arXiv:2606.24979v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are increasingly employed in urban inspection tasks, where reliable communication is critical but challenging due to the severe spatial channel heterogeneity. To address the issue, in this paper, we focus on the communication-aware path planning for multi-UAV tasks, and propose a channel knowledge map (CKM)-driven trajectory planning framework which integrates the channel modeling and trajectory decision-making. Specifically, we apply the diffusion model to construct a time-accumulated CKM and achieve the accurate perception with low flight overhead, which leverages the sparse observation data to reconstruct the high-fidelity global channel quality distribution. Based on the CKM, we propose a global-to-local graph attention network soft actor-critic algorithm. The graph attention network optimizes the complex combinatorial node ordering problem, generating an optimal and communication-aware sequence for the inspection targets. Subsequently, the soft actor-critic algorithm performs continuous action control to ensure the smoothness of the flight path and dynamically avoid communication attenuation areas. Simulation results demonstrate that the proposed method effectively guides UAVs through high-quality channel regions without dependence on real-time channel feedback, significantly improving both the trajectory efficiency and communication reliability.
Science Journals
arXiv:2606.25151v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) embed governing equations in their loss function, enabling mesh-free solutions to partial differential equations. Low training loss is treated as evidence that the learned solution is physically correct. This paper shows that assumption breaks down when encoded physics are incorrect. By perturbing PDE parameters before training, a setting we describe as physics parameter poisoning or parameter misspecification, we produce models that train to low loss but give incorrect answers; we treat the perturbation schedule as sensitivity analysis rather than only as a security threat, and none of our claims requires an adversary. Achieving low residual loss does not discriminate accurate from inaccurate solutions: poisoned models reach losses at or below the clean baseline yet differ by large margins, so driving the residual down is not evidence of physical accuracy. Across three PDE systems (Burgers equation, Navier-Stokes cavity, and convection-diffusion), poisoned models match or beat the clean-model training loss while their solutions differ by up to 71% in the fixed sweep and up to 128% under adversarial search; at Cavity Re=400 the poisoned loss falls below the clean baseline. We define a detection difficulty ratio R (solution error divided by training loss) to summarize how invisible the corruption is, though cross-PDE comparison is complicated by differences in loss scale. We test six candidate defenses, none of which reliably detects corruption across all regimes. We propose a post-hoc defense: sweeping the PDE residual loss across parameter values without retraining. The loss minimum recovers the true training parameter without external data, and generalizes across all three PDE systems. The effect holds across five network architectures (8.7K to 133K parameters), is bidirectional, and is confirmed across multiple random seeds.
arXiv:2606.25167v1 Announce Type: new Abstract: The channel flow of a liquid metal driven by a rapidly varying applied magnetic field is analyzed. The flow configuration, physical properties, and parameters correspond to a duct within a liquid-metal blanket of a nuclear fusion reactor under off-normal plasma conditions, such as plasma disruptions. The problem is solved numerically using a one-dimensional flow approximation. The longitudinal magnetic field, decaying at a typical rate on the order of 100 T/s, induces eddy currents that interact with a steady wall-normal magnetic field, generating the Lorentz force that drives the flow. Standing Alfv\'en waves are identified as the key mechanism controlling the liquid metal's response. These waves manifest as large-amplitude, gradually decaying oscillations of velocity, the induced magnetic field, and eddy currents. A parametric study predicts a severe response developing within the first few milliseconds of the event, with maximum flow velocities reaching several meters per second and Lorentz forces exceeding $10^9 \text{ N/m}^3$. Power-law approximations for the dependencies of the response characteristics on the flow parameters are developed. Finally, the effects of fluid compressibility and pressure waves are analyzed and found not to lead to a major modification of the flow evolution.
Co-designing a Preliminary Repository of Augmented Reality Concepts for Real-Time Emotion Regulation
arXiv:2606.25271v1 Announce Type: new Abstract: Augmented Reality (AR) can be a positive therapeutic approach to support mental health and emotion regulation. Although AR techniques for therapeutic support exist, there is no user-centered, expert-informed understanding of how real-time AR designs can support people in emotional distress without disengaging them from their ongoing activities. This lack of reusable design resources hinders the adoption of AR for mental health support. This paper addresses this gap by introducing a co-designed collection of AR interventions describing how this technique can support real-time emotion regulation. The repository was created following a two-phase participatory design process. Phase 1 recruited 40 anxiety-prone individuals and used the Nominal Group Technique to list ideas on how AR affordances could support emotion regulation. Phase 2 recruited 10 mental health professionals to organize these ideas into thematic clusters and assess their clinical feasibility. The resulting AR design repository, grounded in user perspective and clinical expertise, identifies eight thematic clusters and 106 design ideas. This work represents a first step towards the development of seamless real-time AR interventions for mental health.
arXiv:2606.25320v1 Announce Type: new Abstract: Since the 1990s, advancements in big data and information technology have increasingly driven data-centric research in the field of Library and Information Science (LIS). To assess the influence of this data-driven research paradigm on the LIS discipline, this study conducts a fine-grained analysis to uncover the evolutionary trends of research methods within the domain. Using academic papers from LIS published between 1990 and 2022, four key categories of data-driven method entities are automatically extracted: algorithms and models, data resources, software and tools, and metrics. Based on these entities, the study examines the evolution of LIS research methods from three dimensions: the characteristics of research method entities over time, their evolution within different research topics, and the evolutionary features of research method entities across various research methods. The findings highlight data resources as a pivotal driver of methodological evolution in LIS, revealing a cyclical pattern of "emergence-stability/practical application" in the development of research methods within the field.
arXiv:2606.25272v1 Announce Type: new Abstract: Code clone detection has been extensively studied for decades, and recent approaches have begun reporting remarkably high performance for semantic (Type-4) clones on benchmark datasets. However, it remains unclear whether these results reflect a genuine ability to capture semantic equivalence between programs, or simply an ability to exploit dataset-specific patterns. In this paper, we present the first systematic empirical study investigating the generalizability of state-of-the-art (SOTA) semantic code clone detectors beyond benchmark evaluation settings. Inspired by the inherent inclusion relationship among clone types, we propose a clone operator framework consisting of eight transformation operators derived from Type-2 and Type-3 clone variations. Using these operators, we construct distribution-shifted yet semantically equivalent Type-4 clone instances and evaluate 11 representative detectors spanning token-based, tree-based, and graph-based paradigms on the real-world BigCloneBench dataset. Our results reveal substantial performance degradation across all evaluated approaches, despite their strong benchmark performance. Further analyses show that existing detectors heavily rely on shortcut learning based on lexical and structural cues rather than robust semantic understanding. Our findings suggest that current SOTA semantic code clone detectors exhibit limited generalizability in real-world scenarios, highlighting important avenues for future research.
arXiv:2606.25279v1 Announce Type: new Abstract: Manual reporting of 3D MRI studies is time-consuming, yet end-to-end structured report generation for 3D liver MRI remains underexplored due to volumetric complexity and scarce paired data. We propose MRI2Rep, an autoregressive framework for liver MRI report generation. From 3,929 real-world MRI-report pairs acquired over a 10-year single-institution cohort, a Report-to-Label Canonicalization (RLC) module converts free-text reports into structured, closed-vocabulary diagnostic sequences without lesion-level annotations. On a held-out test set, MRI2Rep achieves 76.0% case-level sensitivity, 29.4% lesion-level F1, compared with no more than 8.3% for adapted medical vision-language baselines, and 82.4% liver-level accuracy. In a blinded reader study, two radiologists rated 75% and 70% of AI-generated reports as clinically acceptable, compared with 95% and 100% for original reports. Our automated LLM-based judge, LLM-Eval, rated 61.8% of AI-generated reports as acceptable, applying a stricter standard and supporting its use as a conservative proxy. To our knowledge, this is the first end-to-end LI-RADS-structured reporting system for 3D liver MRI.
arXiv:2606.25284v1 Announce Type: new Abstract: Camera-based monitoring systems are increasingly adopted in healthcare settings for the continuous assessment of patient movement and activities. However, their technical performance under real-world indoor conditions remains insufficiently characterised, preventing appropriate camera selection for clinical or home adoption and reproducibility. Existing validation studies typically assess either device metrological performance or algorithm accuracy in isolation, and often do not systematically account for practical deployment factors, such as lighting variability, occlusions, and camera positioning. We present two technical validation protocols: the first evaluates the metrological performance of RGB and RGB-D cameras, and the second assesses their use in supporting human pose estimation, validated using state-of-the-art pose estimators. The proposed protocols systematically assess five cameras, four RGB-D and one RGB, under controlled variations in lighting, camera height, viewing angle, and occlusion level within representative indoor scenarios. The experimental results show that metrological performance varies substantially across cameras, with depth bias at 5 m ranging from 50 mm to over 1400 mm depending on the device. For 2D pose estimation, all cameras achieve broadly comparable accuracy, with mean mAP between approximately 78% and 90% across cameras and estimators, whereas 3D reconstruction error differs markedly across devices, with MPJPE ranging from 104 mm to 365 mm, closely reflecting underlying depth-sensing quality. Environmental factors have a camera- and estimator-dependent effect on 3D performance, while camera mounting height has minimal influence within the evaluated range. This work provides evidence-based guidance for the selection and deployment of cameras in healthcare monitoring applications, addressing an important gap in current technical validation practice.
arXiv:2606.25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideally induce an Attention-Compatible Geometry for self-attention: not merely describing graph structure, but defining a geometry whose inner products reflect meaningful structural relatedness. To realize this geometry, we propose Communicability-Inspired Positional Encoding (CIPE), built from communicability, a measure between pairs of nodes that aggregates contributions from paths of all lengths. By construction, CIPE inner products recover communicability, converting global multi-path connectivity into an attention-ready similarity geometry. For practical Transformer training, we introduce dimensionality alignment, mapping graph-size-dependent CIPE representations to prescribed dimensions while faithfully preserving the induced geometry. Empirically, CIPE improves structure-agnostic Transformers by 35.5% on average across seven benchmarks, outperforming representative PEs; it also consistently improves structure-biased graph Transformers, where competing PEs often yield only marginal benefits. These results position CIPE as a principled framework for attention-compatible graph positional encodings.
arXiv:2606.25301v1 Announce Type: new Abstract: Machine learning (ML) techniques have been commonly adopted to identify the dynamics of building energy systems (BESs), owing to their flexibility relative to first-principles, physics-based modeling approaches. Beyond the choice of ML architecture, the quality of the training data plays an essential role in the resulting model performance. Optimal experimental design (OED), realized in this work through active learning (AL), determines which experiments to conduct in order to collect informative data, rather than relying on standard approaches such as uniformly random sampling. This paper proposes a systematic comparison of OED via AL for building energy system identification, with a particular focus on HVAC thermal dynamics. We investigate fourteen AL techniques across two ML model classes, namely a deterministic feedforward neural network and a stochastic Gaussian process, and classify these techniques into four categories: data space, uncertainty, information gain, and model change. To examine the AL algorithms under realistic conditions, we implement and evaluate them on the high-fidelity building simulator BOPTEST. The results, reported as the root mean square error across multiple test scenarios with varying initial dataset sizes and control input constraints, show that AL-based models generally outperform models trained via passive learning (PL) with uniformly random control inputs, achieving error reductions of up to 54\%, although the magnitude and consistency of this improvement vary across acquisition functions and operating regimes.
arXiv:2606.25351v1 Announce Type: new Abstract: This paper studies the secrecy capacity of a class of degraded broadcast channels in the presence of an external eavesdropper, where a transmitter aims to deliver two independent confidential messages to two legitimate receivers. The transmitter is assumed to have non-causal access to the channel state information (CSI), and each legitimate receiver possesses prior knowledge of the other receiver's message, referred to as receiver message side information (RMSI). We consider two distinct scenarios: complementary RMSI, where each receiver knows only the other's message, and non-complementary RMSI, where the side information does not perfectly align. For both scenarios, we derive novel inner bounds on the achievable secrecy rate region and present tight outer bounds, establishing the secrecy capacity region for the considered degraded channel settings. Unlike prior works, which primarily address general broadcast settings without secrecy constraints or omit key interactions between RMSI and CSI, our results provide a complete characterization of the secure communication limits under these conditions. Moreover, we extend our analysis to the Gaussian degraded broadcast channel, highlighting the pivotal role of CSI in enhancing secure transmission performance. Our findings demonstrate that the combination of RMSI and CSI can be strategically leveraged to expand the secrecy capacity region, thus offering new insights into secure multiuser communication system design.
arXiv:2606.25327v1 Announce Type: new Abstract: We developed a nanosecond-resolved 266 nm Mach-Zehnder interferometer for electron-density measurements of dense laser-produced plasmas generated in 100-bar supercritical-fluid (SCF) helium. A 1064 nm pump pulse was focused into the SCF helium medium, and the plasma-induced phase shift of a 266 nm UV probe beam was recorded using an ICCD-based interferometric imaging system. Plasma-arm-only and reference-arm-only images were used to normalize raw interferograms and improve the effective fringe visibility. The corrected interferograms were analyzed using a two-dimensional Fourier-transform method to reconstruct phase-shift maps, which were converted into line-integrated electron-density distributions through the plasma dispersion relation. Assuming cylindrical symmetry, Abel inversion was applied to the plasma with the largest line-integrated electron density, yielding a maximum local electron density of approximately \(2.5\times10^{18}~\mathrm{cm^{-3}}\). The measurement fidelity was evaluated by considering free-free absorption of the probe beam, probe-beam refraction by plasma electron density gradients, and effect of finite-collision-frequency effects on the plasma dielectric response. These estimates indicate that the inferred electron density is not altered by more than an order of magnitude under the present experimental conditions. The present system demonstrates the applicability of 266 nm UV interferometry to nanosecond-resolved density diagnostics of dense plasmas in high-pressure supercritical fluids.
arXiv:2606.25329v1 Announce Type: new Abstract: State Space Models (SSMs), designed for long-range modeling, offer linear computational complexity and strong capabilities in capturing long-range dependencies. In the field of remote sensing, SSMs have gained popularity due to their effectiveness in addressing unique challenges such as dense visual predictions, multi-modal remote sensing data, and temporal remote sensing data, which have also yielded significant advancements in customized architectures. This paper presents a comprehensive review of SSM-based approaches in remote sensing, covering most of the relevant studies since SSMs were first introduced to the field. We offer a multi-dimensional analysis examining SSM applications in remote sensing tasks and discussing advancements in architecture design. This paper not only synthesizes the rapid progress in SSM-based research but also identifies key challenges and future opportunities. By providing a detailed perspective, this paper aims to serve as a foundational resource for remote sensing researchers, offering actionable insights to foster further advancements in this evolving domain. We will keep tracing related works at https://github.com/QinzheYang/Awesome-RS-State-Space-Model.
arXiv:2606.25331v1 Announce Type: new Abstract: Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present \emph{iLLaDA}, an 8B masked diffusion language model trained from scratch with fully bidirectional attention. iLLaDA keeps the masked diffusion objective throughout pre-training and supervised fine-tuning (SFT), scaling pre-training to 12T tokens and fine-tuning on a 25B-token instruction corpus for 12 epochs. We further use variable-length generation for efficiency and introduce confidence-based scoring for multiple-choice evaluation. Compared with LLaDA, iLLaDA improves broadly across general, mathematical, and code benchmarks; for example, iLLaDA-Base improves by 21.6 points on BBH and 14.9 points on ARC-Challenge, while iLLaDA-Instruct improves by 14.5 points on MATH and 16.5 points on HumanEval. Despite its non-autoregressive training, iLLaDA also remains competitive with Qwen2.5 7B on several benchmarks. These results show that fully bidirectional diffusion training from scratch is a competitive path toward strong language models. Model weights and codes: https://github.com/ML-GSAI/LLaDA.
arXiv:2606.25332v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error cascading: failures in early reconnaissance can mask an agent's actual ability to exploit vulnerabilities. To more accurately characterize these capabilities, we propose a two-stage decoupled evaluation framework that separates exploit execution from reconnaissance. Using ground-truth injection and knowledge-driven ablation across 70 high-fidelity web vulnerability testbeds, our framework isolates exploitation performance from reconnaissance noise. We empirically evaluate five open-source penetration-testing agents, covering multiagent, monolithic, and graph-driven architectures, on a strictly aligned subset of 50 representative vulnerabilities. The results reveal a substantial capability gap. With accurate vulnerability context, agents achieve a functional success rate of up to 90.0%, whereas autonomous reconnaissance, measured by targeted vulnerability recall, plateaus at approximately 50.0%, primarily due to failures in parsing unstructured telemetry. Cross-architectural analysis further reveals distinct capability niches: multi-agent isolation is more effective for long-sequence interactions such as de-serialization, while monolithic and graph-driven designs perform better on short-chain injections and cross-session access-control vulnerabilities, respectively. This decoupled evaluation work provides a fine-grained benchmarking protocol and an empirical basis for designing next-generation automated offensive security agents.
arXiv:2606.25335v1 Announce Type: new Abstract: Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances. We trace this issue to stagnant neurons, units whose gradient updates become negligibly small relative to their weights, thereby hindering learning. While existing plasticity injection methods exist, they prove ineffective for such neurons. To address this, we propose Knowledge-retentive Neuron-level PlastIcity Focusing InjEction (KNIFE), a novel method that directly targets stagnant neurons. KNIFE replaces each stagnant neuron with a composite unit comprising three specialized components: a frozen knowledge neuron to preserve acquired knowledge, a re-initialized active neuron to restore learning capacity, and a compensation neuron to ensure the combined output matches the original, thus maintaining previous learned cooperation knowledge. Extensive experiments on SMACv2, predator-prey, and matrix games demonstrate that KNIFE significantly outperforms state-of-the-art plasticity injection methods.
arXiv:2606.25295v1 Announce Type: new Abstract: Mobile manipulation is a fundamental robotics task and has advanced rapidly in recent years, enabling robots to navigate, reach, and interact with objects in complex environments. However, mobile manipulation of dynamic objects remains highly challenging, as robots must coordinate the mobile base and arm while adapting to continuously evolving target poses. A key challenge lies in predicting temporally consistent short-horizon grasp trajectories from dynamic observations. In this work, we propose \ours{}, a dynamic mobile manipulation framework that couples instantaneous grasp trajectory prediction with whole-body control policy. Our predictor uses an anchor-based diffusion model to generate temporally consistent short-horizon grasp trajectories conditioned on historical observations. The predicted trajectories are then encoded as compact features and fed to a whole-body reinforcement learning policy, which controls the mobile manipulator for dynamic grasping. We further introduce a anticipation-guided reward that equips the policy with an anticipatory grasping horizon by adaptively shifting the target from the current grasp observation to the instantaneously predicted grasp trajectory. Through extensive experiments in Isaac Gym simulation, we show that our method achieves strong performance in mobile manipulation of dynamic objects across diverse settings and grasping metrics. Furthermore, our predictor and policy demonstrate strong generalizability in real-world experiments.
arXiv:2606.25456v1 Announce Type: new Abstract: Brain-Computer Interface (BCI) based on electroencephalography (EEG) enables direct interaction between the brain and external environments and has significant applications in assistive technologies, medical rehabilitation, and entertainment. Recently, EEG decoding methods based on Symmetric Positive Definite (SPD) learning have demonstrated superior performance. However, these methods typically employ basic network architectures and do not explicitly capture local relationships between EEG signals. This limitation is problematic for EEG signals due to their inherently low Signal-to-Noise Ratio (SNR). Moreover, most existing Riemannian manifold-based methods are restricted to specific metrics. The most widely used is the Affine-Invariant Metric (AIM). However, it has a quadratic dependency on the SPD matrices and cannot handle ill-conditioned SPD matrices, which hinders the effectiveness of networks. In contrast, the Bures-Wasserstein Metric (BWM) exhibits linear dependence on SPD matrices and demonstrates superior performance for ill conditioning. To overcome these challenges, we propose a Riemannian self-attention network based on the BWM. Additionally, the recently introduced power-deformed generalized Bures-Wasserstein metric reveals a nonlinear relationship between SPD matrices and matrix power deformation. This metric provides a more nuanced representation of the geometric structure of the SPD manifold. Consequently, we extend our model to a learnable version. For simplicity, we refer to it as GBWAtt. Experimental results on three EEG benchmarking datasets validate the robustness and effectiveness of our proposed method. The code is available at https://github.com/jissc/GBWAtt.
arXiv:2606.25388v1 Announce Type: new Abstract: Reliable analytics and machine-learning pipelines depend on clean tabular data, yet production tables often contain missing values, typographical errors, inconsistent formats, violated dependencies, unit mismatches, and ambiguous categorical values. Existing cleaning systems make different trade-offs. Constraint-based systems need experts to specify rules. Learning-based systems need labels or retraining. Recent LLM-based cleaners reduce setup effort, but many call an LLM on rows, cells, or repeated workflow steps, so their cost grows with table size and with every recurring batch. We present TabClean, a model-training-free system that compiles LLM reasoning into reusable guarded cleaning programs. Given a dirty table and a small annotated development set, TabClean profiles table evidence, diagnoses repair mechanisms, synthesizes executable Python transformations, validates candidates with cell-level feedback, and commits the best program for reuse on schema-compatible batches. The key abstraction is an evidence-backed guarded repair clause. A deterministic transformation may fire only when its dirty pattern, target-negative condition, evidence support, and scope constraints are satisfied. Across six benchmarks, TabClean achieves high precision, improves F1 over representative rule-based, learning-based, and LLM-based baselines on five datasets, and substantially reduces recurring runtime and API cost by replacing repeated LLM inference with deterministic program execution.
arXiv:2606.25391v1 Announce Type: new Abstract: Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes. Real-world auditory interpretation requires Context-Aware Auditory Scene Understanding (CASU): the ability to comprehend the holistic scene by integrating sound layers. To evaluate this capability, we introduce the CASU benchmark, which assesses whether Audio LLMs can interpret auditory scenes composed of speech, acoustic events (e.g., announcements), and background environments (e.g., traffic), and reason about the logical relationships between these layers. We propose a scalable pipeline for constructing time-accurate, semi-synthetic audio streams by composing real-world scene sounds with synthetic speech. Building on this data, we design four tasks that probe scene understanding: contextual question answering, entity extraction from the scene, speaker role inference, and counterfactual reasoning where scene is manipulated. Experiments across multiple LALMs demonstrate that effective auditory scene understanding requires integration over all auditory layers, rather than reliance on speech or sound alone, underscoring the necessity of CASU for advancing complex audio understanding in LALMs.
arXiv:2605.23434v2 Announce Type: replace Abstract: Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an explicit density $q_\phi(\bU)$ by an ELBO (DSVI, IPVI, DDVI, DBVI) or sample by MCMC (SGHMC). We instead frame DGP inference as \emph{posterior transport}: learn a deterministic sampler that maps a tractable reference measure to posterior-relevant inducing variables, regularised by a path prior derived from the Doob-bridged reference diffusion. Our realisation, \textbf{OM-Path} (formally FBVI-bridge-Path), uses Song's probability-flow ODE applied to DBVI's Doob-bridged forward SDE; the reference drift is closed-form from the bridge marginal coefficients (no score matching) and the path regulariser is the \textbf{Onsager--Machlup action}. At the finite-$\epsilon$ value used at training, the objective is the negative log unnormalised density of a tempered Doob-bridge path posterior, and Theorem 1 identifies it with the same posterior's small-noise MAP path via the Freidlin--Wentzell LDP. Two strict path-space ELBO variants on the same bridge backbone (FFJORD log-det; OM-regularised CNF) are derived as ablations. Under a matched-seed paired Wilcoxon test against DBVI on seven UCI regression benchmarks, OM-Path delivers statistically significant wins on the two largest datasets (\textit{power}: $p\!=\!0.014$, NLL $\mathbf{0.012}$ matching the DSVI baseline of $0.017$; \textit{protein}: $p\!=\!0.002$, RMSE $\mathbf{0.716}$ vs.\ $0.764$, NLL $\mathbf{1.086}$ vs.\ $1.149$), statistical ties on \textit{yacht} / \textit{qsar}, and concedes \textit{boston} / \textit{energy} / \textit{concrete} to DBVI on small-$N$ noisy data. The strict-ELBO variants do not clear DBVI on any UCI metric: in this regime, reducing the variance of the path objective dominates exact-density tracking.
arXiv:2606.25399v1 Announce Type: new Abstract: Estimating past events in wall turbulence based solely on surface measurements and first principles is an ill-posed problem that is complicated by chaos. The sensitivity of a measurement to the earlier flow state is described by the adjoint Navier-Stokes equations, which are solved in reverse time starting from the measurement kernel at the sensing position and time. The resulting adjoint field is the spatio-temporal domain of dependence (DOD) of the sensor, which is a dual to the concept of the domain of influence (DOI) of an actuator in the linearized forward equations. In channel turbulence, the energy of each adjoint realization grows exponentially in backward time according to the Lyapunov exponent, even though the energy of the ensemble average should decay. We introduce a linear eddy-viscosity closure model in the ensemble-averaged adjoint equations, and directly compute the mean DOD and compare our prediction to the ensemble average. Furthermore, we demonstrate that the DOD of a wall-stress measurement and the DOI resulting from a wall-stress perturbation exhibit respective universal behaviors across Reynolds numbers. However, their spatio-temporal structures differ qualitatively, due to the time-asymmetry of the governing equations. The DOD field has a two-part structure: one component is associated with the Orr mechanism, characterized by rapid reorientation under mean shear, and the other is related to self-similar expanding streaky structures. These two components jointly define the sensitivity of the wall-stress measurement to past flow events.
arXiv:2606.25402v1 Announce Type: new Abstract: Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLMs: they must maintain knowledge of multiple API versions, not merely the latest or most common one. However, current LLMs are trained on temporally mixed corpora and lack explicit mechanisms for such version-specific reasoning, leading to anachronistic errors - calling APIs as they exist in a different library version. To systematically evaluate this phenomenon, we introduce LibEvoBench, a multi-task benchmark spanning multiple versions of widely used Python libraries, along with a new metric, the Software Evolution Understanding Score (SEUS), to measure models' consistency when working with evolving APIs. Our results show that state-of-the-art models are largely version-oblivious: performance degrades for evolving APIs, while for stable APIs it remains the same across versions. Moreover, simply specifying the target version provides no benefit, while relevant documentation significantly boosts models' accuracy. These findings highlight a systematic limitation of current training paradigms and motivate new approaches for temporally grounded knowledge in code generation.
arXiv:2606.25276v1 Announce Type: new Abstract: Combinatorial game theory is a branch of mathematics and theoretical computer science that studies deterministic games with perfect information and no elements of chance. The majority of combinatorial games are impartial and formalized in linear integer arithmetic, which we call LIA-definable impartial combinatorial games (ICGs). This paper studies decidability and undecidability questions for these games. We prove that deciding whether an LIA-definable ICG is terminating or cyclic is undecidable in general, while the corresponding questions become decidable for terminating LIA-definable ICGs. We also show that deciding whether an LIA formula exactly characterizes the set of winning, losing, or draw states of an LIA-definable ICG is undecidable in general and decidable for terminating LIA-definable ICGs. For state-level questions, deciding whether a state is winning or losing remains undecidable even for terminating LIA-definable ICGs, but becomes decidable for terminating finite-depth LIA-definable ICGs. Finally, deciding whether a state is draw for an LIA-definable ICG is undecidable in general and decidable for terminating LIA-definable ICGs.
arXiv:2606.25404v1 Announce Type: new Abstract: Large Language Models (LLMs) can reason over complex instructions but often fail to satisfy the physical and spatial constraints required for robotic task planning. Recent LLM-based planners directly translate text into action sequences, yet they lack structured reasoning about feasibility, reachability, and logical order, resulting in invalid or incomplete plans. We present a heterogeneous multi-LLM framework that decomposes instructions into atomic reasoning tasks and allocates them to role-specialized expert agents under a token budget for real-world computational and communicational constraints. By combining role-oriented reasoning from heterogeneous agents followed by constraint-driven plan synthesis, HEART validates capability, reachability, and constraint conditions before planning and helps produce physically executable plans while maintaining efficiency. Experiments across different household benchmarks show that HEART consistently improves plan success compared to single-LLM and rule-based planners, demonstrating that heterogeneous LLM collaboration enables robust and scalable robotic task planning under resource constraints.