Information Retrieval
Recommendation World Models for Future-State Control
Jinfeng Xu, Zheyu Chen, Ziyue Peng et al. (+6 more)
Sequential recommendation optimizes which items to rank, while each displayed slate also shapes subsequent feedback and user state. We study how a trained ranker can support decisions about these future consequences. We introduce UA-TWM, a utility-anchored world-model interface that constructs nearby slate actions, estimates their target-relevant consequences, and selects an alternative subject to utility constraints. The reference slate serves as a fallback when no alternative qualifies. A logged-replay instantiation combines utility and target-gain estimates with calibrated failure-risk prediction; a closed-loop instantiation uses one-step state-action prediction and updates its decisions after observed feedback. We evaluate transfer across twelve sequential backbones on MovieLens-25M and KuaiRand-Pure, and repeated target-directed interaction in KuaiSim. Attaching the interface improves Recall@20, NDCG@20, and future-state
alignment for every matched logged backbone. Selection ablations reveal the utility and risk costs of aggressive target pursuit, while closed-loop diagnostics isolate the contribution of action-conditioned prediction. Local consequence modeling thus enables target-aware selection around a trained sequential ranker.
Read the full abstract ▾
All authors Jinfeng Xu, Zheyu Chen, Ziyue Peng, Jianheng Tang, Zheng Lin, Jing Yang, Puzhen Wu, Zheng Xing, Victor C. M. Leung
Computer Vision
VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control
Kemou Jiang, Maonan Wang, Xingchen Zou et al. (+6 more)
Traffic signal control (TSC) is essential for mitigating urban congestion. Recent advances in
vision-
language models (VLMs) enable richer interpretation of intersection scenes, opening new opportunities for visual-context-aware TSC. However, the loose coupling and repeated information conversion between modules can lead to the loss of fine-grained visual details, while sequential inference introduces substantial latency. To address these limitations, we propose VLALight, a lightweight end-to-end
vision-
language-action framework that directly maps intersection observations and signal-phase information to discrete signal actions. To handle the multi-view nature of TSC, VLALight combines multiple directional camera views into a unified visual input and uses textual instructions to establish their correspondence with traffic movements and signal phases. This design enables direct action prediction with a compact 0.5 B-parameter model, without intermediate image-to-text descriptions or handcrafted traffic-state representations. Experiments show that VLALight delivers the best emergency-vehicle service of all compared methods, reducing pooled emergency waiting time by 21.1% over the cascaded VLMLight while running in real time on local hardware and generalizing to unseen intersection
topologies and traffic-flow patterns.
Read the full abstract ▾
All authors Kemou Jiang, Maonan Wang, Xingchen Zou, Jiayue Zhu, Yuhang Fu, Sicheng Wang, Xi Chen, Yirong Chen, Zhiyong Cui
Computer Vision
Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation
Tasneem Nasser, Susanne Schmid, Roberto Souza et al. (+1 more)
A key challenge in medical image analysis is the scarcity of large annotated
datasets for specific populations and diseases. As deep learning models rely heavily on labeled data, effective transfer learning strategies are needed to reduce the dependence on manual annotations. Self-supervised learning has emerged as a promising approach for developing foundation models by enabling the learning of transferable feature representations from large-scale unlabeled medical imaging
datasets. In this study, we investigate voxel-level
brain age prediction as a domain-specific self-supervised pretext task and compare it with image inpainting, a widely used non-domain-specific alternative. We further propose a multitask self-supervised pretraining framework that jointly optimizes both objectives to learn complementary neuroimaging representations. The pretrained models are evaluated on three downstream
magnetic resonance image
segmentation tasks: multiple sclerosis lesion
segmentation, ischemic stroke lesion
segmentation, and cortical
brain structure
segmentation. Overall, the proposed multitask pretraining framework consistently outperformed the single-task pretrained models and training from scratch across most experimental settings, demonstrating the benefit of combining domain-specific and general self-supervised learning pretext tasks for the development of generalizable neuroimaging foundation models.\ Code Availability: The source code used in this study is publicly available at https://github.com/TasneemN/Combining-General-and-Domain-Specific-Pretext-Tasks-for-
Brain-MR-Image-
Segmentation/
Read the full abstract ▾
All authors Tasneem Nasser, Susanne Schmid, Roberto Souza, Naser El-Sheimy
Numerical Analysis
A Monolithic Discontinuous Galerkin Framework for Darcy Optimal Control with Radon-Measure Tracking and Pointwise Control Constraints
SeongHee Jeong and Sanghyun Lee
We study an
elliptic optimal control problem governed by Darcy's equation in heterogeneous porous media, with pointwise box constraints on the control. The objective functional is formulated via a Radon measure, which allows the desired pressure state to be tracked on observation sets of varying dimension, including points, curves, and subdomains, within a single formulation. The state and adjoint equations are discretized by a symmetric interior penalty discontinuous Galerkin method, yielding a locally mass-conservative approximation that is robust across strong permeability discontinuities, while the control is approximated by piecewise constants. The state, adjoint, and control are retained as primary unknowns in a single coupled optimality system and solved monolithically by a primal-dual active set strategy. We establish stability and well-posedness of the discretization and derive a priori $L^2$ error estimates for both variables. The principal difficulty is the reduced regularity of the adjoint state induced by the measure-valued tracking data. The analysis controls the resulting adjoint-control coupling through an intermediate adjoint driven by the continuous optimal state. Numerical experiments confirm the predicted convergence rates for point, curve, and subdomain observations, exhibit mesh-independent primal-dual active set iteration counts, and demonstrate local mass conservation.
Read the full abstract ▾
Artificial Intelligence
LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information
Furkan Yilmaz, Habibe Aleyna Tasdemir and Muhammed Faruk Gozay
"System One" decision models such as TypeSafe's Jev and its open counterpart Laya answer typed questions about a text in a single forward pass with calibrated probabilities, but they cannot ask for missing information: when a first message does not say what separates two departments, they guess. We present LAVOIR (Laya with Value-Of-Information Routing), which places the candidate pieces of missing information (slots) in the input next to the answer options, so that one forward pass returns both the decision distribution and, for every slot, the expected gain in the probability of the correct decision if the user were asked about it. VOI targets need no human labels: gold decisions come from schema rules, an LLM only verbalizes messages and answers, a model from another family checks every text, and pairing each message with several profiles makes regression on realized gains estimate the expected gain. A Gini-
impurity cap bounds the predicted value by what a calibrated model can still gain. In a controlled study, decisions on seen schemas are statistically indistinguishable from the Bayes ceiling. The final model's question policy matches a greedy oracle VOI policy on seen schemas (AUC 0.799 vs. 0.797), and with at most 0.5 questions per conversation it is 14.1 points more accurate than never asking. On real ABCD conversations, one real exchange raises accuracy by 8.3 points where LAVOIR asks and leaves it unchanged where it does not; on SGD the cap lowers the asking rate from 93% to 8.6%. On Laya's twelve
benchmarks LAVOIR is above Laya's reported scores on seven, and it answers a question in 31 ms (median, GH200).
Read the full abstract ▾
Artificial Intelligence
The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?
Jiayi Chen and Guiling Wang
While inference-time
reasoning in large
language models (LLMs) promises better decision making, its higher computational cost may not yield better economic outcomes. Yet
reasoning controls are rarely evaluated as economic interventions, where changes in model outputs must translate into better portfolios after trading costs. We conduct a controlled study of representative LLMs from the DeepSeek, GPT, and Gemini families. We vary
reasoning effort while holding information available at each formation date,
prompts, output formats, and portfolio construction fixed. Our evaluation covers a full year of U.S. equities under three input conditions: numerical, identifiable news, and masked news. It includes more than 800,000 asset predictions and repeated model generations. Across all three model families, additional
reasoning does not produce a reliable improvement in net portfolio returns. For DeepSeek, where we examine the full progression from no
reasoning to maximum
reasoning, performance is nonmonotonic. Repeated generations also produce unstable treatment effects and portfolio selections, even when overall scores remain similar. These findings show that additional
reasoning can change financial decisions without reliably improving their economic value, motivating validation for each task before deployment.
Read the full abstract ▾
Robotics
From Visual Search to Movement Control: A Priority Field for Artificial Agents
Han Zhang and Zhong Cao
Human spatial
attention is widely conceptualized as being guided by a priority map that integrates perceptual salience, current goals, and past experiences. Here, we extend priority-based computation to movement control in artificial
agents. We first introduce a lightweight model of visual search based on an integrated priority map. Trained on human saccades, it reproduced key behavioral patterns, including oculomotor suppression and history-driven selection. Extending the search model, we equipped an artificial
agent with a priority field and evaluated its performance in a reach-avoid task that required reaching a goal destination while avoiding moving obstacles. Compared with alternative architectures, priority-field
agents trained more efficiently and performed better in unseen, complex scenarios, even from simple demonstrations. Adding a simple
memory mechanism also produced human-like, history-driven effects in anticipating the likely location of the upcoming goal. These findings suggest that priority-based computation may provide a promising foundation for movement control in artificial
agents.
Read the full abstract ▾
Computer Vision
SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion
Timing Li, Yiming Sun, Boan Tao et al. (+3 more)
Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decouple appearance adaptation,
geometric alignment, and information fusion, limiting dependency propagation across stages. We propose Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T
Alignment and Fusion (SAGE), a unified framework integrating frequency equalization, hierarchical
alignment, and subband fusion. SAGE employs invertible joint encoding and source-specific low-frequency modulation to derive structural and gain guidance while preserving source information. Hierarchical frequency collaborative
alignment estimates global affine geometry from low-frequency approximations and transfers
geometric and contextual cues to high-frequency correlation
reasoning for reliability-aware residual refinement. Guided subband fusion jointly aggregates the aligned frequency coefficients under propagated source and
alignment guidance, coordinates complementary low- and high-frequency information, and reconstructs the fused image through the inverse wavelet transform. Extensive experiments on RGB-T
datasets with real-world and synthetic misalignments demonstrate consistently competitive performance in
alignment and fusion, validating the effectiveness of source-anchored guidance for weakly registered RGB-T images.
Read the full abstract ▾
All authors Timing Li, Yiming Sun, Boan Tao, Xiyuan Gao, Haifang Cao, Pengfei Zhu
Game Theory
From Bilateral Trade to Matching Markets: Sharp Gains from Trade
Zhengyang Liu, Ying Qin and Zihe Wang
We study gains from trade in matching
markets with independent private values and costs,
Bayesian incentive compatibility, interim individual rationality, and no expected budget deficit. A second-best guarantee for finite bilateral trade extends without loss to matching
markets with independent Borel priors, arbitrary downward-closed feasibility, and finite expected first-best gains. For bounded buyers with monotone hazard rates and arbitrary bounded sellers, we determine the exact worst-case ratio of second-best to first-best gains, approximately $0.72490721$. For binary buyers and sellers with at most $m$ types, we determine the exact ratio for every $m$, including $8/9$ when $m=2$ and a limit of $4/5$ as $m$ grows. Both families of bounds are tight already in bilateral trade.
Read the full abstract ▾
Human-Computer Interaction
"If You're Not Doing It, Somebody Else Is": Active Negotiation and the Invisible Labor of Sustained LLM Use
Matt Viana, Patrick Erickson, Shomir Wilson et al. (+1 more)
Large
language models (LLMs) have become fixtures of academic work even as their users describe them as degrading their writing, thinking, and skills. Dominant adoption frameworks read continued use as evidence of satisfaction, and cannot explain continued use of a distrusted tool. We interviewed 36 graduate student workers, balanced between English-as-a-foreign-
language (EFL) and non-EFL speakers, and introduce the Active Negotiation framework: a model of sustained LLM use as a recurring cycle of risk, mitigation, and justification. A failure surfaces a risk, mitigation labor addresses it, and a justification renders the residual risk tolerable until the next failure reopens the cycle. The cycle runs across three dimensions: practical,
auditing output; internal,
auditing one's own cognition and identity; and social, managing how peers and institutions perceive use. EFL participants invoke linguistic parity as a further justification. We reframe continued adoption as compliance sustained by invisible labor.
Read the full abstract ▾
All authors Matt Viana, Patrick Erickson, Shomir Wilson, Dana Calacci
Computer Vision
MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement Learning
Peipei Li, Shuhan Xia, Shengyang Liu et al. (+2 more)
Real-world
multimodal misinformation often involves mixed forgery sources, requiring sample-specific detection strategies. Existing tool-augmented methods rely on predefined workflows or inference-time planning, limiting adaptability or increasing inference cost. To address this issue, we introduce MM-VeriAgent, which learns to verify mixed-source
multimodal misinformation with tools. We first build MM-VeriTools, a specialized toolkit for misinformation detection
agents. By benchmarking various candidate models and methods on the sub-tasks required by mixed-source detection, we select the strongest for textual, visual, and cross-modal forgery analysis and encapsulate them as callable tools with a unified interface. On top of this toolkit, we train the LVLM
agent with reinforcement learning to teach it how to use these tools to better solve mixed-source detection. Since many of the tools are specialized models whose online execution at every rollout severely limits RL efficiency, we further introduce Tool-Execution Cache, which pre-executes candidate tool calls and reuses their cached outputs during training. This preserves multi-step rollouts while reducing online tool execution, largely improving the training efficiency.Experiments on MMFakeBench demonstrate substantial accuracy gains over the base model without explicit tool search at inference time. Ablation and efficiency analyses further validate the learned tool-use policy and show that Tool-Execution Cache reduces online tool executions during training.
Read the full abstract ▾
All authors Peipei Li, Shuhan Xia, Shengyang Liu, Zekun Li, Ran He
Robotics
Learning Vision-Based Agile Gap Traversal: Differentiable Simulation with a Warm-Started Critic
Nuthasith Gerdpratoom, Tianchen Sun, Yichao Gao et al. (+1 more)
Traversing narrow gaps is challenging for autonomous quadrotors, especially when control commands come directly from high-dimensional visual observations. Existing end-to-end methods often rely on behavior cloning or full-rollout backpropagation through time (BPTT) via differentiable simulation, which can limit policy performance or incur high training costs. We propose a two-stage reinforcement learning framework for more efficient ego-centric visuomotor gap-traversal policy training, leveraging quasi-analytical policy gradients (QPG) via differentiable simulation and critic warm-starting. The framework utilizes QPG to avoid backpropagation through visual rendering, reducing computation and
memory costs while improving sample efficiency. In the first stage, an expert actor and critic are trained using privileged observations, including gap geometry. Unlike prior gap-traversal approaches, our training utilizing QPG does not require resetting the
agent along optimized reference trajectories. In the second stage, a visual policy is trained using binary gap masks from two ego-centric cameras and low-dimensional observations, while its privileged critic is warm-started from the first stage. This substantially improves training efficiency and traversal success compared with cold-starting the critic or using full-rollout BPTT. Our framework does not require retraining the expert actor when system parameters change, enabling more efficient generalization across drone platforms than state-of-the-art visual gap-traversal methods based on action supervision. The learned visual policy also generalizes to gaps with unseen shapes. Extensive real-world experiments further demonstrate robust gap traversal using binary masks rendered online. Beyond gap traversal, the proposed framework is generic and can be extended to other visuomotor
robot learning tasks.
Read the full abstract ▾
All authors Nuthasith Gerdpratoom, Tianchen Sun, Yichao Gao, Lin Zhao
Robotics
Multi-Objective Human-in-the-Loop Bayesian Optimization of a Lower-Limb Exoskeleton
Neil Janwani, Matthew T. Lerner, Aaron J. Young et al. (+1 more)
Human-in-the-loop optimization (HILO) is a common approach for optimizing the control of assistive devices to account for the wearer's unique biomechanics and subjective preferences. However, despite research suggesting that a person may have a different prioritization of objectives depending on time-varying factors such as the environment, their mood, or energy levels, existing HILO approaches only consider a single objective or enforce a fixed weighting on a set of objectives. Neither approach is capable of representing an individual's preferences over objectives. In this work, we propose Multi-Objective Human-in-the-loop
Bayesian Optimization (MO-HILBO), which builds on explicit multi-objective
Bayesian optimization to efficiently infer a personalized set of Pareto-optimal controllers. We compare our approach with an existing multi-objective HILO method and experimentally demonstrate MO-HILBO on a lower-limb exoskeleton across two objectives: metabolic cost (efficiency) and ordinal human feedback (comfort). We find that MO-HILBO (1) discovers Pareto-optimal controllers, and (2) that the pairwise ordering of points on the Pareto front itself is consistent with validation trials. Lastly, we open-source mohilo, a Python package for running both HILO and MO-HILBO on wearable devices: https://dynamicmobility.github.io/mohilo/.
Read the full abstract ▾
All authors Neil Janwani, Matthew T. Lerner, Aaron J. Young, Maegan Tucker
Sound
Training-Free Contextual ASR via SpeechLLM-Based Error-Aware Selective Retrieval
Natsuo Yamashita, Ai Nemoto, Ryosuke Koichi et al. (+1 more)
Recognition of domain-specific and low-frequency terms remains challenging for automatic
speech recognition (ASR). Although contextual biasing can improve their recognition, directly providing a large terminology dictionary introduces many irrelevant biasing terms.
Retrieval-based contextual biasing addresses this issue by selecting candidate terms from an external dictionary, but querying many recognized words requires numerous dictionary lookups and may yield poorly targeted candidates. We propose a training-free contextual ASR framework in which a pretrained
speech large
language model (SpeechLLM) jointly generates an ASR hypothesis and localizes error spans likely to involve domain-specific terms. Only the localized spans are used to retrieve phonologically similar terms from an external terminology dictionary. The same SpeechLLM then re-recognizes the audio conditioned on the first-pass hypothesis and the retrieved terms, without task-specific model training. To assess applicability across domains, we evaluate the framework on medical, air traffic control, and financial
speech. The proposed method substantially reduces dictionary queries while improving the recall and ranking of relevant terminology candidates and second-pass ASR performance across all three domains.
Read the full abstract ▾
All authors Natsuo Yamashita, Ai Nemoto, Ryosuke Koichi, Masaaki Yamamoto
Machine Learning
LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant
Md. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Nafiza Anjum et al. (+2 more)
Reliable voice interaction is essential in environments with limited internet connectivity and strong
privacy. However, most existing voice assistants depend on cloud-based services, which leads to latency issues, dependency on internet access, and
privacy vulnerabilities. This research presents LUMO (Lightweight Unified
Multilingual Orchestrator), a
privacy preserving offline voice assistant designed for edge computing environments. This system integrates local Automatic
Speech Recognition (ASR), locally deployed quantized Large
Language Model (LLM), and Text-to-
Speech (TTS) synthesis into a fully offline pipeline running on a Raspberry Pi 5 with 8 GB RAM. To enable efficient operation on resource constrained hardware, the
language model is compressed using 4-bit GGUF quantization, which reduces
memory usage while preserving practical conversational capability. Existing edge based voice assistants Mycroft provides partial offline functionality without a generative LLM, with an approximate latency of ~5 s and power consumption of ~12 W, while Rhasspy supports full offline operation but lacks generative capabilities, with ~3 s latency and ~11 W power usage. In contrast, LUMO achieves a Word Error Rate (WER) of 6.8% for short English utterances in low noise conditions, an end-to-end response latency of 2.0-4.0 s, and a lower peak power consumption of approximately 9.0 W. The system also achieves effective offline recognition for Bangla
speech, supporting
multilingual accessibility in low resource settings. By operating entirely offline, LUMO provides strong data
privacy, reduced need for cloud connectivity, and suitability for
privacy sensitive edge execution such as rural healthcare, education, and disaster response scenarios.
Read the full abstract ▾
All authors Md. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Nafiza Anjum, Shakila Sultana, Md. Sujan Ali
Multiagent Systems
ADF-EA: A Unified Execution Assurance System for Agent Device Foundation
Xuechun Li, Jiaxin Liang, Jie Li et al. (+4 more)
Agents based on large
language models (LLMs) can access heterogeneous devices through tools and APIs, but reliable execution must account for unmet effects, uncertain outcomes, and changing prerequisites. A command may be acknowledged without producing its intended effect, while missing feedback may obscure an action that has already succeeded. We present
Agent Device Foundation–Execution Assurance (ADF-EA), an architecture that connects
agent planning and device execution through shared capability contracts. Device Capability Contracts (DCCs) unify invocation conditions, intended effects, evidence requirements, and recovery rules across heterogeneous interfaces.
Agents use these contracts to plan, while the runtime applies the same semantics to authorize actions, verify effects, and govern continuation and completion. Persistent execution state retains verified progress, unresolved outcomes, and remaining budgets across plan revisions, enabling observation-based recovery, authorized retries, and necessary state repair. We formalize the execution lifecycle and establish conditional soundness properties for completion and recovery authorization. Evaluations span multiple LLMs, five
agent frameworks, and simulated process-control, household, and robotic manipulation domains. Compared with direct invocation and existing execution-checking approaches, ADF-EA reduces false completion and unnecessary repetition, supports necessary state repair, prevents calls to unavailable capabilities, and preserves permitted task completion and recovery. These results demonstrate DCCs as a reusable semantic foundation for
agent autonomy across heterogeneous devices, unifying capability-based planning, evidence-grounded execution, and authorized recovery within one architecture.
Read the full abstract ▾
All authors Xuechun Li, Jiaxin Liang, Jie Li, baolong Li, Jue Wang, Peng Yuan, Hang Huang
Information Theory
Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
Faisal Al-Kamali, Hussein A. Ammar, Francois Chan et al. (+3 more)
Ensuring operational safety in threat-prone environments remains a critical challenge for multi-
UAV networks serving as aerial base stations. This paper proposes an efficient framework to maximize global energy efficiency (EE) while promoting safe operation through threat-aware clustering and reward-based safety enforcement. The proposed framework is executed in three steps. First, a threat-aware K-means (TAKM)
algorithm determines the minimum required
UAVs and computes safe initial placements. Second, an optimal matching stage assigns physical
UAVs to these centroids to minimize energy expenditure. Third, a threat-aware multi-
agent twin delayed deep deterministic policy gradient (MATD3)
algorithm dynamically optimizes trajectories, power, and user associations. Simulation results show that the proposed framework achieves zero observed safety violations in the considered scenarios while achieving superior EE and faster convergence than other learning methods and non-clustering baselines. Compared to heuristic optimization, the proposed framework outperforms the greedy particle swarm optimization (GPSO) and achieves performance comparable to that of the optimized PSO (OPSO), while incurring significantly lower online deployment computational complexity. Furthermore, the proposed framework demonstrates effective generalization to unseen user distributions, large
UAV fleets, and different threat geometries, while maintaining zero safety violations.
Read the full abstract ▾
All authors Faisal Al-Kamali, Hussein A. Ammar, Francois Chan, James H. Bayes, Yasser Gadallah, Mohamed H. Ahmed
Information Theory · Cross-listed from math.PR
Comment on "Symmetric Pseudo-Random Matrices"
Chin Hei Chan
In 2018, Soloveychik, Xiang and Tarokh considered a pseudo-random symmetric circulant
matrix constructed from binary Golomb sequences of length $n=2^m-1$, and claimed a proof that its empirical spectral distribution converges almost surely to the semicircle law as $n$ grows to infinity by the method of moments. In this comment note we show that their argument contains several technical flaws and inappropriate applications of technical lemmas. Instead we demonstrate that the
eigenvalues of the
matrix are simply a normalized twisted Kloosterman sum varying over the multiplicative character, to which we apply Katz's result directly to establish the asymptotically semicircle spectral distribution deterministically.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.ao-ph
On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting
Yilin Zhai, Hongyuan Shi and Zaijin You
This study conducts a systematic hyperparameter search across five deep learning architectures, DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2, and nine context lengths (1-168 h) for single-station significant wave height (Hs)
forecasting on NDBC buoy 41009, followed by re-evaluation of the best configurations on a 47-buoy, 37-year corpus. The five families converge to a common performance level on the multi-buoy evaluation (between-family SD = 0.0014 m^2, 0.8% of the grand mean), a spread dwarfed by the 4.83x cross-
dataset MSE shift between buoy corpora. All multi-buoy trials beat persistence (mean skill +0.062), but no architecture consistently outperforms the others. On the single-buoy experiment, skill peaks at 12-24 h where five trials fall below persistence, per-family Q4/Q3 test MSE ratios range from 2.4 to 2.6, and deep models underperform persistence for the most extreme 1% of waves. These findings are consistent with the interpretation that persistence already captures the dominant linear-inertial signal in univariate Hs, and that architecture engineering under this univariate input setting has reached diminishing returns: cross-buoy variance, not model class, dominates forecast error. Future work should prioritise atmospheric
covariates, zero-shot cross-buoy transfer, and decomposition of Hs into swell and wind-sea components. By establishing a rigorous reference baseline for what univariate Hs models can and cannot achieve, this study provides a
benchmark against which future multivariate and physics-informed approaches can be calibrated, and offers practical guidance for lightweight buoy-level
forecasting in mid-latitude storm-dominated and swell-mixed environments.
Read the full abstract ▾
Numerical Analysis · Cross-listed from physics.flu-dyn
Particle Trajectories Beneath Fully Nonlinear Waves Generated by Horizontal Seabed Motion
João Vitor P. Poletto, David Andrade, Marcelo V. Flamarion et al. (+1 more)
We investigate fully nonlinear water waves and fluid-particle dynamics generated by the horizontal motion of a seabed obstacle with prescribed time-dependent velocity. The governing equations are the full Euler equations, formulated in a time-dependent conformal domain that simultaneously maps the moving free surface and seabed onto fixed boundaries. The main contribution of this work is a Lagrangian formulation for computing particle trajectories in the resulting genuinely unsteady conformal domain. We derive a closed-form trajectory system in the canonical domain in which the time dependence of the conformal map is entirely represented by the real and imaginary parts of an analytic function that can be evaluated spectrally from the surface. We apply the formulation to waves generated by horizontal submarine landslide motion and characterize particle displacements throughout the fluid as functions of the initial particle position and Froude number. Our findings identify distinct regions in which particle motion is predominantly associated with the moving seabed, the generated wave, or the combined action of both. The results reveal a transition in the dominant mechanism driving particle motion: at low Froude numbers, particle displacements are primarily associated with the moving seabed, whereas at high Froude numbers the generated wave becomes increasingly dominant, particularly near the free surface and away from the obstacle path.The numerical predictions are benchmarked against laboratory data available in the literature, showing good agreement and providing a quantitative assessment of the model accuracy. Moreover, laboratory topographies beyond those considered here can be readily incorporated into the numerical framework through a Hermite interpolation procedure.
Read the full abstract ▾
All authors João Vitor P. Poletto, David Andrade, Marcelo V. Flamarion, Roberto Ribeiro-Jr
Machine Learning
PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints
Bashir Zeimarani, Alireza Khatib, Somayeh Mousavinasr et al. (+1 more)
Brazil's Pix settles about 5.9 billion instant, irreversible transfers a month. A fraudulent transfer can be recovered only while the funds remain in a traceable account, and in 2025 the Central Bank's recovery mechanism (MED) returned 9% of accepted contested value. Interdiction therefore has to happen before settlement, by routing each transaction to pass, human review or block, under a finite analyst team and a regulatory hold window. To our knowledge no public simulator jointly models irreversible settlement, a regulated recovery mechanism, downstream fund dispersal and capacity-constrained review. We present PixSim, an open-source simulator of the Pix rail with these elements, calibrated to Banco Central do Brasil open data, with every parameter sourced, calibrated to one published observable, or registered as an assumption. With the model frozen, full-scale runs reproduce the 2025 recovery rate within 0.006 and its decomposition within 0.02; the February-April 2026 window is reported as a misfit and the May 2026 tracing regime as a projection. On a
benchmark with a payer-side scorer, four reference policies and ten scenarios, within the simulated mule model: recovery after settlement is constrained by dispersal speed; staffing by the arrival profile cuts a fixed rule's alert expiry from 52% to 2% at constant hours; halving the team removes a fixed threshold-and-block rule's advantage over a queue-aware rule, on loss and on loss plus false-block harm (+0.106 of victim value, positive on all twenty paired seeds), while a reversal at two thirds of the team was not confirmed on independent seeds; and a synthetic scorer of held-out AUC 0.82 cuts lost value by about a quarter. Code and data: https://doi.org/10.5281/zenodo.22948895
Read the full abstract ▾
All authors Bashir Zeimarani, Alireza Khatib, Somayeh Mousavinasr, Carlos Maurício Serodio Figueiredo
Cryptography and Security
A Large-Scale Empirical Study of Modern Phishing Email Content
Jaehwan Park, Woonghee Lee, Fujiao Ji et al. (+1 more)
Phishing remains one of the most pervasive threats to Internet users, and email remains its predominant delivery channel. Email content is the attack surface of phishing: it is what the victim reads and what automated defenses inspect. Yet the composition of modern phishing content is poorly measured. Prior work has characterized dimensions such as theme, call-to-action (CTA), and impersonation, but not at scale, and their associations and temporal changes remain unclear, owing to small or source-specific corpora, bag-of-words topic models, and a focus on text alone. We present a content-focused measurement study of 2.9M distinct real-world phishing emails collected over 13 months (June 2025 - June 2026) in collaboration with the Anti-Phishing Working Group (APWG). We treat each email as a composite artifact comprising message text and its attachments: 272K images, 143K PDFs, and 57K calendar invitations. Using an LLM pipeline validated against human-annotated samples, we analyze these components along three dimensions (theme, CTA, and impersonation), examine the associations among them, and measure longer-term change against a historical
dataset. We find that attackers diversify what they use to deceive but converge on how victims should respond: no theme exceeds 21.3% of emails, while a single CTA, URL
navigation, accounts for 73.0%. CTA and impersonation choices are conditioned on theme. Attachments play three roles: images supplement the message text, PDFs substitute for it by carrying the pretext, and calendar invitations reinforce it by replicating interaction endpoints into a persistent medium. Over the longer term, the dominant CTA for invoice-themed phishing shifted from URL
navigation to offline communication, rising from 6.7% in 2015 to 46.9% in 2025.
Read the full abstract ▾
All authors Jaehwan Park, Woonghee Lee, Fujiao Ji, Doowon Kim
Computer Vision
Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
Enzhi Zhang, Du Wu, Rui Zhong et al. (+18 more)
Self-supervised pre-training with
Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random masking is poorly matched to the structured, multi-scale morphology of scientific data, while uniform tokenization produces prohibitively long sequences that make $O(N^2)$
attention impractical. We propose SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images. SGMA couples two components: a content-adaptive quadtree tokenizer that compresses gigapixel images into a fixed-length sequence, and a structure-conditioned masking process that biases reconstruction toward spatially informative regions. To stabilize this process across scales, we introduce Damped Accumulation (DA), which aggregates signal-dependent responses across the tree into a structure canvas used to guide masking. The resulting pre-training task preserves fine microstructure while remaining compatible with standard ViT encoders and MAE-style reconstruction. Across electron microscopy, whole-slide optical microscopy, and X-ray CT
datasets, SGMA consistently outperforms MAE baselines. It achieves 95.68% Dice on the 8K x 8K x 28K SpringXCT
dataset, improving over the same-architecture MAE baseline by +13.00 points, and 83.21% Dice on the 32K^2 WSI PAIP
dataset, improving by +16.84 points, while providing up to a 24.8x inference speedup.
Read the full abstract ▾
All authors Enzhi Zhang, Du Wu, Rui Zhong, Cong Ma, Isaac Lyngaas, Amir Koushyar Ziabari, Xiao Wang, Peng Chen, Tao Luo, Toshio Endo, Fumiyoshi Shoji, Kento Sato, Kentaro Uesugi, Takayuki Nonoyama, Ryuji Kiyama, Masahiro Yoshida, Masaru Tezuka, Tetsuya Ishikawa, Satoshi Matsuoka, Masaharu Munetomo, Mohamed Wahib
Computational Engineering
Simulation-Efficient Analog Circuit Yield Optimization via Monte Carlo Zeroth-Order Gradient Estimation
Liyan Tan, Yequan Zhao, Ben F. Jamroz et al. (+2 more)
Yield optimization under process variation is expensive because each candidate design must be evaluated across many Monte Carlo SPICE samples. The resulting finite-sample yield is also piecewise constant in the design parameters, providing little local information for optimization. We introduce zeroth-order Monte Carlo
stochastic gradient descent (ZO-MC-SGD), a black-box method that converts continuous specification margins into
stochastic descent directions. Each update evaluates opposite design perturbations under shared process samples, allowing a small simulation batch to estimate a local direction without differentiating SPICE or fitting a global surrogate model. A Spearman rank-correlation test checks that the margin-based loss orders designs consistently with empirical yield. We prove that the
estimator is unbiased for a Gaussian-smoothed surrogate and derive variance and sample-complexity bounds with no explicit dependence on process dimension. Across five analog
circuit benchmarks with up to 30 design variables and 42 process variables, ZO-MC-SGD reaches a mean yield of 0.95 on four
circuits within 50–200 simulations and the empirical yield ceiling on the fifth. Relative to the best of five black-box and learning-based baselines, it reduces the required simulation budget by up to a factor of eight.
Read the full abstract ▾
All authors Liyan Tan, Yequan Zhao, Ben F. Jamroz, Ari Feldman, Zheng Zhang
Robotics
Can a Robot Read Braille? - Learning to Adapt Contact via Imitation Learning for Tactile Braille Recognition
Xi Chen, Yunlong Shan, Sihan Chen et al. (+7 more)
For people who are blind, touch provides an essen-tial channel for accessing written information through Braille. Bringing a similar capability to
robots requires them not only to recognize tactile patterns, but also to actively establish physical contact that makes those patterns readable. Yet existing robotic Braille readers largely focus on recognition after contact, leaving contact establishment itself insufficiently addressed. We present an adaptive-contact framework for robotic tactile Braille reading that assesses contact quality and physically corrects unsuitable contact before recognition and reconstruc-tion. Multi-Head Policy Learning uses expert-guided contact-adjustment demonstrations to jointly learn contact acceptability and pose corrections. During deployment, the
robot iteratively evaluates and re-establishes contact, retaining reliable tactile observations for pose-aware fusion and Braille reconstruction. Across 20 physical Braille plates used for learning and eval-uation, the proposed approach achieves 94.0% tactile quality and 88.6% tactile reconstruction on the ten online-evaluation plates. These results demonstrate the importance of actively establishing readable contact, rather than relying solely on recognition under imperfect tactile observations, for reliable robotic Braille reading.
Read the full abstract ▾
All authors Xi Chen, Yunlong Shan, Sihan Chen, Jun Hu, Zhongxuan Li, Shiyao Zhang, Sichao Liu, Zhong Zhao, Kosta Jovanovic, Peng Zhou
Computational Engineering
SkillRefine: Cross-Source Skill Induction and Execution Validation for LLM Agents in Refinery Planning Software
Dongxiao Liu, Boren Zhu, Yuwen Ding et al. (+3 more)
Operating industrial planning software such as AspenTech PIMS (Process Industry Modeling System) requires an LLM
agent to combine structural knowledge, procedural knowledge from expert records, and constraints revealed only during execution. These evidence sources are heterogeneous and individually incomplete: documentation describes tables and interfaces but omits task-level coordination, expert CASE records expose multi-table modification patterns without explicit schema grounding, and execution feedback reveals latent constraints only when a plan is executed. We present SkillRefine, a framework that exploits the Documentation–Practice Gap between documented structure and expert practice to extract candidate coordination patterns, ground them against table definitions and COM specifications, and compile them into progressively disclosed skill packages with provenance. The library is then refined through label-free compliance screening, oracle-based match decomposition over table, row, column, and value dimensions, and signal-conditioned trajectory attribution for localized repair. We evaluate SkillRefine on PIMS-Bench, a
benchmark built from two AspenTech PIMS demonstration models, using disjoint construction and held-out test tasks. On the held-out test set, SkillRefine achieves absolute component match F1 gains of 14%–30% across four LLM backbones, with the largest gains on complex multi-table coordination tasks.
Read the full abstract ▾
All authors Dongxiao Liu, Boren Zhu, Yuwen Ding, Linghui Li, Lei Li, Xiaoyong Li
Emerging Technologies
Highly Scalable Selectorless Cryogenic Memory Array Using Ferroelectric Josephson Field-Effect Transistors
Saheeb Ahmad and Shamiul Alam
Scalable
memory systems that satisfy the temperature, speed, and energy requirements of cryogenic environments are essential for the development of large-scale
quantum computers. They may also benefit high-performance computing and space applications. However, existing cryogenic
memory technologies often suffer from limited scalability, low operating speed, and/or high power consumption, restricting the scalability of target applications. Ferroelectric Josephson field-effect transistors (Fe-JoFETs), which combine ferroelectric polarization with the superconducting properties of Josephson junctions, offer a promising solution. The ferroelectric layer enables nonvolatile storage capability, while the Josephson junction supports high-speed, energy-efficient operations. In this work, we leverage Fe-JoFETs to develop a highly scalable, ultra-low-power, nonvolatile cryogenic
memory array that does not need additional selector devices for random access. Moreover, the superconducting component of Fe-JoFET provides a binary decision during read, eliminating the need for sensing peripheral circuitry. We first develop a physics-based Verilog-A compact model for Fe-JoFETs and use it to verify the functionality of the proposed
memory array. By eliminating both selector and sensing circuitry, the proposed
memory architecture offers higher scalability than existing technologies. The ultra-low-power operation of this
memory also makes it compatible with strict power budgets of cryogenic applications.
Read the full abstract ▾
Computation and Language
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
Yibo Ma, Qianqian Zhang, Peng Liu et al. (+1 more)
Streaming
video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how responses are triggered. As a result, similar scores may correspond to different workloads, failure modes, and operational behavior. We introduce TRACE (Temporal Audit and Condition-aware Evaluation), a condition-aware
benchmark and evaluation framework that makes these factors explicit. TRACE combines temporally audited visual tasks with evidence timing and instruction-dependent trigger annotations, a unified causal Core–Adapter protocol that controls information availability while recording actual history processing and response events, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. On 1,240 records from 517
videos, we evaluate eight publicly available models or systems in eight configurations. We find that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms (responses emitted while no target window is currently valid and a later one remains), and missed target windows. These results show that streaming-
video performance should be interpreted as execution-conditioned system behavior rather than a single score. Our
benchmark and code can be accessed at \href{https://github.com/om-ai-lab/trace-bench}{https://github.com/om-ai-lab/trace-bench}.
Read the full abstract ▾
All authors Yibo Ma, Qianqian Zhang, Peng Liu, Tiancheng Zhao
Computer Vision
StarWM: Self-Supervised Trained Attention Routing for Robust World Models
Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte et al. (+4 more)
A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-
attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic
video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential
video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential
video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms StarWM preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors.
Read the full abstract ▾
All authors Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte, Daniel Schmid, Sebastian Gottwald, Arne Peter Raulf, Daniel Alexander Braun
Artificial Intelligence
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
Dongsheng Xiao, Zeyuan Wang, Xuzhe Xia et al. (+2 more)
Large
language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project-level executive control.
Agents may continue acting after the original objective is satisfied, producing low-value refinements, repeated verification, and repairs to self-created complexity. We use LLM Parkinsonism as a narrowly defined, non-clinical metaphor for this pattern of persistent action despite diminishing task-level value. We argue that the problem is not explained by autoregressive next-
token prediction alone, but more directly by concentrating proposal generation, scope interpretation, progress assessment, and stopping authority within the same self-conditioned loop. We therefore introduce Global Executive Control (GEC) v0.2, an uncertainty-aware governance architecture that separates action generation from project-level control. In a 24,000-episode matched-candidate
benchmark under a common 40,000-
token ceiling, a first-candidate baseline achieved 67.42% hard-goal success, a candidate-set local control achieved 96.53%, and GEC achieved 96.57%. The candidate-set control shows that access to multiple candidate actions explains most of the success gain; relative to that control, GEC preserved success while reducing mean
token use from 19,782 to 12,574 (36.4%) and restricted mean
tokens to completion at the 40,000-
token ceiling from 16,136 to 13,114 (18.7%), while eliminating measured pre-completion drift and sharply reducing gross complexity. Governance-overhead sensitivity remained favorable through an additional 500 synthetic governance
tokens per cycle. These mechanistic simulations support explicit governance of scope, evidence, resource use, and stopping, while live-model validation remains necessary.
Read the full abstract ▾
All authors Dongsheng Xiao, Zeyuan Wang, Xuzhe Xia, Bo Zhao, Yankai Cao