Computer Vision
LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation
Yi Luo, Yike Guo, Wenxuan Li et al. (+3 more)
Delineating lung tumours on computed
tomography (CT) takes a considerable share of the time spent on radiotherapy planning, and a contour proposed by a model can be refined interactively by the clinician. Promptable foundation models such as SAM 3 support this workflow by writing each correction into a session
memory that conditions the remaining slices, while the model weights stay fixed. On 690 test cases from five public CT cohorts, fine-tuning SAM 3 on lung tumours raises the Dice obtained from a single point
prompt from 0.298 to 0.757, and seven rounds of corrections raise it further to 0.765, but under
memory conditioning alone the accuracy on slices the annotator has not touched stops improving after six rounds. We therefore treat each correction as a training signal and propose LeCor, which performs test-time training on a small set of case adapters that are reset for every case and meta-learned such that a single gradient step driven by a click improves the slices that were not clicked. On the 133 test cases that span at least eight slices, LeCor raises the Dice reached after seven correction rounds from 0.787 with the fine-tuned model to 0.827, reduces the number of cases that never reach a Dice of 0.80 from 47 to 27, and reaches in three correction rounds the accuracy that the fine-tuned model attains in seven.
Read the full abstract ▾
All authors Yi Luo, Yike Guo, Wenxuan Li, Zongwei Zhou, Rui Zhang, Kai Ding
Machine Learning
From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
Hamed Jafarzadeh Asl, Yuanhao Yu and Vahid Partovi Nia
In-vehicle assistants must translate natural-
language requests into accurate vehicle function calls under strict
memory and latency constraints, making small
language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional
Token (FT) or provide function schemas directly in the
prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-
Prompt (SIP) can generalize to unseen functions at the cost of longer
prompts and higher inference overhead. We introduce a
benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, and the highest Seen accuracy in our main grid occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with a higher inference cost, chiefly the latency of processing the schema
prompt. Our theoretical analysis formalizes why only SIP can predict functions withheld as training targets and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
Joint Deployment and Resource Management for Group-Tag-Based Physical-Layer Authentication and Collaborative Communication in NTN
Parsa Rajabi, Mohammad Reza Abedi, Paeiz Azmi et al. (+1 more)
Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) has primarily been studied from a security perspective, while its system-level integration with communication remains less explored. We propose the secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a system-level formulation for the joint management of collaborative group-tag and private-data delivery in NTN, where high-altitude platform station (HAPS) placement, user association, and transmission powers are jointly selected under service and secrecy constraints. Group-level authentication tags and user data are collaboratively transmitted by multiple HAPSs, with artificial noise (AN) mitigating information leakage. We jointly optimize HAPS placement, user association, and power allocation to balance deployment regularity, tag distribution, and user-rate
fairness under secrecy, quality-of-service (QoS), power, and coverage constraints. The problem is addressed using a repair-based cross-
entropy method (RCEM) and a graph-aware advantage actor-critic (A2C)
algorithm (GA2C). Under colluding and non-colluding eavesdropper models, GA2C improves average secrecy spectral efficiency (SSE) by 135–139% over its single-connect baseline and 21.1–23.2% over its baseline without AN. Across ten independent random seeds, GA2C achieves approximately 23.4% and 17.9% higher mean per-user SSE under non-colluding and colluding eavesdropping, respectively, and a 16.2% higher mean private-rate Jain's index than RCEM. These results quantify the gains of multi-node connectivity and AN within the proposed framework under the evaluated assumptions.
Read the full abstract ▾
All authors Parsa Rajabi, Mohammad Reza Abedi, Paeiz Azmi, Nader Mokari
Discrete Mathematics
Polynomial-time algorithms for setting tight big-M coefficients in transmission expansion planning with disconnected buses
Behnam Jabbari-Marand and Adolfo R. Escobedo
The increasing penetration of renewable energy and rising electricity demand are driving the need to integrate new buses and transmission lines into transmission grids. These trends are reshaping transmission expansion planning (TEP), motivating the development of effective methodologies to manage the resulting complexity. This paper introduces the longest shortest-path connection (LSPC)
algorithm, a graph-based method to enhance the mixed-integer linear programming disjunctive formulation of TEP using valid inequalities (VIs). Traditional approaches for determining big-M coefficients in disconnected TEP networks typically rely on solving the computationally intensive longest path problem (LPP). In contrast, LSPC circumvents these limitations by efficiently identifying relevant power-flow paths between disconnected buses within the expansion network. We demonstrate that the VIs generated from these identified paths dominate those derived from LPP-based methods and other existing approaches.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Mode Coverage in Normalizing Flow Boltzmann Generators via Log-Ratio Variation
Qi Feng, Rongjie Lai, Di Qi et al. (+1 more)
Normalizing flow Boltzmann generators retain a tractable pushforward density, but training with forward KL depends on target samples that may be biased or omit modes. As a result, a flow can miss target mass while its observed importance weights give a high effective sample size. We introduce the log-ratio variation $\X_\omega$, the mean absolute pairwise difference of the target-to-pushforward log-density ratio under a weighting measure $\omega$, and use it to define KLXX, a new loss function. Two log-ratio variations are added to the forward KL (denoted by the two X's): one weighted by the target to improve accuracy, the other by a mixture of quench and temper samples with pushforward samples to search candidate modes. We derive the Fisher–Rao gradient flow of KLXX, where both variations contribute nonpositive dissipation, and a fixed-surrogate error bound for KLXX. We use KLXX in an adaptive-staging Boltzmann generator, with importance reweighting at every stage. We bound the sampling error of its inference scheme when the stage weights are essentially bounded, and prove it asymptotically unbiased in the sample size. In the numerical tests, KLXX improves mode coverage over forward KL. It also improves the generator's per-stage diagnostics against the loss that built the schedule. The observables the generator recovers are close to independent references. The log-ratio variations thus supply information that the forward KL loss usually omits.
Read the full abstract ▾
All authors Qi Feng, Rongjie Lai, Di Qi, Xuda Ye
Human-Computer Interaction
Exploring 3D Glyph Physicalizations for Public Engagement through River Health
Maria Teresa Ortoleva, Min Chen, Rita Borgo et al. (+1 more)
Introduction: In this paper, we present the preliminary design of a toolkit for making glyph-based physicalizations for public engagement. We use London river health data as a case study: a data set of significance to urban issues related to
climate change and of interest to draw public
attention, as part of the Greater London Authority's strategies. Design: We present the components of a 3D glyph-making toolkit, its encodings, and a step-by-step process for crafting a physicalization of a river's water quality using recycled materials. We reason about how users can use the template to learn about a data set while reflecting on the data's significance to their personal experience and self-mapping onto the physicalization. Reflection: We reflect on the opportunities that extending the design space of glyphs to 3D physicalization offers for supporting public engagement with complex, multi-dimensional data sets, scaffolding cognitive processes, and self-reflection, thereby bringing crucial environmental data to life. Conclusion: Future implementation of the 3D glyph template will enable the public of all abilities to explore river health data, physicalize complexity, and realize its relevance. We hope that its use in public engagement workshops will help raise awareness, invite care, and foster a sense of belonging.
Read the full abstract ▾
All authors Maria Teresa Ortoleva, Min Chen, Rita Borgo, Alfie Abdul-Rahman
Machine Learning
Code-to-Harness: Distilling Black-Box Optimizers from Self-Play
Yi Wu, Zheng Ren, Zhiyu Hu et al. (+8 more)
Can an
agent learn a numerical search strategy through executable practice and then transfer that strategy as text? We study low-budget black-box optimization, where unaided
language models remain well below strong classical optimizers. During development, an
agent repeatedly writes and evaluates optimizer programs. It then distills the resulting program and practice record once into a 197-word primary Harness A, which is frozen before evaluation. Harness A reduces Gemini Flash regret by 48% in an independent $N=30$ study ($p<.001$), enters the GP-BO performance range on the practice family, and lowers mean regret on all three held-out BBOB landscapes. The same text improves every tested Gemini executor and transfers to Claude Sonnet, reducing regret by 43% and 49% ($p\leq.005$). An independent end-to-end replication produces Harness B, a different program and text at the same performance tier. The same framework also attains the lowest regret on a sealed YouTube reward-tuning production
benchmark. Executable practice is thus a viable way to discover a search policy, and
language a portable medium for deploying it.
Read the full abstract ▾
All authors Yi Wu, Zheng Ren, Zhiyu Hu, Haochen Wang, Daryl Chang, Li Wei, Ting Wang, Zhen Li, Pooja Gupta, Nitin Jindal, Lukasz Heldt
Machine Learning
Exact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-Leader
Ashkan Soleymani, Gabriele Farina and Patrick Jaillet
Online gradient descent is usually studied through external regret, where the learner competes with fixed alternatives. Recent work shows that first-order methods control richer action-dependent deviations. We ask for a
geometric characterization of the deviations with respect to which online gradient descent, mirror descent, and follow-the-regularized-leader (FTRL) achieve no regret. We identify exactness as the common principle. Exactness means that the relevant displacement field is generated by a scalar potential, or equivalently that the associated one-form is exact in the geometry used by the
algorithm. This geometry depends on the
algorithm. For gradient descent it is Euclidean geometry, for mirror descent it is the geometry induced by the regularizer, and for FTRL it is the cumulative dual state. Under mild regularity conditions, exactness yields sublinear regret, while nonzero circulation provides the complementary obstruction and leads to linear regret. This gives a unified
geometric framework for understanding the deviation classes controlled by these
algorithms and reveals that different first-order methods can control genuinely different classes of deviations. These deviation classes have direct consequences for learning, particularly in games. We study the
equilibrium notions induced by exact-form deviations and introduce conservative correlated
equilibrium, reflecting both the conservative geometry of the underlying displacement fields and the restricted family of deviations available to the players. We characterize its relation to correlated
equilibrium, determine when the resulting
equilibrium notions coincide and when they separate, and show how these relationships depend on the geometry and the learning
algorithm. Overall, this work gives a unified
geometric account of what first-order online learning
algorithms are no-regret with respect to, beyond fixed comparators.
Read the full abstract ▾
Computers and Society
Democracy Needs Reach: Political Equality, Online Speech, and Algorithmic Recommendation
Etienne Brown
Within democracies, the capacity to influence political outcomes through
speech depends not only on the right to express oneself, but also on the opportunity to reach relevant audiences. In this paper, I argue that the unequal distribution of algorithmic reach on social media platforms undermines equality of opportunity for political influence (EOPI), which is a central democratic ideal. Drawing on Niko Kolodny's work, I contend that current recommendation
algorithms create and perpetuate informal inequalities by concentrating
attention among a small minority of already-amplified speakers while systematically marginalizing others. To address this problem, I propose recommendation floors as a mechanism for equalizing political
speech. To help users achieve meaningful participation, each verified account would receive guaranteed minimum recommendation for up to a limited number of political posts per week. Although this measure represents one component of the structural reforms needed to move the digital public sphere closer to democratic ideals, it offers a feasible pathway to reducing informal inequalities in political influence online.
Read the full abstract ▾
Computer Vision
Tanvir Muntakim Tonoy, Sajjad Ghiasvand, Mahnoosh Alizadeh et al. (+1 more)
Prompt learning adapts CLIP to downstream recognition by replacing hand-written templates with learned continuous context vectors, which in Context Optimization (CoOp) form a dense
prompt matrix $\mathbf{P}\in\mathbb{R}^{m\times d}$ trained from only a few examples per class. We study whether this
matrix is over-parameterized by factorizing it as $\mathbf{P}=\mathbf{B}\mathbf{A}$, which cuts the trainable
prompt parameters from $md$ to $r(m+d)$, and to $rd$ once the
token-side factor $\mathbf{B}$ is fixed. Across seven few-shot
benchmarks and two CLIP backbones, low-rank
prompts match or improve dense CoOp at far fewer parameters, with the clearest gains on low-shot base-to-new generalization. We then find that the
token-side factor need not be learned at all: fixing $\mathbf{B}$ to a Gaussian, orthogonal, SVD-derived, or even random basis and training only the
embedding-side factor $\mathbf{A}$ stays on par with the fully trainable factorization, and a source-trained $\mathbf{B}$ offers no advantage over a random one. A
prompt-factor asymmetry and a local update-space dimension gap show why fixing $\mathbf{B}$ is far less restrictive than fixing $\mathbf{A}$, and a smoothness-only guarantee certifies that optimizing $\mathbf{A}$ over a fixed $\mathbf{B}$ converges. In the CLIP
prompt setting, the
embedding-side coefficients carry the adaptation while the
token basis can simply be fixed.
Read the full abstract ▾
All authors Tanvir Muntakim Tonoy, Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani
Emerging Technologies
OmniEye: Efficient Multimodal Forensic Video Intelligence for Law-Enforcement Body-Worn Cameras
Mamadou K. Keita, Angela Srbinovska, Anita Srbinovska et al. (+12 more)
We introduce OmniEye, a
multimodal video intelligence system for law-enforcement training and review (source code available on request to verified law-enforcement and public-safety agencies). OmniEye ingests body-worn camera footage and perceives every 30-second window jointly across
video and audio with one
multimodal foundation model. It then stores the model's structured output in an embedded SQLite database with BM25 full-text search. Officers can question the footage through an
agent that writes structured queries, retrieves candidate windows, and re-perceives them with the model before it may cite them. The whole system runs on one 16 GB GPU with a 4-bit quantization-aware-trained model, and it also scales to full bf16 precision on a multi-GPU cluster.
Read the full abstract ▾
All authors Mamadou K. Keita, Angela Srbinovska, Anita Srbinovska, Nishka Desai, Isabella Zicari, P. Kwaku Sanaah-Faried, Sanjay Charitesh Makam, Wyatt Auten, Vivek Senthil, Hannah Desnick, Jonathan Bateman, Adrian Martin, Christopher Homan, John McCluskey, Ernest Fokoué
Artificial Intelligence
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance
Praphul Singh, Shanu Kumar, Akshat Agarwal et al. (+1 more)
As LLM
agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks acceptable even though the system skipped the check, branch, dependency, or invariant that made the answer justified. Output-only evaluation sees the answer, and trace-aware judging sees activity, but neither identifies which obligations were active for the query. We introduce CONTRACTEVAL, a diagnostic framework for making those active obligations explicit. It represents procedural instructions as query-active obligations and matches them against response or trace evidence, turning omissions, wrong branches, ordering errors, extra actions, invariant breaches, and output-contract violations into distinct conformance failures. On a controlled suite of audited procedural contracts, output-only and trace-aware LLM judges miss many injected structural failures; under gold expected and observed graphs, ContractEval detects and localizes all of them. LLM-backed extraction preserves much of this signal but remains calibration-sensitive. ContractEval is therefore not a compliance guarantee; it makes procedural conformance auditable rather than implicit in final-answer quality.
Read the full abstract ▾
All authors Praphul Singh, Shanu Kumar, Akshat Agarwal, Ganesh Kumar
Machine Learning · Cross-listed from quant-ph
A Block Tensor Train Burer-Monteiro Framework for Low-Rank Quantum State Tomography
Shakir Showkat Sofi, Charlotte Vermeylen, Fatemeh Mohammadi et al. (+1 more)
Quantum state
tomography is a fundamental technique for estimating the state of a
quantum system from measured data and plays a crucial role in evaluating the performance of
quantum devices. However, standard estimation methods become computationally prohibitive as the system size increases due to the exponential growth of the density
matrix, describing a
quantum state, with the number of
qubits. We propose a low-rank tensor-network framework for mixed-state
quantum state
tomography based on a block tensor train (Block-TT) factorization. Specifically, the density
matrix is represented as the contraction of a Block-TT with its Hermitian transpose, yielding a TT analogue of the Burer-Monteiro factorization. This parameterization guarantees Hermiticity and positive semidefiniteness by construction while compressing the number of optimization variables from exponential to linear in the number of
qubits. Building on this representation, we develop single-site and two-site density
matrix renormalization group (DMRG)
algorithms for estimating
quantum states from compressed measurements. The resulting methods operate directly on the compressed parameterization, support adaptive rank refinement, and exploit efficient tensor-network contractions for expectation-value evaluation. The framework is applicable to a broad class of low-rank
quantum states, including pure states, nearly pure states, and ground states that admit accurate tensor-network approximations. Numerical experiments demonstrate accurate state reconstruction from limited measurements together with substantial reductions in
memory requirements and computational cost compared with conventional low-rank
tomography methods.
Read the full abstract ▾
All authors Shakir Showkat Sofi, Charlotte Vermeylen, Fatemeh Mohammadi, Lieven De Lathauwer
Machine Learning
Uncertainty-Aware Sea-Ice Type Mapping with Multiple Ice Charts
Samira Alkaee Taleghan, Younghyun Koo, Andrew P. Barrett et al. (+1 more)
Sea-ice stage of development (SoD) describes the age and associated thickness of sea ice and provides important information for
navigation, and operational ice monitoring. SoD labels are obtained from operational ice charts, where trained analysts interpret satellite observations and assign standardized stage codes to regions with similar ice conditions. These codes often represent ranges of compatible ice thicknesses rather than exact physical values. Deep-learning methods can automate SoD mapping and commonly adopt operational ice charts as reference labels for training. These annotations are not exact, however; this is because chart interpretation relies on analyst judgement and on the observations available at the time, so different ice services may assign different SoD labels to the same conditions. We term this variation across independently produced expert annotations multi-annotator label uncertainty; collapsing the annotations into a single deterministic target discards this variation. A second source of uncertainty originates in the learned model itself. In this paper, we quantify both sources: annotation uncertainty from disagreement among independent ice-service charts and model uncertainty from the learned predictive models. We then evaluate their relationship by testing whether model uncertainty is higher where ice services disagree. We observe that supervision incorporating information from multiple annotators can improve this correspondence, with soft supervision achieving the highest overall correlation of 0.256. The relationship becomes substantially stronger near the ice edge, where model predictive uncertainty closely tracks multi-annotator disagreement, reaching a correlation of 0.704 within 0–10 km. Among the uncertainty-estimation approaches, Monte Carlo dropout provides the best-calibrated confidence estimates, with an expected calibration error of 0.050.
Read the full abstract ▾
All authors Samira Alkaee Taleghan, Younghyun Koo, Andrew P. Barrett, Farnoush Banaei-Kashani
Systems and Control
Data-driven design of steady-state feedforward inputs for nonlinear systems under partial measurement
Sathya Aswath Govind Raju, Berk Altiner, Zongxuan Sun et al. (+4 more)
Designing trajectory tracking controllers for nonlinear systems remains a significant challenge, traditionally requiring precise mathematical models and complex analytical derivations. While the Internal Model Principle (IMP) provides a robust theoretical foundation for such problems, its application is often hindered by model uncertainty and the inherent complexity of nonlinear controller synthesis. This work proposes a practical data-driven control framework that bypasses the need for an explicit first-principles model by utilizing raw input-output data. By integrating fundamental results from IMP theory with nonlinear system analysis, the proposed approach improves design tractability. The framework's efficacy is validated through numerical simulations on two distinct nonlinear platforms: a mechanical load with a nonlinear friction term and an electrohydraulic actuator system.
Read the full abstract ▾
All authors Sathya Aswath Govind Raju, Berk Altiner, Zongxuan Sun, Arunava Banerjee, Rajasree Sarkar, Kenneth Kim, Chol-Bum Mike Kweon
Artificial Intelligence
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
Priyanka Mary Mammen, Emil Joswin and Srujananjali Medicherla
As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to the traditional machine learning systems, agentic workflows have complex failure modes with planning, tool invocation and dynamic environment interactions. In this paper, we investigate whether model's internal representations provide stronger signals of eventual task success in multi-turn agentic setups. We introduce two complementary methods: Latent Trajectory Dynamics (LTD), which summarizes changes in residual-stream representations across an interaction trajectory, and the Action Representation Probe (ARP), which predicts success from representations formed at action decisions. Across three interactive
benchmarks (Bash, SQL, Python) and three model families (Qwen14B, Qwen7B, DeepSeek6.7B), our methods consistently outperform surface level generation and sequence-based calibration baselines providing a zero-overhead reliability monitor that requires neither
prompt alterations nor multi-sample rollouts.
Read the full abstract ▾
Human-Computer Interaction
"It's Like Drinking from a Fire Hose": Understanding and Characterizing Video Learning Experiences for Individuals with ADHD
Hanxiu 'Hazel' Zhu, Weiyu Zhang, Ru Wang et al. (+1 more)
Video lectures have become increasingly prevalent for education and professional development, yet their static visuals, dense information, and long duration pose attentional challenges for individuals with ADHD. While adaptive learning offers opportunities towards ADHD-accessible
video learning, little is known about how to suitably adapt such
videos: What components in
multimodal video lectures are challenging for ADHD viewers? How do these experiences surface in behavioral signals to trigger an adaptation? What presentations do they prefer? To answer these questions, we conducted an eye-tracking-based retrospective think-aloud study with 16 participants with ADHD, who watched and reflected on a curated set of
video lecture segments. Our study uncovered
video design elements that hindered learning and revealed participants' coping strategies along with their limitations. By jointly analyzing behavioral signals and retrospective reflections, we characterized how these experiences manifested in behavioral patterns. We further surfaced participants' practices for addressing learning needs beyond the
video watching process, and derived design implications for future ADHD-friendly adaptive
video learning systems.
Read the full abstract ▾
All authors Hanxiu 'Hazel' Zhu, Weiyu Zhang, Ru Wang, Yuhang Zhao
Cryptography and Security
Concept drift mitigation through community and spectral graph analysis for the detection of cyberattacks in network traffic
Julien Michel, Abdul Qadir Khan, Majed Jaber et al. (+1 more)
In network traffic, legitimate behaviours and attack techniques evolve jointly - the phenomenon known as 'concept drift' [1]. Every detector is thereby left obsolete between two updates, and always one step behind adversaries. In this work, we propose to move the point of intervention from the model, repaired after the drift, to the feature space, selected before learning. We therefore introduce t-robustness, a stability score defined for each feature independently of any detection model, comparable across an entire feature space. It combines the step-by-step distance between successive statistical states of a feature, and its cumulative divergence from its initial state, so that a slow monotonic drift cannot pass for stability. The candidates are drawn from abnormal network connectivity patterns left by scans, DoS and communications between endpoints, read through graph community metrics and spectral metrics. The evaluation is performed on the UGR16
dataset, across three learning scenarios and a control scenario, as well as without model update, and demonstrate that t-robust feature spaces sustain detection where the baselines collapse: retained expectancy at the last test interval reaches 0.6025, against 0.5230 for graph community features and 0.3831 for the base NetFlow features.
Read the full abstract ▾
All authors Julien Michel, Abdul Qadir Khan, Majed Jaber, Pierre Parrend
Logic in Computer Science
Fast Constraint Extraction for Corrective Control under STL Specifications via Logical Dependency Tracking
Antoine Besset, Joris Tillet, Chuchu Fan et al. (+1 more)
Ensuring the satisfaction of Signal Temporal Logic (STL) specifications under uncertainty is challenging, as reachability-based monitoring provides guarantees but does not indicate how to restore satisfaction when it becomes indeterminate. A key difficulty is identifying which uncertain components actually affect global satisfaction, especially for nested formulas. This paper introduces a logical dependency tracking framework that propagates uncertainty through the STL structure and captures the causal contribution of reachable sets to satisfaction. By associating markers to uncertain predicates and propagating them via three-valued semantics, we extract in milliseconds a compact Disjunctive Normal Form (DNF) of sufficient constraints, avoiding combinatorial enumeration. As an application, we formulate control correction as a minimum-effort optimization problem. Using zonotopic reachability, the derived constraints are enforced via linear programming, yielding corrections that guarantee STL satisfaction under bounded uncertainty and provide certified probabilistic bounds in the
stochastic case. We demonstrate the approach on a nonlinear system with nested STL specifications, showing that dependency tracking enables efficient and formally guaranteed correction. The tracking implementation is available at https://github.com/Antoine-Bst/STL-Three-Valued-Clause-Filtering/.
Read the full abstract ▾
All authors Antoine Besset, Joris Tillet, Chuchu Fan, Julien Alexandre dit Sandretto
Machine Learning · Cross-listed from math.ST
MiNCE: Nonparametric, Strongly Consistent Confidence Envelopes for Band-Limited Functions and their Smoothed Spectra
Balázs Csanád Csáji and Bálint Horváth
Minimum-norm confidence envelope strategies offer a nonparametric approach to constructing nonasymptotic, simultaneous confidence regions for band-limited functions, exploiting the theory of Reproducing Kernel
Hilbert Spaces (RKHS). While the finite-sample coverage guarantees of these envelopes have been established, their consistency has not been analyzed so far. In this paper, we study this construction, here termed the Minimum-Norm Confidence Envelope (MiNCE) framework, and establish the strong uniform consistency of the resulting bands, both for noise-free and noisy observation models, under mild assumptions on the measurement noises. We further extend this formulation to the frequency domain, deriving nonasymptotic, simultaneous, strongly uniformly consistent confidence bands for the smoothed spectra. Numerical experiments in nonparametric regression and spectral estimation empirically confirm our theoretical results, illustrating the contraction of the confidence envelopes toward the target function as the sample size increases.
Read the full abstract ▾
Machine Learning
Tensor-Train Weak SINDy: Identifying High-Dimensional Nonlinear Dynamics
Will Houser, Vanja Dukic and David M. Bortz
Weak Sparse Identification of Nonlinear Dynamics (WSINDy) provides a noise-robust approach for learning dynamical systems from data without requiring numerical differentiation. However, for high-dimensional systems, tensor-product libraries of candidate functions grow exponentially with the state dimension, making standard WSINDy expensive in both computation and
memory. The Multidimensional Approximation of Nonlinear Dynamics (MANDy) addresses this scaling through a tensor-train (TT) representation of the candidate library, but does not provide a mechanism for sparse model selection. Here, we combine these approaches to develop TT-WSINDy, which performs the weak-form transformation, regression, and sparsification in TT format. We show that the TT formulation recovers the corresponding WSINDy regression problem and derive
polynomial time and
memory complexity bounds for the tensor-train sparsification procedure. Numerical experiments demonstrate robustness to measurement noise and computational savings for high-dimensional systems.
Read the full abstract ▾
Machine Learning
Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
Heinke Hihn
Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain
dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.
Read the full abstract ▾
Machine Learning
SCCM : Stream Cruise Control Method for Automated Drift Detection and Adaptation
Mohammad Abu-Shaira and Weishi Shi
Real-world
datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixed hyperparameters further limits model adaptability under changing conditions. Adaptive learning addresses this challenge by continuously updating models online, allowing them to incrementally adjust and remain effective as data distributions evolve. This paper presents the Stream Cruise Control Method (SCCM), a comprehensive framework for drift detection and adaptation in online regression. SCCM enables automated adaptation through early-response, pre-update drift detection, drift magnitude quantification, KPI-window-based thresholding for local false-alarm mitigation, dynamic hyperparameter tuning, and model recalibration. SCCM also adopts an in-
memory design for real-time adaptability, unlike purely reactive methods that typically activate adaptation only after performance degradation is observed. By using dynamic thresholding and remaining agnostic to data distributions, SCCM supports KPI-based monitoring across varying data streams, including high-dimensional and large-scale settings. SCCM is integrated with four online regression models and evaluated on 18 synthetic
datasets covering abrupt, incremental, and alternating gradual drift, together with eight real-world
datasets. The evaluation uses both R2 and MSE and compares against eight detector–adaptation baselines. Results show improved predictive performance and effective drift handling across the evaluated online regression settings.
Read the full abstract ▾
Machine Learning
Applying foundation model embeddings towards urban livability evaluation
Ayush Khot, Wen Zhou and Shaowen Wang
While accurate measurement of socioeconomic indicators remains challenging in data-scarce regions, which limits policy interventions and resource allocation, high-resolution geospatial data is widely available and can contain information on various livability statistics. We investigate which physical features are encoded within foundation model
embeddings, such as AlphaEarth, AnySat, and TerraMind, and provide a systematic framework for identifying the most predictive geospatial indicators. By analyzing how different types of geospatial data influence urban livability predictions, our approach enables researchers to prioritize the most informative features for their specific applications. Additionally, we demonstrate how to leverage foundation model
embeddings to enhance prediction performance for these outcomes. This work contributes a principled methodology for extracting actionable information from satellite imagery while accounting for complex spatial dependencies, with applications in predicting urban livability in regions with limited observation data.
Read the full abstract ▾
Artificial Intelligence
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein et al. (+1 more)
Evaluating the quality of explanations produced by explainable AI (XAI) methods remains challenging because existing approaches often rely on subjective human judgment, limiting reproducibility, scalability, and comparability between studies. We examine whether LLMs can serve as a reproducible and scalable mechanism to make comparative assessments of the quality of XAI explanations. We introduce XAI-Arena, an LLM-as-a-judge framework for scalable, reproducible, multidimensional, and stakeholder-sensitive evaluation of XAI explanation quality. XAI-Arena then allows us to compare XAI explanations along various dimensions, namely, perceived simplicity, clarity, task adequacy, trust calibration, actionability, transparency, faithfulness, and overall interpretability. We then
benchmark XAI explanation methods across various
datasets, machine learning models, and stakeholder personas. Human validation shows a strong positive association between LLM-generated and human ratings (Spearman's rho=.693, p<.001). Together, LLM-based evaluations can capture systematic differences in XAI explanation quality and provide a scalable and reproducible framework for comparative assessment of XAI explanations.
Read the full abstract ▾
All authors Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein, Stefan Feuerriegel
Data Structures and Algorithms
Approximate Nearest Neighbor in Ultra-High Dimensional $\ell_\infty$
Nathan White and Tian Zhang
We study the approximate nearest neighbor problem under $\ell_\infty$ in the ultra-high dimensional setting where the dimension $d$ is significantly larger than the number of points $n$. Thus, we desire data structures with no dependence on $d$ in the query time. [Herold-Nanongkai-Spoerhase-Varma-Wu, SoCG 2025] introduce this problem and give data structures in $\ell_p$: for $p=1,2$, they give $(1+\varepsilon)$-approximation data structures with space $\tilde{O}(n\log d/\text{poly}(\varepsilon))$ and query time $\tilde{O}(n/\text{poly}(\varepsilon))$. Since any data structure must have query time $\Omega(\min \{n,d\})$, this query time is nearly tight. However, their results are inefficient for $\ell_\infty$, with query time $\Omega(nd)$. In order to handle the challenges of $\ell_\infty$, we introduce a notion of subset
embeddings, which embed points by simply selecting a subset of dimensions. In particular, we show one may preserve all pairwise distances of an $n$ point
dataset up to a factor of $O(c)$ by computing distances on only $n^{1+1/c}$ coordinates. We also show a matching lower bound: for any $c > 1$, there exists a set of $n$ points in $\mathbb{R}^{d}$ such that any subset
embedding for the set with approximation $c$ must have at least $n^{1+\Omega(1/c)}$ coordinates. Using our subset
embeddings, we give data structures for approximate nearest neighbor in $\ell_\infty$ with space $O(n^2\log d)$, query time $\tilde{O}(n^{1+1/c})$, and approximation $O(c\log\log n)$ for any $c \geq 1$. Finally, we give another data structure for the approximate nearest neighbor under $\ell_\infty$ with the same space and query time as our subset
embedding approach, but with approximation $O(c^{\log_2 3}) \approx O(c^{1.58})$. This allows us to achieve $O(1)$-approximation with query time e.g.~$n^{1.01}$
Read the full abstract ▾
Computation and Language
Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements
Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu et al. (+6 more)
Educational data filters have become a practical way to improve
language-model pre-training, but most filters treat educational value as a single scalar property. This may be too broad for some applications, especially if the data set already features a high density of educational material. Useful learning material needs to be accurate, engaging, well structured, and appropriate for the intended audience and application (e.g. learner- vs teacher-facing). Following QuRating (Wettig et al. 2024), we introduce Edu-QuRating: a pipeline for multi-dimensional educational data scoring and curation. Edu-QuRating defines education-specific rubrics, uses an LLM judge to label sampled document pairs and distills those pairwise preferences into reusable Edu-QuRaters, which can score individual text chunks on a set of educational criteria. Across two sequence-classification base models and six educational criteria, the best Edu-QuRater recovers held-out GPT-4.1-mini pairwise judgements with mean accuracy 0.917. We then apply the resulting scorers in two applications. First, we investigate the potential of Edu-QuRaters for corpus filtering to improve pretraining of small
language models. We scored 322.25M FineWeb-Edu-Fortified documents to obtain a filtered pre-training mixture. In matched single-run pre-training comparisons, models trained with Edu-QuRating-based mixtures reached higher observed aggregate accuracy across nine
benchmarks than the FineWeb-Edu baseline, with gains concentrated in particular tasks. Second, we used Edu-QuRater scores as reward terms for GRPO post-training. In held-out pairwise judge evaluations, combining Edu-QuRater and answer-structure rewards produced responses preferred to the Qwen3-4B base model on both pedagogical quality and instruction following.
Read the full abstract ▾
All authors Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu, Mohamed Huti, Moritz Boos, Amy Waldock, Dominic Andrews, Romana Alonso-Kropil, Paul Atherton
Computer Vision
Longitudinal tracking of multiple sclerosis lesions in the spinal cord: A validation study
Pierre-Louis Benveniste, Julian McGinnis, Shannon Kolind et al. (+11 more)
Longitudinal characterization of multiple sclerosis (MS) lesions remains constrained by the lack of frameworks capable of establishing consistent instance-level correspondences across time. Conventional
segmentation approaches produce semantic lesion masks at each visit and therefore fail to capture the complex instance temporal patterns associated with lesion appearance, disappearance, splitting, or merging. This study presents a comparative evaluation of five strategies for automated tracking of spinal cord MS lesions in longitudinal MRI data from a multi-site cohort. The investigated strategies rely either on deformable registration or on a spinal anatomical reference system, and encompass overlap-based matching, coordinate-based Hungarian
algorithm, gradient-boosted classification, and Siamese model classification. Tracking accuracy is quantified using instance-level true positives, false positives, and false negatives, allowing to assess the presence of one-to-many and many-to-one associations. Results show best performance for the registration-based overlap method. This study provides the first systematic analysis of lesion-instance correspondence in the spinal cord and outlines the strengths and limitations of registration-based and registration-free paradigms for longitudinal MS assessment. The code is available at http://github.com/ivadomed/longitudinal-sc-ms-lesion-tracking .
Read the full abstract ▾
All authors Pierre-Louis Benveniste, Julian McGinnis, Shannon Kolind, Larry D. Lynd, Sarah A. Morrow, Jiwon Oh, Alexandre Prat, Alice Schabas, Penelope Smyth, Roger Tam, Anthony Traboulsee, Mark Mühlau, Herve Lombaert, Julien Cohen-Adad
Cryptography and Security
FPGA Acceleration of Fully Homomorphic Encryption with Adaptive Key Switching
Zhihan Xu, Jayashree Adivarahan, Rajgopal Kannan et al. (+1 more)
Fully Homomorphic Encryption (FHE) enables
privacy-preserving cloud services but incurs substantial computation overhead, making hardware acceleration essential. Among FHE operations, key-switching is a major performance bottleneck. Recent cryptographic advances introduce a novel key-switching method (i.e., KLSS) that reduces certain operational complexity but demands higher computational precision than the traditional Hybrid Key Switching (HKS) method. This trade-off leads to distinct computation and
memory requirements, making the relative latency of KLSS and HKS highly dependent on hardware parallelism, FHE security parameters, and available on-chip
memory capacity, particularly on FPGA platforms, where
memory resources and parallelism must be carefully balanced. In this work, we first propose a
memory-efficient KLSS datapath that eliminates off-chip ciphertext transfers. We then develop a performance model to analyze and compare the overheads of both KLSS and HKS. Our analysis reveals that an adaptive solution supporting both methods can achieve lower overall latency than a static method during FHE computation. Guided by the performance model, we design an adaptive FPGA-based FHE accelerator that dynamically selects between HKS and KLSS during computation. We implement the accelerator on an Alveo U280 and evaluate it across multiple FHE
benchmarks. Experimental results demonstrate that our adaptive solution achieves a 1.84-3.31$\times$ speedup in bootstrapping latency and a 1.66-2.52$\times$ speedup in secure image classification compared to state-of-the-art FPGA accelerators.
Read the full abstract ▾
All authors Zhihan Xu, Jayashree Adivarahan, Rajgopal Kannan, Viktor K. Prasanna
Cryptography and Security
DuplexJail: Spoken Interruption Attacks on Full-Duplex Speech Models
Jaechul Roh, Deepak Chandran, Amir Houmansadr et al. (+1 more)
Full-duplex
speech models accept user
speech while generating responses, making input timing a potential safety concern. We introduce DuplexJail, which delivers fixed, request-independent spoken jailbreak
prompts through the user audio channel. Across four open-source models and 720 harmful requests from AdvBench and HarmBench, we compare fixed-delay and refusal-triggered interruption with request-end and post-response controls. On AdvBench, Guided Completion at a 1.0 s delay raises whole-response attack success rates to 40.3% for PersonaPlex and 48.7% for PersonaPlex-RL, increases of 33.8 and 39.3 percentage points over baseline. On HarmBench, which was not used for
prompt selection, the same
prompt at a 0.5 s delay increases ASR by 14.7 and 12.3 points, respectively. Effects vary across models: selected conditions increase FLM-Audio's harmfulness, while BayLing-Duplex shows decreases. These results show that spoken-jailbreak effectiveness depends on delivery timing and motivate safety evaluation across stages of full-duplex interaction.
Read the full abstract ▾
All authors Jaechul Roh, Deepak Chandran, Amir Houmansadr, Andrea Fanelli