arXiv:2607.03768v1 Announce Type: cross Abstract: Classical training-free denoisers such as BM3D and non-local means owe much of their strength to search: content-dependent block matching whose memory traffic and data-dependent control flow parallelize poorly and preclude fixed-latency implementations. Learned denoisers reach the highest quality, but they need training data, degrade outside their training domain (which we also observe), and carry per-pixel compute budgets that effectively require a GPU. We present GALOSH (Generalized Anscombe LOcal SHrinkage), a redesign of training-free denoising that removes the search entirely and aims at multi-domain coverage, speed, and quality at once: a blind per-image Poisson-Gaussian noise fit, a generalized Anscombe transform, a two-pass local Walsh-Hadamard shrinkage of luminance, and a luminance-guided local regression of chrominance -- two deliberately different operators for the two perceptually different noise components, each with its own strength control. Every stage is local, data-independent, and regular -- the same computation graph for every pixel of every image. One core serves two domains: raw Bayer mosaics and sRGB/YUV images. On four real-noise benchmarks (SIDD Medium and RawNIND, raw and sRGB) GALOSH is consistently the strongest among the tested blind, training-free methods -- surpassing BM3D- and NLM-family baselines even when those are given an oracle noise level -- and approaches trained networks on raw data while remaining below in-domain trained networks at high ISO in sRGB. Being search-free makes it fast: 7x-650x faster than the DL baselines on the same GPU at full benchmark size, and the only strong method in the comparison that also runs practically on plain CPUs. The fixed, data-independent structure is designed to map naturally onto fixed-point and streaming hardware, supported by an operation-count analysis and a working INT16 fixed-point realization.
Science Journals
arXiv:2607.03815v1 Announce Type: cross Abstract: For compact convex sets $L,K \subset \mathbb{R}^n$, denote by $\lambda_K(L)$ the smallest size of a homothet of $K$ that contains $L$. We define a measure of symmetry based on the $n$-simplex $\Delta = \Delta^n \subset \mathbb{R}^n$ as the ratio \[ \rho_\Delta(L):=\frac{\lambda_{-\Delta}(L)}{\lambda_{\Delta}(L)}. \] We study this measure and deduce the following results: (1) The classical Minkowski measure of symmetry $m^*(L)$ can be defined as an affine-invariant version of $\rho_\Delta(L)$. (2) We improve the stability analysis for the Minkowski measure of symmetry; if $m^*(L)\ge n-\varepsilon$ then $L$ is $\tfrac{1}{1-\varepsilon}$-close to $\Delta$ in the Banach--Mazur distance. (3) We obtain a novel characterization of simplices as the only convex bodies $K$ for which the function $L \mapsto \lambda_K(L)$ is additive (a property we term ``outer additivity''). (4) Motivated by the expressivity of ReLU neural networks, we study the depth complexity of polytopes in $\mathbb{R}^n$ under the two operations: Minkowski sum and convex hull of a union. We prove the sharp bound $\rho_\Delta(P) \leq 2^d -1$ for every polytope $P$ of depth complexity $d$. In other words, simplices cannot be approximated by low-depth polytopes.
arXiv:2605.30919v2 Announce Type: replace Abstract: The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing interest in LLM unlearning. Many existing LLM unlearning approaches rely on optimizing prediction loss(es), such as maximizing the loss on the forget set, but often face critical issues like over-forgetting and poor model utility. To address them, this paper novelly frames the optimization objective for LLM unlearning as one of zeroing out data attribution instead. In particular, we propose the first LLM unlearning framework based on data attribution rewards called DareU that performs reinforcement learning to update the LLM by reducing the attribution score of its generated responses (i.e., de-attributing) to the forget data owners. Empirical evaluation using an LLM classifier as an efficient approximation of attribution shows that DareU outperforms existing baselines by achieving effective unlearning while balancing forget quality and model utility well.
arXiv:2607.04060v1 Announce Type: cross Abstract: We derive a quasi-incompressible Cahn-Hilliard-Darcy phase-field model (qCHD) with the logarithmic Flory-Huggins free energy density function for two-phase flows in porous media. The model satisfies an energy-dissipation law. In the formal sharp interface limit, the qCHD model gives rise to the classical Muskat's problem. By exploiting estimates of the pressure from Darcy's equations, we establish global existence of weak solutions in both 2D and 3D to the qCHD model.
arXiv:2607.01793v2 Announce Type: replace Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded rules, making them costly to extend as agents evolve. To this end, we present Vera, an end-to-end automated safety testing framework that instantiates software engineering testing principles for non-deterministic agents through a three-stage, self-reinforcing pipeline. First, a literature-driven exploration continuously discovers and structures emerging risks into taxonomies of safety risks, attack methods, and tool execution environments. Second, combinatorial composition across taxonomy dimensions produces executable safety cases, each specifying a concrete safety goal, a programmatically constructed initial state, and a deterministic verification predicate grounded in observable artifacts. Third, adaptive execution runs heterogeneous agents in isolated sandboxes where a control agent steers multi-turn interaction based on runtime observations, while evidence-grounded verifiers judge outcomes from environment state and tool-call evidence rather than model self-report. We evaluate Vera on four production agent frameworks (OpenClaw, Hermes, Codex, Claude Code), revealing substantial safety weaknesses, with average attack success rates reaching 93.9\% under multi-channel attacks; we also release Vera-Bench, comprising 1600 executable safety cases spanning 124 risk categories across three execution settings. These results indicate that modular, executable testing infrastructure is essential for rigorous and maintainable safety evaluation of rapidly evolving agentic systems at scale. The code is publicly available at https://github.com/Yunhao-Feng/Vera.
arXiv:2605.01259v2 Announce Type: replace-cross Abstract: The Domination game is an impartial game on graphs, introduced in 2010, and proved PSPACE-complete in the normal variant in 2026. In this game, Alice and Bob alternately select playable vertices, where a vertex is playable if it dominates at least one vertex not dominated by the vertices selected before in the game. The game ends when the selected vertices form a dominating set. In the normal variant, the player unable to move loses. In contrast to the impartial game, the partizan game has the vertices already colored with $A$, $B$, or $C$, in such a way that Alice (resp. Bob) can only select vertices colored with $A$ (resp. $B$) or $C$. The partizan game was proved PSPACE-hard in 2026. In this paper, we determine the winner of the Normal Domination Partizan game in graphs whose connected components are complete bipartite graphs or complete split graphs, including star forests, for any initial coloring of its vertices.
arXiv:2601.11923v3 Announce Type: replace Abstract: The integration of complementary medicine into oncology represents a paradigm shift that has seen to increasing adoption of Traditional Chinese Medicine (TCM) as an adjuvant to radiotherapy. About twenty-five years since the formal institutionalization of integrated oncology, it is opportune to synthesize the trajectory of evidence for TCM as an adjuvant to radiotherapy. Here we conduct a large-scale analysis of 69,745 publications (2000 - 2025), emerging a cyclical evolution defined by coordinated expansion and contraction in publication output, international collaboration, and funding commitments that mirrors a define-ideate-test pattern. Using a theme modeling workflow designed to determine a stable thematic structure of the field, we identify five dominant thematic axes - cancer types, supportive care, clinical endpoints, mechanisms, and methodology - that signal a focus on patient well-being, scientific rigor and mechanistic exploration. Cross-theme integration of TCM is patient-centered and systems-oriented. Together with the emergent cycles of evolution, the thematic structure demonstrates progressive specialization and potential defragmentation of the field or saturation of existing research agenda. The analysis points to a field that has matured its current research agenda and is likely at the cusp of something new. Additionally, the field exhibits positive reporting of findings that is homogeneous across publication types, thematic areas, and the cycles of evolution suggesting a system-wide positive reporting bias agnostic to structural drivers.
arXiv:2605.12757v2 Announce Type: replace Abstract: Generative AI is rapidly reshaping STEM higher education. Not only are our educational practices changing, but how we think about educational transformation must adapt. Existing models of institutional change in STEM, aimed at interactive engagement, have largely followed an adoption logic: relatively stable, well-researched educational practices are evaluated and then scaled. These assumptions do not hold for generative AI, which is an arrival technology -- entering classrooms before a sufficient pedagogical evidence base could form. Building on recent decades of work on STEM institutional change, we propose a framework identifying six dimensions along which prior change models must be reconsidered in light of AI: three concerning the tools at the center of reform (the tool's evidence base, rate of change, and scope), and three concerning the people involved in change (faculty, change agents, and students). For each dimension, we examine how AI-era assumptions differ from those underlying prior interactive engagement reforms and derive design implications, including: privileging humble and local inquiries; organizing reform around pedagogical approaches rather than specific tools; repositioning change agents as facilitators of collective inquiry; and engaging students as partners in reform. Collectively, the six dimensions and design implications constitute a new framework for adapting change models to support institutions under conditions of genuine uncertainty. Finally, we illustrate how the framework may be applied through a brief case-study of a faculty workshop series carried out in a university physics department to support instructors adapting to this modern AI era.
arXiv:2505.07681v3 Announce Type: replace Abstract: We present OCaml and Rocq implementations of Kaplan and Tarjan's purely functional, real-time catenable deques. The correctness of our Rocq code is machine-checked.
arXiv:2605.09575v2 Announce Type: replace-cross Abstract: Prenatal germinal matrix-intraventricular hemorrhage (GMH-IVH) is a leading cause of infant mortality and neurodevelopmental impairment, yet its manual diagnosis and lesion segmentation on fetal brain MRI are labor-intensive and error-prone. Although supervised deep learning offers potential for automation, it typically requires large amounts of annotated GMH-IVH data, which are challenging to obtain for such a rare condition (0.5-0.9 per 1000 pregnancies). To address these problems, an annotation-free deep learning framework, FreeHemoSeg, was developed for automated detection and segmentation of GMH-IVH without any real patient annotations. Instead of learning from expert labels, FreeHemoSeg was trained on pseudo GMH-IVH images synthesized from normal fetal data guided by medical priors. The framework was evaluated in a retrospective multicentre study of 1,674 stacks of 2D T2-weighted MRI from 558 pregnant women, using data from one hospital for internal training and validation and two hospitals for external validation. FreeHemoSeg achieved the highest diagnostic and segmentation performance in both internal validation (AUROC: 0.959; AUPR: 0.928; sensitivity: 0.914; specificity: 0.966; DSC: 0.559) and external validation (AUROC: 0.930; AUPR: 0.884; sensitivity: 0.824; specificity: 0.943; DSC: 0.512), outperforming a supervised model trained on limited empirical data and unsupervised anomaly detection methods. Moreover, FreeHemoSeg assistance improved radiologists' sensitivity (from 0.882 to 0.941-1.000) and diagnostic confidence, while reducing interpretation time by 16.0-52.7%. We anticipate its immediate utility in supporting earlier diagnosis, prognostic counselling, and perinatal planning for fetal GMH-IVH. Code: https://github.com/Arktis2022/FreeHemoSeg.
arXiv:2606.06253v2 Announce Type: replace-cross Abstract: Generative AI raises short-term productivity by completing tasks that learners would otherwise practice on their own. Whether this exchange erodes frontier skill depends on the mode of use: substitute-users let AI stand in for deliberate practice and fail to develop skill, while complement-users use it to accelerate skill development. For institutions that train and certify talent, the design question is not whether to allow AI but how to govern the mode of its use. We ask whether AI-prohibited evaluation gates can separate the two modes. In elite competitive programming, the International Collegiate Programming Contest (ICPC) and the International Olympiad in Informatics (IOI) prohibit AI under in-person proctoring, with qualification-round entry, whereas Codeforces (CF) practice is unproctored and open to all. From CF submission histories we build an AI-prompt signature, more first-attempt acceptances, fewer attempts, fewer debugging retries, consistent with AI-assisted practice. CF practice has shifted toward this signature across entry cohorts spanning two AI rollouts. In CF contests, a stronger signature predicts smaller rating gains for users with no ICPC-IOI affiliation, but not for those who qualified. Inside the AI-prohibited ICPC environment, a shift toward AI-style practice predicts higher non-AI-aided scores for AI-era entrants. The same signature carries opposite signs across the two environments, exactly the pattern a type-separating gate predicts. The message is constructive: AI-style practice is compatible with frontier skill; the erosion risk links to the substitute mode; and that mode is separable by gates standard at credential boundaries, from medical and legal boards to professional certification.
arXiv:2508.16239v2 Announce Type: replace Abstract: Quantitative microstructural characterization is fundamental to materials science, and electron micrographs (EMs) provide indispensable high-resolution insights. However, progress in deep learning-based analysis of EMs has been hampered by the scarcity of large-scale, expert-annotated public datasets. To address this issue, we introduce EM3M, a large-scale and multimodal dataset for instance-level understanding of EMs. EM3M comprises 5,091 high-quality EMs, approximately 3 million instance segmentation annotations, and image-level textual descriptions with disentangled attributes. The dataset is constructed through a rigorous multi-stage curation and validation pipeline, with comprehensive statistical analyses to ensure reliability and reproducibility. Building upon these curated image-text pairs, we further provide a text-to-image diffusion model that serves as a controllable data augmentation engine, demonstrating that synthetic augmentation consistently improves downstream segmentation performance. To establish a systematic benchmark, we evaluate representative instance segmentation methods on EM3M. Our results reveal that conventional detection-based and query-based methods struggle with the extreme instance densities and textural complexities inherent in EMs. We additionally provide an optimized flow-based baseline to facilitate fair comparison and future research. EM3M {Dataset: https://huggingface.co/datasets/UniParser/EM3M}, the generative engine {Generation: https://huggingface.co/UniParser/EM3M-Gen}, and an online demo {Segmentation demo: https://www.bohrium.com/apps/uni-aims} are publicly available to support future research in automated materials analysis.
arXiv:2509.09475v3 Announce Type: replace Abstract: Existing theoretical analyses on Faraday instability in Hele-Shaw cells typically adopt gap-averaged governing equations and rely on Hamraoui's model coming from molecular kinetics theory, thereby oversimplifying essential transverse information, such as contact line velocity and capillary hysteresis, and conflicting with the unsteady meniscus dynamics. In this paper, a gap-resolved approach is developed by directly modeling the transverse gap flow and the contact angle dynamics, which overcomes the aforementioned limitations, ultimately yielding a modified damping with respect to the static contact angle and hysteresis range. A novel amplitude equation for linear Faraday instability is derived that combines this damping and the gap-averaged counterpart based on the oscillatory Stokes boundary layer, with the viscous dissipation preserved. By means of Lyapunov's first method, an explicit analytical expression for the critical stability boundary is established. Two series of laboratory experiments are performed that focus, respectively, on evolutions of the lateral meniscus and the longitudinal free surface near the Faraday onset, from which key parameters relevant to the theory are precisely measured. Based on the experimental data, the validity of the proposed mathematical model for addressing the Faraday instability problem in Hele-Shaw cells is confirmed, and the generation and development mechanisms of the onset are clarified. In the asymptotic analysis, the inclusion of contact angle dynamics increases the overall damping and thus partially compensates for the frequency detuning introduced by oscillatory Stokes flow approximation.
arXiv:2509.10448v2 Announce Type: replace Abstract: Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a computational framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale. Our approach transforms tables into graph-based representations processed by constraint-driven GNNs that encode scientific principles directly into model architecture. MatSKRAFT significantly outperforms contemporary frontier large language models, achieving F1 scores of 89.33 for property extraction and 71.35 for composition extraction, while processing data 6-496 times faster compared to the fastest and the slowest models respectively, with modest hardware requirements. Applied to 66,267 tables from more than 45,500 research publications, we construct a comprehensive database containing 509,281 entries, including 104,000 compositions that expand coverage beyond major existing databases. This systematic approach reveals previously overlooked materials with distinct property combinations and enables data-driven discovery of composition-property relationships forming the cornerstone of materials and scientific discovery.
arXiv:2606.07944v2 Announce Type: replace Abstract: Spectrum aggregation has been a key enabler of LTE and 5G capacity growth and will remain essential in 6G as networks combine fragmented spectrum across low bands, existing mid bands, new upper-mid/centimetric bands, and millimeter wave bands. This article examines how 5G carrier aggregation (CA) and dual connectivity (DC) inform the design of 6G spectrum aggregation. The central thesis is that CA is the necessary carrier-level scaling mechanism, while DC is a higher-layer cell-group architecture that should be used only when a second cell group is genuinely needed. We argue that CA provides a cleaner and more scalable foundation for multi-band operation in standalone 6G. Building on lessons from 5G, we advocate enhanced CA as the preferred 6G spectrum aggregation framework and point out the corresponding key enhancement directions.
arXiv:2512.20677v5 Announce Type: replace Abstract: Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suites. This creates a gap between what is easy to test and what deployed models can actually do: failures may be rare, context-sensitive, and distributed across many threat categories. We study automated red-teaming as a constrained adversarial search problem and introduce a learning-driven framework that couples category-aware attack generation with hierarchical vulnerability detection. The method starts from curated safety seeds, expands them through meta-prompt-guided and evolutionary search, and scores the resulting prompt--response pairs with lexical, semantic, and behavioral detectors. Across six threat categories on GPT-OSS-20B, the framework discovers 47 validated vulnerabilities, including 21 high-severity cases and 12 novel attack patterns. Under matched query budgets, it achieves a 3.9$\times$ higher discovery rate than manual expert red-teaming while maintaining 89\% detection accuracy and full category coverage. Ablations show that the gains do not come from more prompts alone: diversity constraints prevent template collapse, coverage constraints prevent category blind spots, and semantic detection recovers failures missed by lexical rules. These results suggest that red-teaming can be made more scalable and reproducible when treated as adaptive search rather than as a static checklist.
arXiv:2512.23124v2 Announce Type: replace Abstract: Zero Trust architectures strengthen continuous verification and least-privilege enforcement, but general-purpose implementations do not explicitly treat financial exposure and transaction-level operational cost as first-class decision inputs. This paper presents SecureBank, a financially-aware Zero Trust architecture that combines identity and device trust, contextual consistency, financial risk, business-aligned segmentation, and policy actions such as allow, step-up verification, and block. The empirical study validates the architecture's financial-risk decision component rather than claiming end-to-end production validation of the complete architecture. A public credit-card fraud dataset containing 284,807 transactions was divided into independent training, validation, and test partitions using a 60/20/20 stratified design. A class-weighted logistic regression model produced a risk score. The operational threshold was selected only on the validation partition using an asymmetric cost function in which a false negative was assigned a cost 50 times greater than a false positive, and the frozen threshold was then evaluated once on the independent test partition. The final test set contained 56,962 transactions and 99 fraud cases. At the validation-selected risk-score threshold of 0.9991, the model achieved ROC-AUC 0.9664, average precision 0.7119, precision 71.03%, recall 76.77%, F1-score 0.7379, and a false-positive rate of 0.0545%. These results provide reproducible component-level evidence that financially asymmetric operating costs can be integrated into a Zero Trust decision process while keeping the scope of the empirical claims explicit.
arXiv:2604.24827v2 Announce Type: replace Abstract: Closed-source frontier labs do not disclose parameter counts. Storing F facts requires at least F/(bits per parameter) weights, so factual recall lower-bounds parameter count--an intrinsic, serving-independent signal, though (as we show) a coarse one. We introduce Incompressible Knowledge Probes (IKPs), a benchmark of 1,400 factual questions spanning 7 tiers of obscurity, designed to isolate knowledge that cannot be derived by reasoning or compressed by architectural improvements. We score with no hallucination penalty (lambda = 0: IKP accuracy is simply the fraction of probed facts answered correctly), which removes both the penalty hyperparameter and the per-tier flooring choice; a full lambda x flooring ablation shows the calibration is robust across scoring choices while individual estimates are not, motivating the no-penalty default. We calibrate a log-linear mapping from IKP accuracy to parameter count on 93 open-weight models (135M-1,600B) spanning 19 vendors, achieving R^2 = 0.910; leave-one-out cross-validation confirms generalization (median fold error 1.48x, 72% within 2x, 86% within 3x). The instrument is deliberately coarse--its 90% prediction interval spans ~3x in either direction, wider than inference economics--so IKP recovers order-of-magnitude effective capacity and relative rankings, not precise parameter counts. For Mixture-of-Experts models, total parameters predict knowledge (R^2 = 0.67) better than active parameters (R^2 = 0.41). We evaluate 201 models from 27 vendors on a curated probe set (1,311 of 1,400 probes surviving name-collision and label-ambiguity filters) and report effective knowledge capacity for all major proprietary frontier models as prediction bands rather than point estimates; for heavily safety-tuned models these are lower bounds, since refusal policy can suppress tens of percentage points of otherwise-answerable capacity.
arXiv:2601.19128v2 Announce Type: replace Abstract: In terrestrial laser scanning (TLS)-based mechanical, electrical, and plumbing (MEP) point cloud segmentation, safety-critical components such as reducers and valves are persistently misclassifed, blocking reliable engineering knowledge extraction. This stems from a dual crisis--extreme class imbalance (215:1) compounded by geometric ambiguity, since most tail classes share cylindrical primitives with dominant head classes--that existing frequencybased re-weighting methods cannot resolve. We propose spatial context constraints that exploit neighborhood prediction consistency to disambiguate locally similar structures. Our approach extends Class-Balanced (CB) Loss with two architecture-agnostic mechanisms: Boundary-CB, an entropy-based constraint that emphasizes ambiguous boundaries and encodes an MEP assemblytopology prior, and Density-CB, a density-based constraint that compensates for scan-dependent variations and encodes TLS sensor-physics knowledge. Both operate at the loss level and integrate into existing pipelines without backbone modifcations. On the Industrial3D dataset (612.7M labelled points from water treatment facilities), our method achieves 55.74% mIoU, exceeding the strongest of three representative fully supervised backbone baselines (39.83-52.48% mIoU), with a 21.7% relative improvement on tail-class performance (29.59% vs. 24.32%) while preserving head-class accuracy (88.14%). Components with primitive-sharing ambiguity show strong gains: reducer improves from 0% to 21.12% IoU, and valve improves by 24.3% relative. These results show that spatial context constraints reduce primitive-sharing errors in the target industrial MEP setting and support more reliable identifcation of safety-critical components for Digital Twin and Scan-to-BIM applications. Code: https://github.com/PointCloudYC/LongTail3D.git.
arXiv:2603.08990v2 Announce Type: replace-cross Abstract: We design and evaluate an edge-side measurement procedure for auditing service tiering and quota-based throttling in Starlink. Using a 232.8-hour plan-hopping campaign on a UK residential terminal, we align 1 Hz terminal telemetry with host-side probes to obtain portal-labeled traces spanning priority, post-quota throttling, stay-active operation, and residential service. These regimes manifest as distinct signatures in goodput, PoP RTT, and an internal-to-user ratio \(R=C_{\mathrm{int}}/T_{\mathrm{user}}\). We further show that high-speed \(R\) is stable over 30-minute sub-windows, that low-rate clusters have no aligned persistent obstruction or PoP-loss signature, and that clean high-speed dips do not move \(R\) into the low-rate band. A lightweight rule on windowed medians separates high-speed from low-rate operation on this trace without operator visibility.
arXiv:2603.14830v3 Announce Type: replace Abstract: Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical. Mechanisms underlying the extraction of task-relevant information from the training process and the efficient encoding of such information into synthetic data points remain elusive. In this paper, we theoretically analyze practical algorithms of dataset distillation applied to the gradient-based training of two-layer neural networks with width $L$. By focusing on a non-linear task structure called multi-index model, we prove that the low-dimensional structure of the problem is efficiently encoded into the resulting distilled data. This dataset reproduces a model with high generalization ability for a required memory complexity of $\tilde{\Theta}$$(r^2d+L)$, where $d$ and $r$ are the input and intrinsic dimensions of the task. To the best of our knowledge, this is one of the first theoretical works that include a specific task structure, leverage its intrinsic dimensionality to quantify the compression rate and study dataset distillation implemented solely via gradient-based algorithms.
arXiv:2603.14844v2 Announce Type: replace Abstract: The ocean remains one of the least instrumented parts of Earth, and many geophysical, biological, and anthropogenic signals go undetected for lack of instrumentation. Distributed acoustic sensing (DAS) can transform submarine fiber-optic cables into dense seafloor sensor arrays, but extracting diverse signals from massive DAS recordings remains challenging. Here we present DASNet, a deep learning framework that detects, classifies, and picks arrival times of diverse marine signals in continuous DAS data. Applied to nearly four years of Seafloor Fiber-Optic Array in Monterey Bay recordings, DASNet identifies more than 620,000 events. These detections reveal local earthquakes; distant earthquake- and volcanic-eruption-generated T-waves from the southwestern Pacific and mid-ocean ridge systems; more than 510,000 blue and fin whale calls with seasonal and interannual variability consistent with hydrophone records; and vessel traffic near the cable. Together, these results show that submarine fiber-optic cables combined with deep learning enable scalable, high-resolution ocean monitoring.
arXiv:2603.03695v2 Announce Type: replace Abstract: Reliable localization is essential for sustainable forest management, as it allows robots to revisit and monitor the status of individual trees over long periods. In modern forestry, this management is structured around Digital Forest Inventories (DFIs), which encode stems using compact geometric attributes rather than raw data. Despite their central role, DFIs have been overlooked in localization research, and most methods still rely on dense gigabyte-sized point clouds that are costly to store and maintain. To improve upon this, we propose TreeLoc++, a global localization framework that operates directly on DFIs as a discriminative representation, eliminating the need to use the raw point clouds. TreeLoc++ reduces false matches in structurally ambiguous forests and improves the reliability of full 6-DoF pose estimation. It augments coarse retrieval with a pairwise distance histogram that encodes local tree-layout context, subsequently refining candidates via DBH-based filtering and yaw-consistent inlier selection to further reduce mismatches. Furthermore, a constrained optimization leveraging tree geometry jointly estimates roll, pitch, and height, enhancing pose stability and enabling accurate localization without reliance on dense 3D point cloud data. Evaluations on diverse forests across four countries show that TreeLoc++ achieves precise localization with centimeter-level accuracy. We further demonstrate robustness to long-term change by localizing data recorded in 2025 against inventories built from 2023 data, spanning a two-year interval. The system represents 15 sessions spanning 7.98 km of trajectories using only 250KB of map data and outperforms both hand-crafted and learning-based baselines that rely on point cloud maps. This demonstrates the scalability of TreeLoc++ for long-term deployment. TreeLoc++ is open-sourced at \bl{https://github.com/minwoo0611/TreeLoc-plusplus}.
arXiv:2603.27044v3 Announce Type: replace Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework, which we refer to as Action-based Policy Compression (APC), mitigates this issue by compressing the parameter space $\Theta$ into a low-dimensional latent manifold $\mathcal Z$ using a learned generative mapping $g:\mathcal Z \to \Theta$. However, its performance is severely constrained by relying on immediate action-matching as a reconstruction loss, a myopic proxy for behavioral similarity that suffers from compounding errors across sequential decisions. To overcome this bottleneck, we introduce Occupancy-based Policy Compression (OPC), which enhances APC by shifting behavior representation from immediate action-matching to long-horizon state-space coverage. Specifically, we propose two principal improvements: (1) we curate the dataset generation with an information-theoretic uniqueness metric that delivers a diverse population of policies; and (2) we propose a fully differentiable compression objective that directly minimizes the divergence between the true and reconstructed mixture occupancy distributions. These modifications force the generative model to organize the latent space around true functional similarity, promoting a latent representation that generalizes over a broad spectrum of behaviors while retaining most of the original parameter space's expressivity. Finally, we empirically validate the advantages of our contributions across multiple continuous control benchmarks.
arXiv:2505.15720v2 Announce Type: replace-cross Abstract: In this paper, we introduce a new family of codes relevent for rank and sum-rank metrics. These codes are based on an effective Chinese remainders theorem for linearized polynomials over finite fields. We propose a decoding algorithm for some instances of these codes.