Artificial Intelligence
A dataset of formalised theorem statements from the Annals of Mathematics
Thomas Browning, Katerina Hristova, David Ledvinka et al. (+4 more)
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires
datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised
theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release them without formalised proofs.
Read the full abstract ▾
All authors Thomas Browning, Katerina Hristova, David Ledvinka, Justus Springer, Hang Lu Su, Jack McKoen, Kevin Buzzard
Data Structures and Algorithms
The Complexity of Hamiltonian Cycles and Paths with Prescribed Walk Lengths
Hitendra Kumar, Mathieu Mari and R. B. Sandeep
Fix a set $S$ of positive integers. An $S$-
Hamiltonian cycle is a cyclic ordering of all vertices of a graph such that each consecutive pair is joined by a walk whose length belongs to $S$. We study the complexity of deciding whether an input graph admits such an ordering, together with the corresponding path variants with prescribed or unrestricted endpoints. We complete the complexity classification for undirected graphs. In particular, we prove NP-completeness for every finite nonempty set of odd lengths, resolving an open problem posed by Amarilli, Lombardo, and Monet (WG 2026). For digraphs, all three problems are NP-complete for every fixed finite nonempty $S$ and admit linear-time
algorithms when $S$ is cofinite. For other fixed infinite sets $S$, we establish NP-complete and undecidable cases, with undecidability occurring even when $S$ is recursive.
Read the full abstract ▾
Computation and Language
LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation
Hui Huang, Jie Zhou, Hongli Zhou et al. (+7 more)
Reward models are central to preference
alignment for legal tasks, yet existing reward model
benchmarks are still primarily centered on general-domain preferences. In this work, we introduce LegalRewardBench, the first human-verified
benchmark for evaluating reward models in the legal domain. The
benchmark organizes legal preference evaluation into five capability levels: knowledge, understanding, analysis, decision, and writing, and preference examples are constructed through rubric-guided automatic judging combined with human verification. We evaluate three families of judges, covering both general and fine-tuned models, and generative and discriminative architectures. Experimental results show that strong general-purpose generative models are currently the most robust legal reward models, while existing fine-tuned reward models transfer less reliably to legal preference evaluation. We also conduct detailed comparisons of input organizations and training strategies.
Read the full abstract ▾
All authors Hui Huang, Jie Zhou, Hongli Zhou, Qundong Shi, Shuyuan Zheng, Yini Su, Shaochun Wang, Biyuan Lin, Muyun Yang, Tiejun Zhao
Artificial Intelligence
Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
Jing Liu, Yongxing Qi, Ping Yao et al. (+1 more)
What binds large
language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the public TCMEval-SDT
benchmark for Traditional Chinese Medicine syndrome differentiation (200 cases), the binding constraint is output discipline and
reasoning structure, not model capability alone: two years of model scaling move zero-shot scores by only -0.03 to +0.08, while output-discipline failures (non-terminating
reasoning, format non-compliance, large run-to-run spread) persist even in frontier models. We test this with a model-agnostic
agent framework formalizing decision making as a five-stage closed loop, enforced by a candidate x evidence
matrix falsification protocol: every candidate is judged against every evidence item, at least half of the candidates must be falsified before a conclusion is licensed, and survivors are emitted in a machine-verifiable single-line format. Across five base models, the effect is sign-conditional on zero-shot output discipline: it rescues models whose discipline fails (DeepSeek-V4-Flash: +0.267/+0.271, entirely termination rescue), reduces a high-variance model's run-to-run standard deviation from 0.218 to 0.007 (Kimi K3), and significantly costs already-disciplined models (-0.087 to -0.120 on budget-matched Qwen3-4B/32B). Ablations attribute the cost to the candidate-bounded format layer and show the effect is independent of injected knowledge content (protocol-knowledge decoupling). The protocol also transfers to misinformation-robust mathematical
reasoning, detecting injected false premises at 89.8% recall with a 6.8% false-positive rate (MCC 0.54; a flag-everything baseline scores 0) and restoring accuracy to the no-misinformation ceiling. Where zero-shot output discipline is weak, the
reasoning protocol sets the floor; base-model capability always sets the ceiling.
Read the full abstract ▾
All authors Jing Liu, Yongxing Qi, Ping Yao, Ting Wu
Computer Vision
Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies
Ufuk Efe and Alptekin Temizel
Detectors of logical anomalies, such as missing, extra or wrongly combined parts, usually score a test image by its distance from normal (good) images. They achieve near-perfect image-level AUROC on standard industrial anomaly detection
benchmarks such as MVTec LOCO, but their robustness to changes in capture conditions remains largely unexamined. Under a heterogeneous perturbation protocol in which each test image is randomly kept unaltered or subjected to a brightness reduction or a zoom-out transformation, the normal-reference methods we tested lose 9.7 to 34.1 AUROC points, and two of the strongest, CSAD and SALAD, fall from 97.7% and 96.4% to 68.1% and 62.3%. We propose a framework in which a classifier, trained on normal images and on synthetic anomalies, scores a test image without comparing it with normal data. From a short description of each product, a
language model derives anomaly types and editing instructions, an image editor applies them to normal images, and the classifier learns to separate the edited images from automatically discovered normal sub-modes. With its full training recipe, the framework reaches 94.9% AUROC on clean images, 1.5 to 2.8 points below SALAD and CSAD, and 94.1% under the perturbation protocol. Trained without brightness or zoom-out augmentation, so that neither test perturbation occurs in training, it still reaches 92.5% (93.2% clean). These results suggest that clean
benchmark scores can hide a strong sensitivity to capture conditions, and that learning the decision from both normal images and rule violations may reduce it.
Read the full abstract ▾
Machine Learning
Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller
Sagi Habani, Yehonathan Refael and Ofir Lindenbaum
Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training. We ask whether the choice of optimizer affects the ability to recover the training data. Extending work connecting Karush–Kuhn–Tucker conditions to training-data reconstruction, we show that the implicit biases of popular optimizers (SGD, Adam,
Muon) leave very different fingerprints of the training data. We argue that the key distinction is the weight-specificity of these implicit biases, namely how much continuous information about the final weights the optimizer-dependent target of the stationarity conditions encodes. The limiting stationarity conditions for models trained with SGD and
Muon retain enough weight-specific information to reconstruct training examples in practice. For Adam in the $\ell_\infty$ implicit-bias regime, the optimizer-dependent part of these conditions encodes only a discrete pattern of maximal coordinates and their signs, and at nondegenerate KKT points the conditions are too few to identify the training set to first order. Experiments on MNIST and CIFAR-10 support these claims: models trained with
Muon can yield stronger reconstructions at much lower training cost than models trained with SGD, although this advantage depends on the training regime and architecture, and models trained with Adam appear consistently more resistant to the evaluated attacks.
Read the full abstract ▾
Machine Learning
Reliable Risk Estimation with Kernel Mean Matching under Dependent Sampling
Alexey Zaytsev, Diana Koldasbayeva and Egor Serov
Kernel Mean Matching (KMM) estimates risk under
covariate shift by reweighting labelled source samples so that their kernel mean
embedding matches that of unlabeled target samples. Existing finite-sample guarantees are usually stated for independent samples, although many applications involve temporal, spatial, or clustered dependence. We give a finite-sample KMM analysis under dependent sampling by replacing nominal sample sizes with effective sample sizes in the concentration steps used by the classical proof. The approach uses Bernstein inequalities for geometrically strongly mixing processes and derives a model-based effective sample size. The resulting bound separates overlap, dependence, and smoothness effects with specific constants derived under a Gaussian process assumption. This analysis yields an additional tradeoff: smoother losses preserve more input dependence and therefore reduce effective sample size, while also reducing function complexity and empirical-to-population risk gaps. Applying the result to prediction yields confidence intervals that achieve near-nominal coverage in synthetic experiments and substantially reduce undercoverage on real monitoring data.
Read the full abstract ▾
Computer Vision
Unsupervised and Supervised Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 2)
Thierry Bouwmans, Anastasia Zakharova, Belmar Garcia et al. (+3 more)
Since the rise of supervised deep learning modelet dets, researchers has attempt to solve infrared small targection using various models like conventional neural networks, GANS,
Transformers, Mixture of Experts and recent graph/hypergraph neural networks. Moreover, these deep neural networks methods surpassed the traditional unsupervised models and the low-rank and sparse decomposition unsupervised models reviewed in "Traditional and Recent Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 1). In this context, the aim of this paper is to provide a complete survey of the deep learning models in infrared small target detection. First, we categorize the different approaches found in the literature in terms of the modeling models of strategies. Then, we have discussed them in terms of the critical situations that they claim to handle. Furthermore, we present the specific performance evaluation. Then, we conclude with several promising directions for future research.
Read the full abstract ▾
All authors Thierry Bouwmans, Anastasia Zakharova, Belmar Garcia, Marwa Chendeb El Rai, Meghna Kapoor, Badri Narayan Subudhi
Systems and Control
On Over-Conservatism Under Low-Probability Extreme Events: A KL-Regularized Wasserstein Distributionally Robust Planning Method
Xinda Shen, Yifan Su, Bo Hu et al. (+3 more)
The increasing penetration of renewable energy makes power systems more vulnerable to low-probability extreme events, elevating system planning to a critical role in ensuring reliability. Distributionally robust optimization (DRO) based on the Wasserstein distance is widely used to address this challenge. However, we find that the conventional Wasserstein ambiguity set tends to excessively amplify the probabilities of low-probability extreme events, leading to over-conservative investment decisions. To mitigate this over-conservatism, this paper proposes a novel ambiguity set that modifies the Wasserstein distance with a Kullback-Leibler (KL) divergence regularization term. By leveraging the KL divergence's sensitivity to relative probability changes, the proposed set effectively curbs the unrealistic magnification of low-probability events. A two-stage distributionally robust planning model built upon this new ambiguity set is developed to optimize the installed capacity of photovoltaic, wind, and energy storage. The complex model is then reformulated as an equivalent exponential cone program with strict theoretical proofs, making it computationally tractable. Numerical results on the PJM 5-bus and IEEE 118-bus systems reveal the over-conservatism of standard Wasserstein DRO under low-probability extreme events and validate the effectiveness and efficiency of the proposed planning model and solution
algorithm.
Read the full abstract ▾
All authors Xinda Shen, Yifan Su, Bo Hu, Yanbo Chen, Changzheng Shao, Tao Wu
Computer Vision
LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout
Ziyu Zhu, Zhaoxu Sun, Fan Jiang et al. (+5 more)
Autoregressive
video diffusion models have emerged as a foundation for long-horizon world rollout. However, when extended far beyond their training windows, these models suffer from progressive drift: visual quality deteriorates, motion becomes inconsistent, and object identity gradually collapses as generated frames are recursively reused as context. We study a supervision-horizon gap: short-horizon
distillation leaves later rollout states without direct supervision. We show that matching short-window marginals need not determine long-horizon behavior, while longer on-policy trajectories expose delayed failures to training. This motivates temporal
manifold matching at scale for long-horizon world models. Building on this insight, we introduce LongForcing, a
distillation approach that scales teacher supervision to long student self-rollouts. LongForcing preserves the short-horizon teacher-forcing and causal ODE-
distillation stages, while replacing the realscore teacher in the final distribution-matching stage with an extended-horizon bidirectional teacher. The long-horizon teacher supervises extended student self-rollouts using the standard distribution-matching formulation, without modifying the student architecture or increasing inference cost. We evaluate LongForcing on text-to-
video generation and interactive action-conditioned world models, achieving a VBench Quality score of 85.52 and improving WorldRoamBench 60s action score by 23.9 points in first-person ablations. Qualitative stress tests further sample interactive rollouts up to 24 hours, far beyond the training horizon. These results suggest that scaling supervision along the temporal axis is a practical step toward long-horizon world models. The project website and code are at https://github.com/Fantasy-AMAP/LongForcing.
Read the full abstract ▾
All authors Ziyu Zhu, Zhaoxu Sun, Fan Jiang, Mengchao Wang, Junfeng Ni, Ting-Bing Xu, Zhicheng Liu, Mu Xu
Logic in Computer Science
Finite-on-Top-of-Temporal CSPs in Fixed-Point Logic
Manuel Bodirsky and Philipp A. Grzywaczyk
We study definability in fixed-point logic with counting (FPC) for a class of constraint satisfaction problems (CSPs) that simultaneously generalises finite-domain CSPs and temporal CSPs. The templates for the CSPs are first-order expansions of the structure $([k] \times {\mathbb Q};<_1,\dots,<_k,\sim)$ where $<_i \, := \{((i,x),(i,x')) \mid x<x'\}$ and $\sim \, := \{((i,x),(i,x')) \mid i \in [k], x,x' \in {\mathbb Q}\}$, i.e., $k$ copies of $({\mathbb Q};<)$. Such a CSP is definable in FPC precisely when the template pp-constructs neither the ternary temporal relation $X$, which holds on three elements if the minimum is attained exactly twice, nor a nontrivial finite affine structure. Equivalently, the template has global polymorphisms that witness the tractability of the temporal CSPs on the copies, and that provide 3-4 weak near-unanimity operations on the set of copies of ${\mathbb Q}$. In this case, we prove that the CSP is even expressible in the less expressive logic FP$^*$, which is the restriction of FPC without counting terms (i.e., the extension of first-order logic by a fixed point operator and an ordered auxiliary number sort). Our
algorithm samples finitely many values in each copy and then performs nested constraint-singleton consistency tests (which is a uniform
polynomial-time
algorithm for finite-domain CSPs). The correctness proof uses finite-domain CSP theory to combine consistency certificates by a single polymorphism term, fixing each variable to one copy without destroying the certificates needed for the temporal
algorithm. We then use a known normal form for algebraic products to control the remaining interactions between different copies.
Read the full abstract ▾
Computer Vision
Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation
Yaoli Liu, Guo-Hua Wang, Yiyang Chen et al. (+4 more)
Generated images often have coherent layouts and visual content, yet local errors in small text and complex characters still limit their readability and practical use. Scene-text refinement requires accuracy, preservation, and efficiency. Existing methods based on variational autoencoders (VAEs) can lose fine strokes during reconstruction, while full-image editing can shift background colors. In this work, we introduce PixText, a model that formulates local text refinement as grouped image generation in pixel space. Conditioned on the original image, PixText generates only the target regions, preserves unedited content, and uses MeanFlow for four-step generation. We further introduce Text Refinement Bench to evaluate text correction and image preservation in generated images. On this
benchmark, PixText achieves 83.06% glyph pass and 94.66% exact target-character OCR accuracy, versus 36.77% and 52.31% for the strongest baseline. Its four-step MeanFlow variant retains an 81.84% pass rate with less than one GPU-second of amortized generation cost per image.
Read the full abstract ▾
All authors Yaoli Liu, Guo-Hua Wang, Yiyang Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Yao-Xiang Ding
Machine Learning
PING: physics informed graph neural network for advection-diffusion processes with applications to solar power forecasting
Jelena Simeunović, Baptiste Schubnel, Pierre-Jean Alet et al. (+2 more)
Advection-
diffusion plays an essential role in transport phenomena such as atmospheric and cloud dynamics. Improved forecasting of cloud motion, in turn, enhances solar power production forecasts and facilitates the integration of additional photovoltaic (PV) sources into the power grid. However, both classical numerical models and emerging deep learning approaches face challenges when applied to spatially irregular sensor networks such as those formed by weather stations. In this work, we adopt a graph signal processing perspective and model advection-
diffusion particles as signals on a graph to capture the dynamics of these processes. We introduce a Physics-Informed Graph Neural Network (PING) for forecasting future advection-
diffusion particle concentrations on irregular grids. The model incorporates a discretized advection-
diffusion equation as a soft constraint in the loss function to guide learning toward physically consistent solutions. This model is on par with state of the art models on synthetic and real transport phenomena
datasets, including sea surface temperature and cloud index
datasets. Furthermore, the PING model is successfully coupled with models for forecasting PV power production. This hybrid approach leverages data fusion from ground-based sensors at PV stations and satellite images with cloud concentration to improve the accuracy of intra-day PV power production.
Read the full abstract ▾
All authors Jelena Simeunović, Baptiste Schubnel, Pierre-Jean Alet, Pascal Frossard, Rafael E. Carrillo
Computer Vision
Traditional and Recent Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 1)
Thierry Bouwmans, Anastasia Zakharova, Belmar Garcia et al. (+3 more)
Infrared small target detection is often used in different civilian and military applications to detect static or moving targets in scenes like in ground, air and sea surveillance. First valuable research has emerged since 30 years ago and the two last decades witnessed very significant publications in this field following the rise of low-rank and sparse decomposition (model-based methods) and deep learning models (data-based methods). Furthermore, several surveys can be found in the literature but none of them addresses an overall review in this field. In this context, the aim of this paper is to provide a complete survey of the traditional and recent approaches in infrared small target detection. First, we categorize the different approaches found in the literature in terms of the modeling models, i.e mathematical models, machine learning models and signal processing models. Then, we have discussed them in terms of the critical situations that they claim to handle. Furthermore, we present the available resources,
datasets and libraries. Then, we conclude with several promising directions for future research. For the sake of reading, this survey is divided into two parts: 1) "Traditional and Recent Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 1)" about conventional and low-rank and sparse decomposition (model-based methods), and 2) "Traditional and Recent Approaches for Infrared Small Target Detection : Overview, Challenges and Perspectives (Part 2)" about deep learning models (data-based methods).
Read the full abstract ▾
All authors Thierry Bouwmans, Anastasia Zakharova, Belmar Garcia, Marwa Chendeb El Rai, Meghna Kapoor, Badri Narayan Subudhi
Social and Information Networks
CSBA-Net: Learning Cross-Scale Structural Dependencies for Influential Node Identification in Complex Networks
Rihab Boukheche, Mohammed Lalou and Nardjes Bouchemal
Identifying influential nodes is a fundamental task in complex network analysis, with applications in epidemic control, information
diffusion, and network robustness. Existing centrality-based and learning-based methods often provide limited integration of structural information across different network scales. To address this limitation, we propose CSBA-Net, for Cross-Scale Structural BiGRU
Attention Network, a multi-scale structural representation learning framework that jointly captures local, community-level, and global structural patterns. The extracted representations are processed by CNNs and integrated through a BiGRU with multi-head self-
attention to model dependencies across structural scales. Influential-node scores are learned through regression using SIR-based
diffusion simulations as reference targets. We conduct experiments on 24 real-world and 12 synthetic networks from social, biological, technological, and knowledge domains, and show that CSBA-Net achieves Kendall's tau=0.802, Spearman's rho=0.943, NDCG10 =0.898, and NDCG20 =0.916, outperforming the considered centrality-, CNN-, and GNN-based baselines. The results demonstrate the effectiveness of combining complementary structural scales for accurate influential-node ranking across diverse network structures.
Read the full abstract ▾
Systems and Control
Fast Analytical Method for Resource Adequacy Assessment in Renewable-Rich Power Systems
Seyed Amir Hosseini, Mohammad Reza Karimi Gharigh, Antonello Monti et al. (+2 more)
This paper proposes a novel analytical method for resource adequacy assessment in renewable rich power systems. The approach begins by applying the stress strength method to estimate two key resource adequacy indices: loss of load expectation (LOLE) and expected energy not supplied (EENS). This method requires defining the probability distribution functions (PDFs) for both the generation side and the load side. The load is assumed to follow a normal probability distribution, while the generation side probability distribution is derived from the combined PDFs of conventional, wind, and solar power sources. The approach models the cumulative impact of uncertainties on resource adequacy using the central limit
theorem (CLT), and improves accuracy with a cumulant based Gram Charlier expansion when the CLT alone is insufficient. The effectiveness of the proposed method is validated through Monte Carlo simulations conducted on the IEEE single area and multi-area RTS-96 test systems. The results demonstrate that the proposed method achieves a substantial reduction in computational time, which is crucial in the context of operational planning, without sacrificing accuracy. Furthermore, its performance improves as renewable penetration increases, making it particularly suitable for future power systems operation and planning.
Read the full abstract ▾
All authors Seyed Amir Hosseini, Mohammad Reza Karimi Gharigh, Antonello Monti, Peter Palensky, Saeed Peyghami
Computation and Language
JevGPT: Thinking Fast and Slow in Autonomous Research
Yasheng Sun, Yanning Dai, Yimeng Chen et al. (+9 more)
Autonomous research
agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between
retrieval coverage and the evidence that informs research. The challenge is to align fast local judgments with changing evidence needs and feed their findings back into research decisions. We introduce JevGPT, a dual-system architecture for autonomous research that couples fast evidence processing with deliberative research planning. System Two sets evidence objectives and integrates findings, while System One locates support, assesses relevance, and guides further inspection. Independent source judgments run in parallel; selected original passages inform the next research step. Experiments on fixed-corpus question answering and document ranking show that JevGPT achieves leading task performance, with faster completion and lower cost than comparably effective research
agents. Evidence analysis shows broader source inspection and greater coverage of supporting documents in the research loop, highlighting efficient evidence processing as a route to more capable autonomous research.
Read the full abstract ▾
All authors Yasheng Sun, Yanning Dai, Yimeng Chen, Nanbo Li, Firas Laakom, Yifan Xu, Piotr Piękos, Mateusz Ostaszewski, Wenyi Wang, Cheng Luo, Yuhui Wang, Jürgen Schmidhuber
Computation and Language
PAINT: A Framework for Multilingual Pain Representation from Medical Licensing Exams to Real-World Clinical Texts
Boya Zhang, Yuanchao Ma, Jiageng Wu et al. (+14 more)
Pain is one of the most common and clinically important symptoms, reflecting disease onset, progression, and treatment response. However, pain is difficult to accurately capture and interpret from medical text, as its expression varies across
languages, documentation types, and patient demographics, and is often embedded in terminology, negation, temporality, and contextual descriptions. Existing pain-related studies remain largely monolingual or limited to narrow clinical settings. In this study, we introduce PAINT, a multilingual framework for studying pain representation across medical exams and real-world clinical texts. PAINT includes nine pain-focused
dataset partitions spanning English, Spanish, Portuguese, and Japanese, with clinician annotations in all four
languages. We curated a structured schema covering pain relevance, pain presence, anatomical location, pain descriptors, and demographic information. To capture multilingual pain representations, we leverage large
language models (LLMs) and adopt an ensemble strategy to improve performance. Ten clinicians across four
languages validate the labels: the ensemble reaches macro-F1 of 0.91-1.00 on pain relevance and pain presence and 92-100% accuracy on demographics, with inter-annotator $\kappa$ of 0.82-1.00. We release the WorldMedQA-Pain ensemble labels, the extraction pipeline, validation scripts, and clinician annotation sheets for publicly licensed corpora, providing a foundation for pain-centered clinical NLP and for studying pain documentation across
languages and healthcare contexts.
Read the full abstract ▾
All authors Boya Zhang, Yuanchao Ma, Jiageng Wu, Krittaphas Chaisutyakorn, Rodrigo Gameiro, Ahram Han, Chien-Yu Huang, Nikhil Jaiswal, Marianna Leite, Miriam Mora-Mau, Jaime Pineda-Moreno, Siena Placino, Ryohei Yamamoto, Yugang Jia, Jie Yang, Leo Anthony Celi, Douglas Teodoro
Systems and Control
Data-Driven Surrogate-Model for Real-Time Loads Prediction in Floating Wind Farms
Federico Bellini, Majid Ebrahimi, Alessandro Fontanella et al. (+4 more)
This work presents a data-driven load-surrogate modelling framework for real-time control of floating offshore wind farms. The proposed methodology uses mid-fidelity simulations performed with OpenFAST and FAST.Farm together with MLife fatigue analysis to generate Damage Equivalent Load (DEL)
datasets of floating wind turbines under wake steering conditions. A two-stage surrogate modelling approach is adopted: first, a Feed-Forward Neural Network (FFNN) is trained using data from simulations of a single floating wind turbine, while a second stage corrects the residual error between the FFNN predictions and FAST.Farm simulations using either Gaussian Process Regression (GPR) or an additional FFNN. The results show that the proposed framework can estimate DELs with errors generally below 15% for tower base bending moment, blade root bending moment, yaw bearing moment, and fairlead tension, while maintaining computational times compatible with real-time applications. The study also highlights the challenges related to generalization of the load-surrogate model under varying environmental and control conditions, especially for large floating wind farms. Overall, the proposed methodology demonstrates the potential of surrogate-based DEL estimation for load-aware floating wind farm control applications.
Read the full abstract ▾
All authors Federico Bellini, Majid Ebrahimi, Alessandro Fontanella, Marcus Becker, Jan-Willem Van Wingerden, Sara Muggiasca, Marco Belloli
Cryptography and Security
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Yan-Lun Chen, Pin-Yu Chen and Chia-Mu Yu
Third-party skills can expose LLM
agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for
agents to decode and follow. We evaluate Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success. In the primary setting with shortened skills, the variants achieve attack success rates of up to 47.5% and 40.3%, respectively. Successful decoding does not guarantee attack success, and layering has model-dependent effects. The tested skill scanners rarely flag injected skills. These findings highlight the risk of promoting decoded, untrusted content into actionable instructions.
Read the full abstract ▾
Computer Vision
FALLNEST: Dual-Domain Dataset Condensation of Imbalanced IMU Data for Wearable Fall Detection
Rashi Niyas P, Ritika Jain and Hitika Tiwari
Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Existing methods either rely on hand-crafted features with shallow classifiers, which limits learning from raw signals, or train deep networks on full
datasets that require re-sampling to counter class skew and demand substantial data and compute. To address this, we propose a novel Fall detection framework via Normalized-gradient and
Embedding matched Synthetic Time-frequency condensation, dubbed FALLNEST, a data-centric approach that distills large, imbalanced IMU
datasets into tiny, class-balanced synthetic training sets. Building on dual-domain time-series condensation (CondTSC), FALLNEST introduces a fall-specific 7-channel input with accelerometer vector magnitude, class-balanced K-Means initialization, and normalized gradient matching with gradient clipping, combined with MMD-based
embedding alignment and multi-view
Fourier-domain augmentation, so that class balance arises from the condensed set itself rather than from re-sampling. We evaluate on SisFall, KFall, and MobiFall using strict subject-wise splits and naturally imbalanced test sets, reporting accuracy, Macro-F1, and PR-AUC over five seeds. A 102K-parameter TinyCNN trained on only 32 to 146 synthetic windows (about only 1% of the training windows) reaches 93.5-95.8% mean accuracy and 0.89-0.98 PR-AUC, with standard deviations of 1.0-1.7% in accuracy, demonstrating the efficacy of our approach.
Read the full abstract ▾
Machine Learning
Optimal Online Regret for Context-Lumpable Bandits
Chenyu Lu and Zihan Zhang
We study
stochastic contextual bandits with an unknown context-lumpable structure. The $S$ contexts are partitioned into $r$ blocks, and every arm has the same mean reward across contexts in the same block. Under arbitrary context distributions and without separation assumptions, we design an
algorithm with expected regret $\widetilde{O}(\sqrt{r(S+K)T})$, matching the lower bound of Lee et al. (2023) up to logarithmic factors and improving their previous upper bound by a factor of $r$. The
algorithm operates over dyadic accuracy levels, using a baseline policy and confidence-based early stopping to control exploration. It then performs cross-context elimination: since rewards are identical within a block, one selected arm eliminates all surviving records from that block, requiring at most $r$ selections at each level. Multi-scale exploration assigns finer accuracies to frequent blocks and coarser accuracies to rare blocks, yielding a near-optimal arm for every block while keeping the weighted policy error small.
Read the full abstract ▾
Machine Learning
Teach Me After You Learn It: Lookahead Self-Distillation for RLVR
Zepeng Zhai and Meilin Chen
On-policy self-
distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense,
token-level supervision by aligning a model's own distribution with the distribution induced by privileged information. However, existing OPSD methods derive supervision solely from privileged information of the same instance, leaving inter-instance supervision largely unexplored. We propose Lookahead Self-
Distillation (LEAD), which introduces inter-instance
distillation by allowing the teacher to first learn from other on-policy rollouts before teaching the student. LEAD constructs lookahead teachers through virtual RL updates on disjoint subsets of on-policy rollouts, and uses each teacher to provide cross-group
token-level supervision for the other subset. To reconcile the complementary yet potentially conflicting signals from OPSD and RLVR, we introduce harmonious modulation, which adaptively modulates the GRPO advantage based on the agreement between the two signals. Extensive experiments on scientific
reasoning and interactive-
agent benchmarks show that LEAD achieves the best in-domain average performance across model scales while maintaining out-of-domain generalization comparable to GRPO.
Read the full abstract ▾
Logic in Computer Science
The Complexity of Verifying Strategic Abilities in Succinct Multiagent Systems
Yifan He, Munyque Mittelmann, Aniello Murano et al. (+1 more)
This paper studies the complexity of model checking strategic abilities in multiagent systems under imperfect information, in particular systems represented succinctly. Such a representation can describe systems that are exponentially larger than their input and is particularly relevant to practical implementations of model checkers such as MCMAS. The logics we consider include epistemic strategy logic supporting partial binding $SLK_{P}$, and its syntactic fragments: epistemic strategy logic $SLK$ and variants of Alternating Time Temporal logics. We show that succinct model checking for $SLK_P$ and $SLK$ is $AEXP(poly)$-complete, while objective ATL and ATL$^{*}$ are $P^{NEXP}$-complete. The latter corrects a previous NEXP-completeness result for model checking succinct imperfect-information systems. Under subjective semantics, $P^{NEXP}$-completeness already holds for one-step Coalition Logic, and therefore also for ATL and ATL$^{*}$.
Read the full abstract ▾
All authors Yifan He, Munyque Mittelmann, Aniello Murano, Michael Thielscher
Computation and Language
Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models
Guoming Ling, Yupei Lin, Zhongzhan Huang et al. (+5 more)
Benchmarks are essential for evaluating and improving large
language models (LLMs). Yet many widely used
benchmarks are redundant, making evaluation unnecessarily expensive.
Benchmark compression lowers this cost by estimating full-
benchmark scores and rankings from a partial evaluation. Research in this area has grown rapidly since 2024, but to our knowledge no survey has systematically organized its methods and findings. We review 119 papers to explain how methods choose what to evaluate, recover full-
benchmark results, and verify their reliability. From this analysis, we develop a taxonomy covering compression within individual
benchmarks, across
benchmark suites, and during adaptive evaluation, together with work on redundancy and reliability. We compare their information needs, total costs, reliability checks, and limitations. Methods reduce evaluation costs by selecting representative subsets, using cheaper or reusable information, and testing adaptively, but risk poor coverage, inaccurate estimates, and sequential delays. The resulting taxonomy and practical guide help researchers choose, validate, and deploy methods for more efficient and reliable LLM evaluation.
Read the full abstract ▾
All authors Guoming Ling, Yupei Lin, Zhongzhan Huang, Junxin Li, Junjie Liu, Shanshan Zhong, Hefeng Wu, Liang Lin
Computation and Language
PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation
Yuchen Song and Satoshi Nakamura
Speech-to-
speech translation should preserve not only what is said, but also who says it and how it is said. Existing end-to-end S2ST,
speech MLLM, and cascade systems can preserve content or timbre, but often struggle to realize emotion, tone, rhythm, pauses, and pragmatic attitude in the target
language. We propose PACT, a target-space pragmatic prompting framework for expressive and voice-preserving S2ST. PACT extracts source pragmatic cues, projects them into the target-
language expression space, calibrates the projected representation to a realizable target subspace, and converts it into continuous
prompts for a frozen
speech generator. On bidirectional Spanish-English TOPI evaluation, PACT achieves the best overall performance among evaluated systems across content fidelity, voice preservation, and expression preservation metrics.
Read the full abstract ▾
Computer Vision
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
Hao Zhang, Yi Huang, Wei Liu et al. (+6 more)
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed
tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challenging due to NCCT's inherently low tissue contrast, lack of hemodynamic enhancement, and complex anatomical background. These limitations make subtle, heterogeneous, and multifocal hepatic lesions difficult to identify. Although large-scale self-supervised pretraining can learn robust representations from unlabeled NCCT scans, conventional voxel-wise reconstruction does not fully exploit the complementary information available in NCCT. Under weak NCCT contrast, low-level intensity patterns become less informative for pathology recognition, limiting the capture of lesion-specific discriminative features. In this paper, we propose the Liver Frequency-Spatial Unified Self-Supervised Pretraining (LiFUSE). The frequency branch applies random band-stop masking and spectrum reconstruction to encourage the model to capture subtle differences between lesions and surrounding tissues, while the spatial branch performs hybrid-granularity masked volumetric reconstruction to accommodate lesions of diverse sizes and morphologies. Finally, a cross-domain consistency scheme couples the spatial and frequency branches, yielding more discriminative representations for hepatic structures and lesions. Extensive experiments on three clinically relevant tasks across internal cohorts and a public target-domain transfer setting show that LiFUSE consistently outperforms strong baselines. These results suggest that unified frequency-spatial learning can improve liver disease analysis on NCCT, highlighting its potential for large-scale screening.
Read the full abstract ▾
All authors Hao Zhang, Yi Huang, Wei Liu, Yuan Gao, Zeju Li, Xu Han, Yu Shi, Ling Zhang, Ke Yan
Numerical Analysis · Cross-listed from physics.flu-dyn
One-way pressure-independent valves with hysteresis and chattering
Fabio Bagagiolo, Andrea Corli, Stefan Moreti et al. (+1 more)
We propose a model for the one-dimensional isothermal gas flow through a valve in a pipe. The valve aims at keeping the outgoing flow in an assigned interval; moreover, its opening and closing depend on a further parameter. The model is realized by a system of two conservation laws with suitable conditions coupling the ingoing and the outgoing flow. We study the corresponding Riemann problem, where non-classical shocks show up. Although simple, the model allows to study two key oscillatory behaviors of the flow, which are due, respectively, to the chattering of the valve, especially seen in the numerical simulations, and to the stabilizing hysteresis induced by the valve operation. We characterize the states leading to chattering and show how they depend on the parameters of the model. Through several numerical simulations, we study the interplay between the two above phenomena.
Read the full abstract ▾
All authors Fabio Bagagiolo, Andrea Corli, Stefan Moreti, Massimiliano D. Rosini
Artificial Intelligence
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Dezheng Bao, Sihang Du, Renhong Huang et al. (+3 more)
Multi-
agent debate (MAD) aims to improve large
language model
reasoning by exposing
agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring
agents to engage with a particular peer claim. As a result, reliable
reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous
reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source
agent responds to a target's current
reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves
agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance,
agent-transition, and group levels further show more peer-specific deliberation, more correction-oriented revisions, and more favorable consensus dynamics.
Read the full abstract ▾
All authors Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun, Yang Yang
Computer Vision
Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
Qian Chen, Xianyin Zhang, Lifan Guo et al. (+1 more)
Vision-
language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as
retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models indicate heading levels using different numbers of preceding “\#” symbols, page-by-page prediction often lacks document-level consistency. In practice, input-resolution and context-length constraints make it infeasible for a VLM to jointly process all page images in documents containing tens or hundreds of pages. To address this limitation, we propose a VLM-based framework that incrementally reconstructs heading hierarchies with a level-wise
multimodal memory. The
memory retains a compact subset of all previously processed pages, selected by anchors. Our framework supports flexible anchor selection, and in this work we select the most recent node at each level, allowing the VLM to observe the visual, textual, and layout patterns of headings at every level. For comprehensive evaluation, we also introduce the Complex and Long Document Heading Hierarchy Reconstruction
Benchmark (CLDoc-HHRBench), comprising 250 documents and 11,212 pages with expert-verified annotations. Experiments on CLDoc-HHRBench and three existing
benchmarks demonstrate the effectiveness of our method.
Read the full abstract ▾
All authors Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang