Robotics
Timely Activation of Safety Filters via One-Step Reachability Expansion
Javier Borquez
Least-restrictive safety filters based on Hamilton-Jacobi reachability provide strong safety guarantees by overriding a nominal controller only when the system reaches the boundary of the set of unsafe states defined as a Backward Reachable Tube (BRT). These guarantees, however, rely on the continuous-time nature of the underlying formulation. In practice, robotic systems apply control at discrete sampling intervals, which creates a mismatch where the system may jump into the unsafe BRT between updates, allowing failures that are theoretically avoidable. This work introduces a principled solution based on a one-step expanded BRT that predicts all states capable of reaching the true BRT within a single timestep. By using this expanded boundary as the activation condition for the safety filter, safety interventions occur early enough to ensure correctness under discrete-time execution. We formulate this expanded set as a modified reachability problem and compute it using standard continuous-time solvers.
Read the full abstract ▾
Emerging Technologies
Composability rather than computation sets the cost of an analog EML hardware fabric
C. Teuscher
The operator eml(x, y) = exp(x) - ln(y) with the constant 1 generates the elementary functions, a continuous counterpart to NAND. Whether it yields a useful fabric had not been asked of hardware. We ask in network models,
circuit simulation and SkyWater 130 nm layout. Four bipolar junctions evaluate the operator for 13 fJ, beating a width-matched digital datapath by 4-134x. The fabric assembled from them is not cheap: it loses to resource-matched baselines, and over the reals its grammar excludes trigonometry. Amplifiers holding those junctions' operating points take 74.5% of a
cell's current, so a
cell costs 3000 times what they spend. Extracted non-idealities cost 2.6x when a
cell must hold a value and nothing when it need only be repeatable. Sharing them across
cells recovers two of the three orders. The premise was that a universal primitive licenses a uniform machine. It survives in the primitive and fails in the machine.
Read the full abstract ▾
Cryptography and Security
Ghost-Filled Orders: Detecting and Testing Atomicity Violations in Non-Custodial Prediction Markets
Zhiyang Chen, Fan Long and Zhendong Su
Blockchain based prediction
markets combine offchain order management with onchain settlement. This architecture supports user controlled custody, since users keep funds in wallets or smart contracts while submitting signed orders to an offchain order book. However, it creates an atomicity gap. An order may be valid when accepted or matched offchain, but become invalid before the corresponding onchain settlement transaction is executed. This behavior, often called ghost filled orders by the community, can cause trades that appear filled offchain to fail onchain. This paper studies this atomicity gap through a case study of Polymarket. We show how the delay between offchain order acceptance and onchain settlement allows adversaries to invalidate unfavorable orders after observing
market outcomes or price movements. We then quantify the scale and financial impact of this behavior over a nine-month period from August 12, 2025, to May 22, 2026, using 1.8 million reverted transactions involving Polymarket official smart contracts. Our analysis separates attacker profit from
market and user loss, and develops conservative measurement rules to avoid overclaiming impact. We further develop a methodology for testing other blockchain based prediction
markets and apply it to three additional
markets. We find that all three are vulnerable to the same class of attack, and that one design enables direct attacker profit. We have reported the findings to all three projects; one project had acknowledged the issue at the time of the study.
Read the full abstract ▾
Machine Learning
Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds
Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov et al. (+3 more)
Generative modeling of time-dependent data is typically formulated on a discrete temporal grid, restricting supervision to the observed timestamps in the training data. We instead frame generation as continuous-time
evolution on a learned data
manifold. To this end, we leverage pretrained score-based models as
geometric priors and learn a vector field that evolves data along score-induced interpolation paths. Because these dynamics follow transitions that respect the geometry learned by the score model, they support generation at arbitrary timestamps and temporal super-resolution beyond the discretization of the training data. Moreover, this
geometric formulation allows us to train the vector field simulation-free through a regression objective. To improve long-horizon rollout robustness, we introduce an objective that promotes path-relative transverse exponential stability. While motivated by stability theory, it admits a practical interpretation as denoising score matching transverse to the interpolation path. Further, we extend the framework to a probabilistic setting that models a distribution over plausible future trajectories. We demonstrate the method on natural
video and scientific dynamical data, including temporal super-resolution, PDE-based spatiotemporal fields, and molecular dynamics. Our results show that score-based priors provide a strong foundation for learning
stochastic continuous-time generative dynamics.
Read the full abstract ▾
All authors Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov, Andreas Dengel, Andrew B. Duncan, Sebastian J. Vollmer
Cryptography and Security
When AI Agents Meet MEV: Cross-Chain Arbitrage in the Agentic Economy
Wei Ye, Jingyan Xu and Yuanhong Wu
We study cross-chain arbitrage when autonomous AI
agents, rather than humans or bots, are the searchers. We model
agents as both arbitrage extractors and Maximal Extractable Value targets, derive the optimal trade size for a risk-averse
agent under mean-variance utility with
stochastic bridge delays, and formalize multi-chain path selection as a belief-weighted online learning problem whose belief estimates converge under a Robbins-Monro schedule. Using 23,000 Uniswap V3 swap events across Ethereum, Arbitrum, and Base, we find that Ethereum-Arbitrum price gaps average 0.044% at 10-second resolution and Arbitrum–Base gaps average 0.013%, so $10,000 trades clear in 63% of L2-L2 windows via CCTP while L1-L2 routes require $50,000 or more for comparable viability. Our adaptive path-selection
algorithm outperforms standard baselines by 11% on average, and moderate randomization cuts MEV exposure by over 50% with only modest profit loss.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
QEMScore: How Much Does the Measurement Add to Learned Quantum Error Mitigation?
Yue Zhao, Huayue Gu, Yushun Dong et al. (+1 more)
How much does the noisy measurement add to learned
quantum error mitigation? An accuracy table cannot say, because a model handed
circuit structure can score well without reading the measurement at all. QEMScore adds the comparison that can. Each simulated
circuit carries an exact ideal answer. The learned mitigator is scored beside a capacity-matched control, a model just as flexible that reads the same
circuit description but never the measurement. Each method's measurement spend is accounted and not equalized. We run a controlled campaign on simulated
circuits and reanalyze two published learned mitigators, Q-LEAR and QRAFT, from their released hardware data. Three findings stand out. First, under familiar within-family conditions (S0) evaluated across two
spin-chain families and three seeds, continuous couplings identify the target, and the control that never reads the measurement matches 87.7 to 100.5 percent of the mitigator's gain over an affine fit to the
circuit description. A plain
polynomial in the coupling parameters, fitted after the campaign, beats the mitigator on all six evaluations, reflecting the selected learners' capacity. Second, for these selected learners, matching most of the gain is not matching the accuracy: on five of six evaluations the mitigator removes 19.5 to 74.5 percent of the error the capacity-matched control leaves, a learner-specific gap rather than a measurement requirement. Third, on released hardware data where descriptors only partially identify queries, the findings differ: flexible models of the descriptors show negligible mean gain over affine fits in Q-LEAR, and measurement inputs carry predictive gains in both Q-LEAR and QRAFT. These comparisons reflect representation- and protocol-specific behavior rather than an isolated cross-regime difference. A learned mitigator's accuracy should therefore be reported beside such controls.
Read the full abstract ▾
All authors Yue Zhao, Huayue Gu, Yushun Dong, Xiyang Hu
Machine Learning
TabPFN-3.5: Technical Report
Benjamin Jäger, Nick Erickson, Léo Grinsztajn et al. (+44 more)
We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines across a broad range of tabular problems. TabPFN-3.5 sets a new state of the art on standard tabular prediction in TabArena, and extends it to the data practitioners encounter in practice: non-i.i.d. data with temporal or grouped splits, tables with strings, text and images, high-cardinality categorical features, and wide tables with many features. These gains carry over to our task-specific harnesses: state of the art on relational data and stronger time-series
forecasting. For faster inference, our variant TabPFN-3.5-Fast runs up to 3x faster than TabPFN-3 while keeping most of the accuracy gains. In addition, we upgrade TabPFN-3.5-Plus, expanding our
multimodal capabilities with advanced text and date handling alongside proprietary inference optimizations. Finally, we release a new version of our Thinking mode, TabPFN-3.5-Thinking, which scales inference-time computation to push the state of the art further. It benefits from our stronger base model and from inference-time improvements that make it up to 12x faster than TabPFN-3-Thinking.
Read the full abstract ▾
All authors Benjamin Jäger, Nick Erickson, Léo Grinsztajn, Felix Birkel, Klemens Flöge, Oscar Key, Kürşat Kaya, Jonas Kübler, Adèle Frankel, Tobias Schröder, Anurag Garg, Jan Hendrik Metzen, David Salinas, Simon Bing, Kristina Collins, Tuana Çelik, Vahid Balazadeh, Lydia Sidhoum, Tomás Pereda, Brendan Roof, Andrej Tschalzev, Siyuan Guo, Philipp Singer, Lennart Purucker, Jake Robertson, Marie Salmon, Philipp Jund, Jerry Chen, Diana Kriuchkova, Arthur Cahu, Eliott Kalfon, Adrian Hayler, Georg Grab, Vitor Monteiro, Lilly Wehrhahn, Dominik Safaric, Clara Cornu, Alan Arazi, Rylee Grace, Simone Alessi, Mihir Manium, Bernhard Schölkopf, Yann LeCun, Madelon Hulsebos, Sauraj Gambhir, Noah Hollmann, Frank Hutter
Neural and Evolutionary Computing · Cross-listed from astro-ph.IM
Graph neural networks for exoplanet atmospheres
Antonia Vojtekova, Kai Hou Yip, Ingo P. Waldmann et al. (+4 more)
Calculating disequilibrium chemistry in
exoplanet atmospheres remains a significant computational bottleneck in atmospheric
retrievals. The increasing observational precision from facilities such as JWST and the Ariel mission requires including disequilibrium chemistry in these analyses. Previous studies have demonstrated that neural networks can emulate kinetic chemistry, although their spatial inductive bias does not align with the
topology of chemical reaction networks. This study introduces a graph neural network surrogate that represents chemical species as nodes and temperature-dependent reaction rates as edges, thereby enabling information propagation along physically meaningful chemical pathways. The model is trained on atmospheres generated using the Venot+2020 chemical scheme and Guillot temperature-pressure profiles. The GNN accurately reconstructs disequilibrium abundances across the sampled parameter space and reduces the mean abundance error by a factor of approximately 3 compared to the previous U-Net model. When applied to transmission spectra, most predictions fall within the observational precision expected for JWST and Ariel, with only about 7% of test atmospheres exceeding a 20 ppm mean spectral error. Performance variations are primarily observed in chemically transitional regimes near a carbon-to-oxygen ratio of one and at low temperatures. An evaluation of the boundary-case
planet WASP-39b demonstrates effective performance under a moderate domain shift. Perturbation analysis indicates that disturbances propagate along chemical connectivity rather than spatial adjacency, confirming that the architecture captures the structure of reaction networks. These results suggest that GNN surrogates provide accurate, computationally efficient predictions of disequilibrium chemistry, facilitating integration into the atmospheric
retrieval pipeline.
Read the full abstract ▾
All authors Antonia Vojtekova, Kai Hou Yip, Ingo P. Waldmann, Nikolaos Nikolaou, Olivia Venot, Ahmed Faris Al-Refaie, Bruno Merín
Machine Learning · Cross-listed from stat.ML
Bracketing Uncertainty in Clustering Under the Manifold Hypothesis
Savik Kinger, Luciano Dyballa and Steven W. Zucker
The
manifold hypothesis suggests a natural criterion for clustering: partition data according to the
manifold component from which each point is drawn. Whether two components are separable depends on a
geometric tradeoff: the ambient separation between components versus the largest gap in sampling. In practice, this tradeoff is rarely assessed explicitly, leading standard methods to over-commit to a single clustering assignment even when the data do not support a unique answer. We formalize this tradeoff by combining intrinsic
manifold geometry (volume growth and reach) with sample-level quantities (fill distance and density), yielding a threshold phenomenon for mutual-$k$-nearest-neighbor graphs: when the offset-to-fill ratio exceeds a conservative upper threshold, component separation is preserved; below a lower threshold, components fuse. The gap between these thresholds defines a
geometric uncertainty zone in which the number of clusters is not identifiable from the data. Nevertheless, conventional approaches still seek one: sweeping parameters (an engineering approach) or fitting a generative mixture model (a model-based approach). Rather than forcing a single estimate of the number of clusters, we propose
Manifold-Based Clustering (MBC), which returns an explicit bracket interval to quantify the underlying data uncertainty. This bracket acts as an empirically calibrated diagnostic: it narrows when a single resolution is supported, widens when multiple resolutions coexist, and collapses to one when no separated structure is detectable. Empirically, we find that many real
datasets lie within the uncertainty zone rather than admitting one clear answer. Our results suggest that ambiguity in cluster number is often intrinsic, and should be quantified rather than resolved.
Read the full abstract ▾
Discrete Mathematics
Structural Parameterizations for Eternal Vertex Cover
Neeldhara Misra, Sebastian Ordyniak, Giacomo Paesani et al. (+1 more)
Eternal Vertex Cover (EVC) is a turn-based attacker-defender game on an undirected graph $G$. To begin with, the defender places $k$ guards on vertices of $G$. The attacker, on their turn, can choose an edge $e$ not already occupied at both endpoints to "attack". The edge $e$ is defended if a guard moves along the edge $e$. The defender, on their turn, can move any subset of guards. A guard can only move to a neighboring vertex. The minimum number of guards needed to indefinitely defend against any sequence of attacks is called the eternal vertex cover number, generalizing the classic vertex cover number. Determining this number is NP-hard in general, motivating the study of parameterized and approximation
algorithms. The problem is known to be FPT when parameterized by the cover number, but structural parameters remain relatively unexplored in the literature. In this work, we explore structural parameterizations for EVC. We show that EVC is FPT parameterized by the cluster vertex deletion number, which generalizes the previously studied parameterization by vertex cover number. We next study the problem parameterized by vertex integrity, which is the smallest number of vertices we need to delete from $G$ so that the resulting graph is a disjoint union of constant-sized components. We first show that Eternal Vertex Cover is XP parameterized by vertex integrity. Then, we develop a
polynomial-time approximation
algorithm, which computes an additive $6k+1$ ($g(k)$) approximation, where $k$ is equal to the cluster vertex deletion number (vertex integrity). Finally, we show a FPT
algorithm for when the deletion set produces "nice" connected components, which are components that are bounded in size and satisfy a technical condition.
Read the full abstract ▾
All authors Neeldhara Misra, Sebastian Ordyniak, Giacomo Paesani, Mateusz Rychlicki
Artificial Intelligence
OBC-Prune: Outcome-Based Calibration for Large Reasoning Model Pruning
Ha Lan Nguyen, Huy Hoang Tran, Trac-Duy Tran et al. (+1 more)
Large
reasoning models (LRMs) generate long chain-of-thought traces before answering, creating significant inference overhead.
Pruning can reduce this cost, but its effectiveness depends on the calibration data used to estimate parameter importance. Recent work calibrates on the model's own rollouts instead of generic
dataset, but treats all
reasoning tokens uniformly, regardless of whether they contribute to successful
reasoning. As a result,
pruning protects weights by statistical salience rather than by their contribution to correct
reasoning, so weights behind erroneous computation survive as readily as those behind correct computation. These erroneous patterns then get carried into the pruned model, degrading
reasoning quality, producing both lower accuracy and longer
reasoning traces. We propose Outcome-Based Calibration for Large
Reasoning Model
Pruning (OBC-Prune) to close this gap. OBC first constructs difficulty-matched pairs of correct and incorrect rollouts from problems the model answers inconsistently. It then estimates the causal importance of each
reasoning sentence through intervention-based analysis, quantifying how removing its influence affects subsequent predictions. These causal importance scores are converted into per-
token weights that rescale the calibration activations used by one-shot
pruning methods (SparseGPT, Wanda, ALPS), without modifying the underlying
pruning algorithms. Experiments on DeepSeek-R1-Distill-Qwen 1.5B, 7B, and 14B models at 40% and 50% sparsity demonstrate consistent improvements over state-of-the-art calibration baselines across most model sizes and sparsity levels on MATH500, LiveCodeBench, and AIME 2025. These results indicate that preserving causally important
reasoning circuits is a substantially more effective
pruning objective than uniformly preserving observed activations.
Read the full abstract ▾
All authors Ha Lan Nguyen, Huy Hoang Tran, Trac-Duy Tran, Dung D. Le
Machine Learning
Long-Context Demonstration Selection Using State Space Models
Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong et al. (+2 more)
We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a
language model. This problem is closely related to in-context learning and
language model inference. Since the inference cost of a
transformer model scales quadratically with sequence length, the selection problem becomes especially challenging in a long-context scenario. In this paper, we tackle this problem by building on state space models (SSMs), which require only linear inference time given the input. Our approach involves two
algorithms. The first learns a small set of SSMs through
distillation of a (trained)
transformer model. We partition all the layers into consecutive groups. Then for each group, we estimate a separate state space model to replicate the input-output behavior within the adjacent layers. Second, we map the distilled model outputs to a small set of
tokens, and apply these
embeddings for demonstration selection in downstream applications. We perform extensive experiments in both synthetic and real-world
datasets to validate our approach. We demonstrate that the distilled SSMs only incur an approximation error of less than $0.7\%$ relative to the true output. In downstream evaluation, we show that on several text classification and
reasoning tasks, our approach reduces FLOPs by $14.2\times$ and improves accuracy by $6.48\%$ relative to baseline demonstration selection methods.
Read the full abstract ▾
All authors Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong, Gene Cooperman, Hongyang R. Zhang
Machine Learning
Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning
Mingyang Jiang, Yamin Li, Daniel Moyer et al. (+3 more)
EEG decoding tasks can rely on different temporal dynamics and cross-channel relationships. We test whether specialized modules improve a fully fine-tuned
EEG foundation model by augmenting CBraMod with cross-depth
Attention Residuals (AttnRes) and two soft-routed expert banks. Across matched three-seed experiments on FACED, ISRUC, SEED-V, and PhysioNet-MI, the complete model changes mean balanced accuracy relative to full fine-tuning by -0.12, +1.27, +0.77, and -1.27 points, respectively. AttnRes alone improves mean balanced accuracy on three
datasets, whereas adding experts on top of AttnRes helps only FACED and SEED-V. These gains come with substantial overhead: AttnRes requires 2.11 to 2.88x runtime and 1.78 to 2.67x
memory, while the complete model requires 2.41 to 3.04x runtime and 1.86 to 2.85x
memory. Overall, the added modules produce
dataset-dependent, sometimes opposing effects rather than consistent gains over full fine-tuning.
Read the full abstract ▾
All authors Mingyang Jiang, Yamin Li, Daniel Moyer, Fan Ma, Hua Xu, Catie Chang
Artificial Intelligence
ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software
Kratika Bhagtani, Kusha Sridhar, Maziyar Baran Pouyan et al. (+2 more)
Computer-use
agents that operate through screenshots and simulated actions are advancing rapidly, yet their evaluation remains anchored to general desktop and web tasks. Enterprise Resource Planning systems run the finance, procurement, inventory, and customer operations of organizations worldwide, and pose distinct challenges for computer-use
agents: dense interfaces, coordinated multi-step interactions, and errors that alter persistent business records rather than surfacing on screen. Existing enterprise computer-use
benchmarks rely on proprietary platforms or on simulated approximations of such software. We introduce ERPBench, a
benchmark that evaluates screenshot-only
agents on a live and reproducible system and scores each task against ground-truth values in its database. Beyond the
benchmark, we present a production-grade harness that gates
agent actions behind human approval for safe deployment. Evaluating six closed and open-source
agents, we demonstrate that strong general performance does not transfer to enterprise reliability. Even when an
agent reaches the right form and saves it, the stored record is often wrong: some
agents save in up to 85% of runs but write the correct value in as few as 3%. We further characterize failure modes specific to enterprise workflows.
Read the full abstract ▾
All authors Kratika Bhagtani, Kusha Sridhar, Maziyar Baran Pouyan, Yuying Zhao, Eugene Siow
Sound
The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification
Andrew P. Berg, Qian Zhang and Mia Y. Wang
As unmanned aerial vehicles (
UAVs) become increasingly prevalent in consumer and defense settings, classifying them reliably from limited, modality-specific data is an urgent challenge. The dominant approach, large pretrained networks fully fine-tuned on task data, carries a substantial computational and
memory weight that is hard to bear in resource-constrained
UAV deployments, where edge inference and rapid retraining for emerging platforms are both required. This paper systematically scales across both model architectures and fine-tuning methods for
UAV audio classification, asking when that weight is justified and when lighter alternatives prevail. Using a custom
dataset of 3,100 audio clips spanning 31 drone classes, we evaluate
transformer (ViT, AST) and convolutional (custom CNN, ResNet-18/152, MobileNet-V3-S/L, EfficientNet-B0/B7) backbones under full fine-tuning, classifier-only fine-tuning, and four parameter-efficient fine-tuning (PEFT) methods: SSF, IA3, OFT, and selective batch-norm tuning. All configurations are evaluated with 5-fold cross-validation across accuracy, training time, trainable-parameter share, and inference-time
memory footprint. Selective batch-norm fine-tuning of EfficientNet-B7 with three-fold augmentations achieves the highest validation accuracy (97.65% +- 0.30) while updating under 0.5% of model parameters. Across the sweep, lightweight CNNs consistently outperform
transformers on both accuracy and efficiency. For
UAV audio classification under data scarcity, scaling the method outperforms scaling the model.
Read the full abstract ▾
Human-Computer Interaction
Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming
Eduardo Davalos and Yike Zhang
The rapid adoption of generative AI has made final artifacts unreliable evidence of student learning, and AI detectors that examine only the finished product are inaccurate and ethically contentious. Process data offers an alternative, but prior work covers only English essay writing. We ask whether AI assistance carries a temporal signature, whether it generalizes from writing to programming, and whether it distinguishes ordinary collaboration from wholesale delegation. We analyze three public corpora: CoAuthor (1,447 keystroke-level co-writing sessions), RealHumanEval (editor telemetry from 243 programmer records), and a pre-LLM CS1 corpus (5.1 million keystrokes) as a human-only baseline, comparing minimal-AI work, collaborative AI use, and simulated wholesale delegation. Three findings emerge. First, the signature generalizes: AI contributions arrive in bursts far outside the author's own baseline in both mediums (paired d_z = 1.13 and 3.54). Second, engagement diverges by medium: 93% of AI-inserted characters survived to writers' final documents, while only 14% of accepted code suggestions survived intact. Third, classifiers using only observable temporal features separate simulated delegation from authentic work nearly perfectly (F1 $\geq$ 0.997; at most 0.5% of real work misclassified), while ordinary collaboration remains hard to distinguish from unassisted work. Temporal evidence flags wholesale delegation rather than assistance, positioning process visibility as a candidate evidentiary basis for academic integrity, pending validation in authentic coursework.
Read the full abstract ▾
Computer Vision
Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?
Seung Jae Lieu, Diego Morra, Chiara Cadoni et al. (+3 more)
An important component of urban accessibility, particularly for wheelchair users and people with reduced mobility, is sidewalk compliance with measurable requirements. We test whether effective width, longitudinal slope, cross slope, and pavement condition can be assessed reliably from pedestrian-level imagery using
vision-
language models (VLMs). We present the first application of sampling-based conformal prediction (CP) for VLM-based accessibility assessment. We evaluate four VLMs on 514 sidewalk images from Seoul, South Korea, with field-measured ground truth. Conformal calibration attains the nominal 90% coverage for all models and attributes, but the calibrated regions differ in informativeness. Effective width yields the most informative estimates, with a mean interval half-width of about 1.0 m for the best model. Since every model overestimates width, asymmetric calibration shortens the intervals by up to 33% at unchanged coverage. Longitudinal slope is marginally informative, cross-slope intervals are too wide to resolve regulatory thresholds, and pavement-condition sets degenerate to all five grades (A-E) for three of the four models. Uncalibrated intervals from raw sampling dispersion cover only 17-47% of field-measured values at a nominal 90% level. Among the images with the most self-consistent responses, these intervals miss the field-measured value in up to 96% of cases. Response self-consistency is therefore not evidence of accuracy, and sampling dispersion cannot be interpreted as uncertainty until it has been calibrated against field-measured ground truth. No quantitative attribute reaches the precision required for general compliance assessment, but CP identifies from calibration data alone which attributes can support screening of segments far from the thresholds. We release the annotated pedestrian-level images and their corresponding field-measured attribute values.
Read the full abstract ▾
All authors Seung Jae Lieu, Diego Morra, Chiara Cadoni, Wonseop Song, Martina Mazzarello, Carlo Ratti
Discrete Mathematics · Cross-listed from math.HO
David R. Wood
We present an exposition of a proof, discovered by GPT-6 Astra, of the Erdős–Sós
Conjecture, which states that every graph with average degree greater than $t-2$ contains every tree on $t\geq 2$ vertices.
Computer Vision
Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology
Kiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti et al. (+9 more)
Pathology
vision-
language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathology
vision-
language model can instead be assembled by parameter-efficient
alignment of frozen unimodal foundation models, leaving their pretrained representations untouched. Here we present Lumen, which aligns frozen Virchow2 and BioMedBERT backbones using rank-4 adapters and projection heads, training only 0.40% of the total parameters on the public QUILT-1M corpus. Across nine public zero-shot patch
benchmarks, Lumen achieved the highest mean chance-corrected balanced accuracy, 0.546 versus 0.461 for the strongest baseline (paired difference 0.086, 95% CI 0.042-0.136). On lymph-node metastasis detection, Lumen reached an AUROC of 0.964 (95% CI 0.956-0.971) on 4,214 held-out internal slides and 0.955 (95% CI 0.942-0.966) on 2,368 slides across nine external cohorts and six organs. At the internally calibrated threshold, it outperformed all
vision-
language baselines, with a balanced accuracy of 0.909 (95% CI 0.896-0.923) internally and 0.915 (95% CI 0.902-0.929) externally. Lumen performed competitively across the evaluations, with the exception of cross-modal
retrieval, where it ranked third behind CONCH and PathGen-L/14. Fully fine-tuning both encoders gave Lumen no consistent benefit over low-rank adaptation, although it improved
retrieval. Aligning frozen unimodal foundation models therefore yields strong and transferable performance at patch and slide level while training only a small fraction of the parameters.
Read the full abstract ▾
All authors Kiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti, Javier Garcia-Baroja, Philipp Zens, Branislav Zagrapan, Yuri Tolkach, Martin D. Berger, Aurel Perren, Bastian Dislich, Inti Zlobec, Amjad Khan
Machine Learning
Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space
Pisante Aida and Formentin Simone
Real-world intelligent systems increasingly operate under open-world conditions, where user intents are not fixed or exhaustively known a priori and may evolve as new interaction patterns emerge. This paper proposes a unified uncertainty-aware probabilistic framework for continual new intent discovery under an evolving label space. Each utterance is encoded through an adaptive $\beta$-VAE into a latent mean, used for classification and density modelling and a posterior uncertainty estimate acting as a global reliability signal. Classifier confidence, posterior uncertainty and DP-GMM likelihood are combined through a multi-signal decision mechanism to distinguish known intents from potentially novel samples. Candidate novel instances are clustered through a density-based discovery module and only reliable clusters are promoted to new labels, enabling controlled label-space expansion. Replay and Elastic Weight Consolidation mitigate catastrophic forgetting and preserve previously acquired knowledge. The paper formalises continual intent discovery as a structured multi-phase open-world problem, introduces adaptive label-space expansion under stability–plasticity constraints and uses posterior uncertainty to regulate trusted-sample selection, pseudo-labelling, novelty admission and replay. Experiments show high novelty precision, stable adaptation across sequential phases and limited forgetting. Near-zero NMI and ARI indicate limited reconstruction of the complete fine-grained intent taxonomy, consistent with the framework's conservative promotion strategy. Qualitative analyses nevertheless reveal dense and locally coherent semantic clusters, showing that reliable novel structures can be discovered without exhaustive recovery of the underlying taxonomy.
Read the full abstract ▾
Artificial Intelligence
Do Frontier Models Seek Safety Evidence Before Acting?
Omer Tafveez
Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled
benchmark in which models make deployment decisions with optional evidence that varies in
retrieval cost, probability, severity, and presentation. Across GPT-5.5, o3, Claude Opus 4.8, and Claude Sonnet 4.6, we find distinct evidence-acquisition policies: Opus inspects nearly by default, o3 is the most skip-heavy and threshold-sensitive, and GPT-5.5 and Sonnet occupy intermediate regimes. Inspection increases strongly with severity and decreases with
retrieval cost, whereas probability has much weaker behavioral influence: increasing the stated likelihood of a problem from 10% to 70% changes inspection by at most 21 percentage points. Despite these differences, Stage 1 rationales are dominated by expected-value
reasoning across models. A cost-obligation decomposition further shows that avoidance is driven primarily by
retrieval friction and explicit threats to the deployment payoff rather than by the remediation duties created by knowing. Counterfactual interventions reveal a further mismatch between behavior and explanation: evidence framing can strongly change decisions near the inspection boundary while going largely unmentioned, whereas probability is frequently cited despite having little causal influence. These results suggest that deployment-time safety depends not only on how models respond to known risks, but also on whether they acquire the evidence needed to know that acting is safe.
Read the full abstract ▾
Artificial Intelligence
The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier?
Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri et al. (+3 more)
LLM inference optimizations report speedups on different models, GPUs,
prompts, and quality metrics, making them hard to compare or combine. We build a cost, quality, and latency Pareto atlas to identify the best configurations for different deployment constraints. Since exhaustive testing is impractical, we measure 54 configurations of Qwen2.5-7B-Instruct running on vLLM 0.12 across L4, A100, and H100 GPUs and use these anchors to calibrate a simulator. It reproduces measurements at anchored batch sizes, with cross campaign drift below 1.5 percent. A separate quality evaluation tests FP16, AWQ 4bit, FP8 weights, and FP8 KV cache on 200 GSM8K questions with five examples per
prompt. Sparse
attention is evaluated only in simulation. On the calibrated grid, 18 of 36 configurations reach the Pareto frontier. Combined methods reach it more often than individual methods, with 9 of 15 combinations versus 9 of 21 single methods. Quality testing changes the winners. AWQ 4bit reduces per
token latency to 0.34 times baseline on L4 but loses 5.9 percent of strict GSM8K accuracy, narrowly missing the 95 percent quality floor within sampling uncertainty. Flexible answer extraction matches FP16 accuracy, suggesting the loss comes from formatting rather than arithmetic. FP8 weights retain 99.4 percent of baseline accuracy at 0.61 to 0.65 times baseline latency across all three GPUs and appear in three of four regime winners. A naive FP8 KV cache maintains normal throughput but answers none of the 200 questions correctly, showing why speed alone is insufficient. Under two
prompt designs, n gram speculative decoding measures at 0.90 to 0.98 times baseline and adds no benefit on this stack. The best choice depends on the constraint and GPU: H100 wins for tight latency, while A100 wins for throughput and low cost at 0.106 dollars per million
tokens.
Read the full abstract ▾
All authors Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly
Systems and Control
Predicting Viral Evolution from a Single Early Measurement Using the Target Cell Limited Model
Rahal Nanayakkara and Paulo Tabuada
Recent advances in diagnostic techniques have enabled the accurate quantification of early-stage viral loads. A key problem of interest is translating these measurements into predictive clinical insights, such as
forecasting a patient's onset of infectiousness and peak infection severity. In this work, we address this problem using the Target
Cell Limited (TCL) model. Because the host's internal biological states are practically unobservable, predicting the viral trajectory from a single noisy viral load measurement is highly nontrivial. To overcome this, we introduce a novel coordinate transformation that converts the nonlinear viral dynamics into a monotone system. By leveraging monotone systems theory and taking into account invariant subspaces of the transformed system, we derive explicit analytical formulae that establish a strict upper bound on the peak viral load and a guaranteed lower bound on the time to infectiousness using a single early viral observation.
Read the full abstract ▾
Systems and Control
Hybrid Sequential Feedback Optimization for Wind Farm Power Maximization
Shijie Huang and Sergio Grammatico
This paper considers feedback optimization for optimal steady-state operation of nonlinear discrete-time systems when the steady-state input-output map and its sensitivity are expensive to compute. We propose a hybrid extension of sequential feedback optimization (SFO) that augments the model-based SFO gradient with correction terms through a convex combination with summable diminishing weights. Two variants are studied: one based on recursive least-squares (RLS) sensitivity estimation, and another on extremum seeking control (ESC) gradient estimation. Under contractivity and smoothness assumptions, we show that both hybrid schemes preserve the convergence of SFO to a neighborhood of the optimal steady state. The proposed methods are validated through a wind farm power maximization problem using a medium-fidelity model, demonstrating improved early transient performance compared to pure SFO.
Read the full abstract ▾
Computation and Language
Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels
David Ababio Awuni, Luke E. K. Achenie, Benjamin Tei Partey et al. (+2 more)
Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four open-weight families (Llama 3.1, Qwen 2.5, Gemma 2, and Yi 1.5) in a fully crossed pairwise design with 9,312 judgments. A common per-family statistic is strongly confounded with candidate quality and correlates with Bradley-Terry ability at r = 0.95. We derive a corrected
estimator that holds the candidate family fixed and compares judges. All four families then show a positive same-family lift (3.4-8.4 percentage points), with global FPS 0.067 (95% CI [0.053, 0.084], permutation p = 0.0002). The effect remains under panel-based quality controls, an independent human-consensus anchor, and a float16 judging replication. Judge-side likelihood is closely related to the effect: adding likelihood advantage reduces the controlled coefficient by 61%, which we treat as descriptive attenuation rather than causal mediation. Position is a separate failure mode. Across the panel, 55.4% of AB/BA pairs reverse, and reversal above 50% is incompatible with a simple independent content-noise model. Relative to a family-balanced reference, panel composition changes 18.5% of pairwise outcomes. A complete reproducibility archive has been prepared for public release.
Read the full abstract ▾
All authors David Ababio Awuni, Luke E. K. Achenie, Benjamin Tei Partey, Elvis Gyasi Owusu, Nii-Nai Derrick Sowah
Computer Vision
Investigating Adversarial Robustness of Heterogeneous Cooperative Perception
Chenyi Wang, Yutong Liu, Qingzhao Zhang et al. (+1 more)
Heterogeneous cooperative perception (CP) enables connected vehicles with diverse sensor setups to share spatial awareness via compact feature maps, where receivers reconcile these maps using learned translation modules for fusion and inference. Prior attacks against CP in a homogeneous setting reveal that the data exchange introduces a critical attack surface: a single malicious
agent can transmit crafted features that erase real objects from a neighbor's fused scene. Yet, it is widely hypothesized that heterogeneity naturally defends against these attacks, as the attacker lacks knowledge of the victim's detector and the translation module scrambles
adversarial gradients. We demonstrate that this protection is largely an illusion. Using a matched-objective harness to standardize the perturbation budget, objective, and forward path, we show that properly tuned iterative attacks close or reverse the apparent robustness gap. However, these optimization-based attacks require ground-truth labels and iterative backpropagation, meaning they do not represent a practical field threat running in real-time. To bridge this gap, we introduce HetPoison, a learned generator that crafts a removal perturbation in a single, label-free forward pass. HetPoison transfers across major heterogeneous designs without requiring access to the victim's detector, matching or exceeding the effectiveness of expensive optimizer-based attacks. Since heterogeneity itself is not a defense, we propose HetShield, a lightweight trust layer that validates the spatiotemporal consistency across features, recovering 83–95% of the accuracy degraded by attacks, outperforming prior art.
Read the full abstract ▾
All authors Chenyi Wang, Yutong Liu, Qingzhao Zhang, Ming F. Li
Artificial Intelligence
SNOMED CT Concept Recommendation from Masked Clinical Context
Ali Noori
Standardizing clinical
language to SNOMED CT supports interoperability, analytics, and reusable phenotyping, but concept recommendation remains difficult when relevant concepts are rare or absent from training data. We present a masked-concept recommendation
benchmark using the SNOMED CT Entity Linking Challenge v1.2.1 data derived from MIMIC-IV-Note. The
dataset contains 75,491 annotations across 272 discharge summaries, with 204 notes used for training and 68 for historical testing. For each unique note-concept pair, the target mention is masked from a local clinical context and the system ranks SNOMED CT concepts observed during training. We compare a popularity baseline, sparse TF-IDF concept prototypes, dense latent semantic analysis
embeddings, sparse-dense fusion, retrieved-note evidence, and a
retrieval-augmented hybrid. Sparse TF-IDF performs best, achieving Recall@1 of 14.81%, Recall@10 of 33.43%, MRR of 0.2114, and nDCG@10 of 0.2297.
Retrieval augmentation does not improve this baseline, with Recall@10 of 31.99% and MRR of 0.1937. Performance is strongly affected by concept frequency: Recall@10 is 7.74% for concepts appearing in only one or two training notes versus 43.90% for concepts appearing in more than ten. In addition, 9.66% of test note-concept pairs contain concepts unseen during training. These findings show that local lexical context and terminology coverage are major determinants of recommendation quality in low-resource settings and provide a reproducible baseline for future ontology-grounded and biomedical-encoder
retrieval systems.
Read the full abstract ▾
Computation and Language
AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content
David Ababio Awuni, Rose-Mary Owusuaa Mensah Gyening and Elvis Gyasi Owusu
AfriSyCo studies answer switching around African-
language factual content with two complementary layers: native-
language follow-ups and a controlled cross-
language factorial whose question, options, and target remain in the African
language while the follow-up framing is English. We analyze 1,415 turn-1-correct model-
language-item observations derived from 100 source questions across seven open-weight checkpoints and six
languages; turn-1-correct denotes observed first-response accuracy, not demonstrated knowledge. Under native
prompts, assertive endorsement produces 29.3 percentage points more any-turn false-target selection than mention-plus-verification (M+V), with a 19.0-point immediate T2 contrast. In the precommitted 2 x 2 factorial, averaged over three tested
prompt families, assertive framing increases target selection by 30.4 points (95% CI [28.4, 32.3]); verification decreases it by 17.4 points, while the assertive effect rises from 20.5 points without verification to 40.2 with it (interaction +19.7). The effect remains 34.8 points among 611 observations correct after option reordering. Magnitude varies sharply by wording and checkpoint:
prompt-family effects span 20.1-42.5 points, a Twi/Qwen3 paraphrase shifts target selection from 70.8% to 4.2%, and checkpoint effects span 9.2-47.0 points.
Prompt realization is therefore part of the measurement problem.
Read the full abstract ▾
Numerical Analysis
A variational mollification approach to circular deconvolution
Mirza Karamehmedović, Pierre Maréchal and Mykhailo Petrov
We propose a variational mollification approach to circular deconvolution based on the reconstruction of a mollified target object rather than the exact solution itself. The method is formulated as a convex variational problem whose solution admits an explicit
Fourier representation. We establish the consistency of the proposed reconstruction as the target resolution increases and derive convergence rates for deterministic data perturbations. For ordinary smooth kernels, the method achieves the classical order-optimal algebraic convergence rates under Besov-Nikolskii smoothness assumptions, while for supersmooth kernels it attains the corresponding order-optimal logarithmic rates. Numerical experiments on synthetic and wind-direction data illustrate the effectiveness of the proposed approach and confirm the theoretical predictions.
Read the full abstract ▾
Computation and Language
SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale
Md Tahmid Rahman Laskar, Xue-Yong Fu and Shashi Bhushan TN
Limited controlled evidence exists on how training data, adaptation method, and model scale jointly affect tool-calling performance in
language-model
agents. We evaluate supervised fine-tuning (SFT) with LoRA, reinforcement learning (RL) via Group Relative Policy Optimization (GRPO), and SFT followed by GRPO across six Qwen3 models from 0.6B to 32B parameters, covering both in-distribution performance and cross-
dataset transfer. SFT with LoRA is the strongest in-distribution method throughout the 0.6B-32B range and best in 15 out of 18 experimental settings. On cross-
dataset transfer, the methods are closer: GRPO wins 29 out of 54 settings where training and test
datasets differ, but its margin over SFT averages under one point, and SFT->GRPO is rarely strongest in either comparison.
Dataset mixing gives consistently strong transfer while staying close to specialized in-distribution training, regardless of method. Additional analysis further confirms that LoRA outperforms full-parameter fine-tuning, demonstrating that LoRA better preserves pretrained agentic behavior.
Read the full abstract ▾