competing natural security notion is identical-challenge security where the adversaries receive the same challenge. This notion has many real-life applications and connections to other fundamental primitives such as unclonable bits (i.e. unclonable encryption) and unclonable lockboxes (i.e. copy-protection of point functions). Despite its importance and numerous attempts, achieving identical-challenge security in the plain model has remained open. We first make progress on the definitional foundations of copy-protection by introducing natural copy-protection security definitions that imply the previous ones (including identical-challenge security) and better capture the security intuitions and real-life use cases; and we also characterize the relationship between the previous definitions. Then, we show how to achieve in the plain model our new stronger definitions for copy-protection of general classes of functionalities. In particular, we resolve the long-standing open questions of copy-protection of point functions, copy-protection of compute-and-compare programs, and identical-challenge secure copy-protection of decryption keys and all puncturable functionalities. Our technical core is a new decisional monogamy-of-entanglement result for coset states, which both allows us to achieve our new results, and also significantly simplifies and unifies unclonable cryptography proofs. We believe this will have further applications and may be of independent interest.
Read the full abstract
Robotics
Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction
Indoor scene synthesis provides essential environments for embodied AI, robotic manipulation, and simulation-based policy learning. Recent code-based scene generation methods produce editable and extensible environments, yet they remain focused on visual construction and object-level articulation, leaving the functional usage of scenes largely unmodeled. To address this problem, we present RoomWright, an agentic usage-driven framework for generating 3D scenes represented entirely as code for embodied interaction. RoomWright performs usage-driven object reasoning, which treats each anchor as a task centre and admits task-required objects and their affordances. A code agent further enables multi-part interaction by compiling each interaction into a trigger, condition, effect rule that updates structured object states, capturing causal dependencies across objects. Moreover, since manipuland orientation is ambiguous and hard to recover from pixels, RoomWright alleviates this via annotation-informed usage-guided orientation. Extensive experiments demonstrate the effectiveness of our method. The resulting scenes are executable, editable, and simulation-ready, providing interactive environments for embodied AI and policy learning.
Read the full abstract
Computational Complexity · Cross-listed from quant-ph
Near-Optimal Mixedness Testing with Pauli Measurements
We consider a fundamental problem of mixedness testing: Given $n$ copies of an $N$-qubit state $\rho$, determine whether $\rho = \mathbb{I}_d/d$ or $\|\rho-\mathbb{I}_d/d\|_1 \geq \varepsilon$ with high probability, where $d = 2^N$. In particular, we focus on performing this task with simple single-qubit measurements, i.e. measurements that are prepared independently on each qubit. We provide a nearly complete picture of single-qubit mixedness testing by showing that its copy-complexity is $\tilde{\Theta}\left(\sqrt{10}^N/\varepsilon^2\right)$. To establish our lower bound, we introduce a new measurement-dependent lower bound framework for adaptive single-copy state certification. For the upper bound, we present a randomized Pauli basis measurement protocol, which relies on a new primitive for computationally efficient uniformity testing of correlation-concentrated distributions on the Boolean hypercube. In conjunction, we provide lower and upper bounds for mixedness testing with fixed Pauli measurement protocols.
Read the full abstract
Data Structures and Algorithms
Minimizing the Makespan Approximately on Two Identical Parallel Machines with a Loading–Unloading Server
We study makespan minimisation on two identical parallel machines that share a single server for both loading and unloading. Each job must be loaded, processed without interruption on its assigned machine, and unloaded immediately after processing, with a common positive integer duration for all loading and unloading operations. We prove that the decision problem is NP-complete for every fixed server-operation duration and strongly NP-complete when this duration is part of the input. We then analyse ordinary list scheduling and the longest-processing-time rule in the non-unit setting. List scheduling has a tight supremum ratio of two. For the longest-processing-time rule, we obtain the exact worst-case ratio when all processing times are at least the server-operation duration, and derive new parameter-dependent lower and upper bounds for unrestricted instances. The results show that both processing-time granularity and blocking generated by short jobs shape the approximation behaviour of the common-server problem.
Read the full abstract
Artificial Intelligence
Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks
Leak localization is usually evaluated as forced-choice prediction, although sparse hydraulic observations may not justify excavation. Here, we quantify a pressure-information limit and use it to recast localization as selective, evidence-gated decision-making. A physics-grounded executor falsifies competing leak, demand, sensor and valve hypotheses in a hydraulic twin. Deterministic code computes every number and every acceptance predicate; an independent large language model auditor may add a rejection but never overturn a failed check. Forced retrieval placed only 95 of 300 leaks in the correct zone. Across 550 mixed events, the gate acted on 223 (214 correct); on a third-party 33-leak benchmark, all four accepted events were correct. In a replay of 194 audited City D repairs, the pressure tier authorized five excavation recommendations, three matching the repaired district, while the district-inflow tier returned the correct district for 85 events. Observability limits with machine-checkable abstention enable auditable utility intervention.
Read the full abstract
Computer Vision
EVADE: Evidence-Verified Agentic Diagnosis with Escape
Medical vision-language models (VLMs) can achieve high accuracy but remain unreliable: they are systematically overconfident, benefit little from test-time reasoning, and lack the ability to reliably calibrate trust in their own responses. We introduce EVADE (Evidence-Verified Agentic Diagnosis with Escape), an inferential, non-training method that enhances the safety of deploying a single frozen VLM. EVADE responds and, when uncertain, localises the region most diagnostically relevant, re-answers on a zoomed view, and commits only when both the entire image and the zoomed view responses agree; otherwise, it abstains. To directly address verification hallucination in single-model self-checking, our main idea is to verify gate consistency across different image views rather than re-reading the model's own text. Experimental evaluation on VQA-RAD, SLAKE, and PathVQA using Qwen2.5-VL-7B reports that EVADE is the only method that simultaneously improves both calibration and selective risk while maintaining accuracy, reducing expected calibration error (ECE) by up to 45% compared to zero-shot. Chain-of-thought, self-consistency, and self-verification all fail at least one axis. A grounding analysis reports that self-proposed regions perform better at diagnostic structure localisation than centres or random crops. However, a 7B VLM cannot use this localisation to revise answers. Therefore, reliability gains come from the consistency gate and calibrated abstention.
Read the full abstract
Computer Vision
EfficientSync: Real-Time Lip Synchronization via Deformation-Based Reference Texture Mixing
Audio-driven lip synchronization manipulates the mouth region of a talking-face video to match the driving audio while preserving head pose, identity, and background. Although the task is inherently local editing, prevailing approaches reconstruct the entire lower face with heavy GAN- or diffusion-based decoders, incurring substantial latency and, more critically, hallucinating intra-oral details such as teeth and lip wrinkles instead of preserving authentic textures. We contend that the bottleneck in identity preservation is not the scarcity of reference frames, but the lack of a mechanism that faithfully transfers the genuine textures they already contain. We therefore present EfficientSync, a real-time deformation-based framework that retains reference textures rather than resynthesizing them. First, the Dynamic Texture Mixer reformulates multi-reference fusion as channel-wise selection, evaluating each spatially aligned reference in a global context and aggregating them by channel-wise weighted summation, preserving textural integrity at low cost. Second, Spatio-Temporal Shifted Adaptive Masking decomposes the source frame into lip-generation conditions and an independent background prior, suppressing lower-face leakage while blending the synthesized mouth seamlessly into the background. Third, STAR Sampling, a zero-overhead pre-processing step, retrieves the sharpest and most topologically diverse reference frames. Experiments on HDTF and VFHQ show state-of-the-art visual quality and identity preservation at 166 FPS on a single GPU. Video demos: https://alunaticat.github.io/EfficientSync/index.html.
Read the full abstract
Machine Learning
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods generate and revise reward functions as monolithic programs, making it difficult to reliably preserve and reuse effective components discovered in earlier iterations, leading to unstable performance across iterations. To address this, we propose Module Level Reward Evolution Framework (MLREF). At the core of MLREF is a module pool, a persistent repository of reusable reward components. MLREF treats the module pool as the primary optimization object: the pool evolves across iterations by accumulating successful modules, refining underperforming ones, and reusing proven components; while reward functions are constructed as linear combinations of modules drawn from this pool. To drive this evolution, MLREF integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization. Experiments on 17 tasks show that MLREF outperforms strong baselines by 25.2% in locomotion and 6.6% in manipulation, with more stable optimization dynamics.
Read the full abstract
Computation and Language
Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis
Medical automatic speech recognition (MedASR) requires adaptation to specialised terminology, limited annotated clinical data, and multilingual use cases. Although large-scale pretrained ASR models such as Whisper achieve strong generalisation, their behaviour after medical and multilingual adaptation remains insufficiently understood beyond word error rate (WER). This paper investigates how multilingual medical adaptation reshapes the internal representations of Whisper models through layer-wise encoder analysis. We compare zero-shot decoding, English-only fine-tuning, German-only diagnostic fine-tuning, two-stage EN->EN+DE continuation, and direct EN+DE fine-tuning across Whisper model sizes. Fine-tuning substantially improves MedASR performance, but the best model depends on the adaptation setting: Whisper-Medium gives the lowest English WER (7.72%) and the lowest combined EN+DE WER under direct EN+DE training (26.30%); German-only Whisper-Large-v3 gives the lowest German WER (44.96%), but as a within-corpus diagnostic on 86 single-speaker training utterances rather than robust generalisation. Layer-wise analysis of the two-stage Whisper-Small trajectory shows that English medical fine-tuning produces the dominant encoder shift, whereas multilingual continuation largely preserves the adapted representation space. Domain and language information remain highly recoverable across layers, while linearly recoverable error-predictive cues weaken as WER improves.
Read the full abstract
Systems and Control
Detecting Feedback-path Delay Injection Attacks Using Interacting Multiple Model Filtering
Time-delays are known to have a detrimental effect on feedback systems. In the context of networked cyber-physical systems, delays can be injected by malicious adversaries. Detecting them early is an important challenge. This paper proposes a novel variation of Interacting Multiple Model filtering to detect delay injection attacks in feedback control systems, when hidden in an open loop setting. The detection scheme is formalised by treating delay as alternative modes of the system, and theoretical analysis of the stationary distribution informs a reduction to a three parameter model as well as the choices of hyper parameter values. The method is evaluated on a cruise control application, and shows detection within a few seconds and a low false alarm probability.
Read the full abstract
Software Engineering
Contract-Aware Rescue of a Drifted Isabelle Development: The Double-Tank Case Study
Large language models can propose proofs for interactive theorem provers, but a successful build does not show the surrounding verification task was preserved. We study this problem in an Isabelle development of a sampled-data double-tank controller. The work began with nine theories and ten unfinished obligations, grew to a 16-theory build without sorry, oops, added axiomatisation, or oracle use, and accumulated 23 stable and 36 broken proof states. A retrospective audit found material changes in 16 of the 100 original declarations, including a weakened end-to-end assurance theorem that assumed three of the four requirements in its conclusion. We used CAPRI, a contract-aware proof-repair tool, to govern a reconstruction by combining Isabelle acceptance with an independent check of repository changes against machine-readable edit contracts. The reconstruction discharged all ten scoped obligations within the original nine-theory structure. A secondary replay by a co-author reproduced the R10 build, contract checks, control tests, and principal audit findings; independent replication remains future work. Operational end-to-end verification remains incomplete: we still need to connect operational executions to the reconstructed quantitative trace contract, a task requiring an extended contract.
Read the full abstract
Computation and Language
Identifying Implicit Premises for Logical Reconstruction of Argument Graphs
The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with implicit premises). There are natural language processing methods for identifying enthymemes in text, and there are symbolic methods based on abduction for identifying missing premises in a logical representation of enthymemes. However, there is a need for methods to generate implicit premises to logically show a known entailment or contradiction relationship between a pair of statements. To address this, we propose a neuro-symbolic pipeline that uses large language models (LLMs) to generate intermediate implicit premises that are translated into logical formulae and used with logical formulae representing explicit premises and explicit claims to show the logical relationships between them (entailment, contradiction, or neutrality). Our approach is evaluated on the Microtext Argumentative Corpus.
Read the full abstract
Artificial Intelligence
Pairwise Logical Selection of Enthymeme Completions under Semantic-Link Uncertainty
Arguments often omit premises or claims, forming enthymemes. We study pairwise logical selection between two candidates for the omitted component. Existing natural language methods can identify or generate candidates but often do not expose how the selected candidate completes the inference, while logic-based approaches usually assume that the required formulae and background knowledge are available. We extend a prior neuro-symbolic pipeline from missing-premise to missing-claim selection and replace binary entailment outcomes with logical-resistance scores. Top-Link uses weighted Partial MaxSAT under a single configuration of highest-confidence semantic links. We then introduce Possible-World Atom-Link Formalization (PWAL), which keeps translated formulae fixed and marginalizes logical resistance over alternative cross-formula semantic-link configurations. We evaluate PWAL on five tasks: ARCT and a CDED-derived task for missing-premise selection, iDebate- and AAE2-derived tasks for missing-claim selection, and alphaNLI for abductive hypothesis selection. Relative to Top-Link, PWAL raises strict accuracy by 2.95-30.86 percentage points and reduces tie rates by 4.57-58.00 percentage points on all five tasks. When ties receive half credit, accuracy still increases by 0.45-6.04 percentage points. PWAL also records the translated formulae, sampled link configurations, and resistance components for every comparison, providing a transparent trace of each score.
Read the full abstract
Machine Learning
A Unifying Relational Perspective on Expressive Lottery Tickets
Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Strong Expressive Lottery Ticket Hypothesis (SELTH) posits the existence of sparse GNNs that preserve Weisfeiler-Leman (WL) expressivity on static graphs. We generalize this existence result to a probabilistic statement for multi-relational and temporal domains via the relational WL (RWL). We prove that sufficiently parameterized RGNNs contain sparse subnetworks that maintain 1-RWL expressivity and derive a lower bound on the probability that a random pruning yields such a subnetwork. We show that common TGNNs and cross-graph message passing schemes admit RGNN reformulations such that they inherit these guarantees and, moreover, that the expressivity of a sparse RGNN is connected to its optimization behavior under common update regimes. Experiments instantiate the bound, compare it to empirical probabilities on synthetic data, and study how pre-training expressivity relates to optimization and prediction quality metrics on temporal and molecular benchmarks.