arXiv:2511.12158v3 Announce Type: replace Abstract: Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse the birdsong. Developing such models requires precise, syllable-level annotated training data. Therefore, automated methods that reduce annotation costs are in demand. This work presents a data-efficient birdsong annotator called Residual Multi-Layer Perceptron Recurrent Neural Network. It then presents a three-stage training pipeline for developing reliable birdsong syllable detectors with minimal annotation. The first stage is self-supervised learning from unlabeled data. Two of the most successful pretraining paradigms are explored, namely, masked prediction and online clustering. The second stage is supervised training with effective data augmentation to produce a robust frame-level syllable detector for each individual. The third stage is a semi-supervised post-training step that refines each individual's model using unlabeled data. The effectiveness of this approach is demonstrated for the Canary song in extreme label-scarcity scenarios. From a signal-processing perspective, the Canary song exhibits one of the most challenging spectro-temporal patterns for algorithmic time-series annotation: rapid vocalizations, brief inter-syllabic intervals, fast and broadband frequency sweeps, and spectrally similar syllables that require fine-grained features to distinguish. Hence, a successful syllable detection algorithm for Canary also establishes a robust baseline for other birds. This methodological generalization is validated in a case study of Bengalese Finch song annotation. Finally, the potential of self-supervised embeddings is assessed for linear probing and unsupervised birdsong analysis.
Science Journals
arXiv:2511.04776v3 Announce Type: replace Abstract: Generative Artificial Intelligence (GenAI) represents a rapidly expanding digital infrastructure whose energy demand and associated CO2 emissions are emerging as a new category of climate risk. This study introduces G-TRACE (GenAI Transformative Carbon Estimator), a cross-modal, region-aware framework that quantifies training- and inference-related emissions across modalities and deployment geographies. Using real-world analytics and microscopic simulation, G-TRACE measures energy use and carbon intensity per output type (text, image, video) and reveals how decentralized inference amplifies small per-query energy costs into system-level impacts. Through the Ghibli-style image generation trend (2024-2025), we estimate 4,309 MWh of energy consumption and 2,068 tCO2 emissions, illustrating how viral participation inflates individual digital actions into tonne-scale consequences. Building on these findings, we propose the AI Sustainability Pyramid, a seven-level governance model linking carbon accounting metrics (L1-L7) with operational readiness, optimization, and stewardship. This framework translates quantitative emission metrics into actionable policy guidance for sustainable AI deployment. The study contributes to the quantitative assessment of emerging digital infrastructures as a novel category of climate risk, supporting adaptive governance for sustainable technology deployment. By situating GenAI within climate-risk frameworks, the work advances data-driven methods for aligning technological innovation with global decarbonization and resilience objectives.
arXiv:2510.14261v2 Announce Type: replace Abstract: We present an experimental recipe for studying the relationship between training data and language model (LM) behavior. We outline steps for intervening on data batches -- i.e., ``rewriting history'' -- and then retraining model checkpoints over that data to test hypotheses relating data to behavior. Our recipe breaks down such an intervention into stages that include selecting evaluation items from a benchmark that measures model behavior, matching relevant documents to those items, and modifying those documents before retraining and measuring the effects. We demonstrate the utility of our recipe through case studies on factual knowledge acquisition in LMs, using both cooccurrence statistics and information retrieval methods to identify documents that might contribute to knowledge learning. Our results supplement past observational analyses that link cooccurrence to model behavior, while demonstrating that extant methods for identifying relevant training documents do not fully explain an LM's ability to correctly answer knowledge questions. Overall, we outline a recipe that researchers can follow to test further hypotheses about how training data affects model behavior. Our code is made publicly available to promote future work.
arXiv:2505.08587v2 Announce Type: replace Abstract: We present a novel two-level sketching extension of the Alternating Anderson-Picard (AAP) method for accelerating fixed-point iterations in challenging single- and multi-physics simulations governed by discretized partial differential equations. Our approach combines a static, physics-based projection that reduces the least-squares problem to the most informative field (e.g., via Schur-complement insight) with a dynamic, algebraic sketching stage driven by a backward stability analysis under Lipschitz continuity. We introduce inexpensive estimators for stability thresholds and cache-aware randomized selection strategies to balance computational cost against memory-access overhead. The resulting algorithm solves reduced least-squares systems in place, minimizes memory footprints, and seamlessly alternates between low-cost Picard updates and Anderson mixing. Implemented in Julia, our two-level sketching AAP achieves up to 50% time-to-solution reductions compared to standard Anderson acceleration-without degrading convergence rates-on benchmark problems including Stokes, p-Laplacian, Bidomain, and Navier-Stokes formulations at varying problem sizes. These results demonstrate the method's robustness, scalability, and potential for integration into high-performance scientific computing frameworks. Our implementation is available open-source in the AAP.jl library.
arXiv:2503.21007v2 Announce Type: replace Abstract: Deep neural networks (DNNs) have emerged as a powerful tool with a growing body of literature exploring Lyapunov-based approaches for real-time system identification and control. These methods depend on establishing bounds for the second partial derivatives of DNNs with respect to their parameters, a requirement often assumed but rarely addressed explicitly. This paper provides rigorous mathematical formulations of polynomial bounds on both the first and second partial derivatives of DNNs with respect to their parameters. We present lemmas that characterize these bounds for fully-connected DNNs, while accommodating various classes of activation function including sigmoidal and ReLU-like functions. Our analysis yields closed-form expressions that enable precise stability guarantees for Lyapunov-based deep neural networks (Lb-DNNs). Furthermore, we extend our results to bound the higher-order terms in first-order Taylor approximations of DNNs, providing important tools for convergence analysis in gradient-based learning algorithms. The developed theoretical framework develops explicit, computable expressions, for previously assumed bounds, thereby strengthening the mathematical foundation of neural network applications in safety-critical control systems.
arXiv:2502.11984v4 Announce Type: replace Abstract: In this work, we introduce Blank Space Adaptive Causal Random Linear Network Coding (BS-AC-RLNC), a novel coding scheme designed to mitigate the triplet trade-off between throughput-delay-efficiency in multi-hop networks. BS-AC-RLNC leverages the physical limitations of the network, considering the bottleneck from each node to the destination. In particular, this approach introduces a light-computational re-encoding algorithm, called AC-RLNC (NET), implemented independently at intermediate nodes. NET adaptively adjusts the Forward Error Correction (FEC) rates and schedules idle periods. It incorporates two distinct suspension mechanisms: 1) Blank Space Period, accounting for the forward-channels bottleneck, and 2) No-New No-FEC approach, based on data availability. We present theoretical lower and upper bounds on in-order delivery delay, goodput, and throughput; in the case of in-order delay, we further derive a mean bound. These analytical results are extended to the multicast scenario, providing a broader understanding of the algorithm's performance under diverse network conditions. The experimental results achieve significant improvements in resource efficiency, demonstrating a 20% reduction in channel usage compared to baseline RLNC solutions. Notably, these efficiency gains are achieved while maintaining competitive throughput and delay performance, ensuring improved resource utilization does not compromise network performance.
arXiv:2412.00404v2 Announce Type: replace Abstract: With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial attacks. Almost all existing 3D attackers simply follow the white-box or black-box setting to iteratively update coordinate perturbations based on back-propagated or estimated gradients. However, these methods are hard to deploy in real-world scenarios (no model details are provided) as they severely rely on parameters or output logits of victim models. To this end, we propose point cloud attacks from a more practical setting, i.e., hard-label black-box attack, in which attackers can only access the prediction label of 3D input. We introduce a novel 3D attack method based on a new spectrum-aware decision boundary algorithm to generate high-quality adversarial samples. In particular, we first construct a class-aware model decision boundary, by developing a learnable spectrum-fusion strategy to adaptively fuse point clouds of different classes in the spectral domain, aiming to craft their intermediate samples without distorting the original geometry. Then, we devise an iterative coordinate-spectrum optimization method with curvature-aware boundary search to move the intermediate sample along the decision boundary for generating adversarial point clouds with trivial perturbations. Experiments demonstrate that our attack competitively outperforms existing white/black-box attackers in terms of attack performance and adversary quality.
arXiv:2310.11203v2 Announce Type: replace Abstract: We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset with respect to the other nodes. We then build a global randomised predictor which inherits the properties of the local private predictors in the sense of a PAC-Bayesian generalisation bound. We consider the synchronous case where all nodes share the same training objective (derived from a generalisation bound), and the heterogenous and homogenous cases where each node may have its own personalised training objective. We show through a series of numerical experiments that our approach achieves a comparable predictive performance to that of the batch approach where all datasets are shared across nodes. Moreover the predictors are supported by numerically nonvacuous generalisation bounds while preserving privacy for each node. We explicitly compute the increment on predictive performance and generalisation bounds for our two federated settings, highlighting the price to pay to preserve privacy.
arXiv:2303.09838v4 Announce Type: replace Abstract: Battery models generally fall into two categories: physics-based models and ECM models. Physics-based Doyle-Fuller-Newman (DFN) models can accurately simulate the battery internal electrochemical processes, but to properly account for thermal effects requires a strong coupling between a DFN model and a 3D thermal model, which is computationally unaffordable. Distributed Equivalent Circuit Network (ECN) models can perform simulations with high speed and reasonable accuracy. However, these models rely heavily on the characterisation experiments for ECN parameter identification, which is resource-intensive and can lead to inaccurate parametrisation outcomes due to internal thermal inhomogeneity. To harness the strengths of both models, we propose a computational framework to integrate electrochemical DFN model and 3D distributed ECN model together. Using this framework, we simulate constant current discharge experiments of Kokam 7.5 Ah pouch cell (Model SLPB75106100) and compare the simulations with the commonly-used lumped DFN-thermal model. The computational model outperforms the lumped DFN model at low-temperature and/or high C-rate scenarios significantly. The largest predicting error of the framework at 3 C-rate &Tam = 25oC and at 1 C-rate &Tam = 0 oC is approximately 1/3 of that for DFN model. At 3 C-rate &Tam = 5oC, the difference between these two can rise to 377 mV. By integrating DFN and 3D-distributed ECN together, the computational framework can simulate the complicated interplay between electrochemistry, thermal process, and electricity within a cell fast and accurately. We anticipate this computational framework to be a valuable toolset to assist researchers and engineers in the design and control of Li-ion batteries.
arXiv:2605.19573v1 Announce Type: new Abstract: We study the soft covering phenomenon through the lens of Neyman--Pearson hypothesis testing: given a channel output sequence $y^n$, can one decide whether it was produced when the channel was driven by a random codeword, or generated independently from the output marginal? We derive exact exponential decay rates for the jointly averaged false-alarm (FA) probability $\alpha_n(\tau,R)$ and missed-detection (MD) probability $\beta_n(\tau,R)$, as functions of the decision threshold $\tau$ and the codebook rate $R$. The derived single-letter formulas of the exponents $\EFA(\tau,R)=-\lim_{n\to\infty}\frac{1}{n}\ln\alpha_n(\tau,R)$ and $\EMD(\tau,R)=-\lim_{n\to\infty}\frac{1}{n}\ln\beta_n(\tau,R)$ are tight in the random coding sense. The analysis reveals a rich phase structure. For $R < I(X;Y)$, there is a genuine exponential tradeoff between the two error types over the interval $\tau \in (0, I(X;Y)-R)$. At $R = I(X;Y)$, this tradeoff interval collapses to the single point $\tau = 0$, where both error exponents simultaneously vanish, a fact which manifests the soft covering phenomenon in the Neyman--Pearson sense. For $R > I(X;Y)$, the same instantaneous collapse persists at $\tau = 0$; moreover, for every $\tau$ at least one exponent is zero: the FA exponent is zero for $\tau \le 0$ (FA probability does not decay exponentially), and the MD exponent is zero for $\tau \ge 0$ (and finite, channel-specific for $\tau<0$; see Remark~\ref{rem:jump}). There is no interval of $\tau$ where both exponents are simultaneously positive. A sharp phase transition in the MD exponent occurs at $\tau^* = [I(X;Y)-R]_+$ for all rates.
arXiv:2605.19527v1 Announce Type: new Abstract: Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-region cues, thereby complicating cross-view matching. Most person ReID methods built on pretrained vision-language models only focus on enhancing prompt-based feature learning while ignoring the semantic information of occluders. Based on the success of CLIP-ReID, we propose a novel Dual Prompt Learning ReID (DPL-ReID) model for occluded person ReID. It incorporates a Dual Prompt Learning (Dual-PL) strategy, which can utilize textual cues to capture complete pedestrian semantics and keep robustness against occlusion, and a Real-World Occlusion Augmentation (RWOA) method that realistically simulates occlusion scenarios encountered in real word to enrich occluded samples. In addition, we also design a Weighted Gated Feature Fusion (WGFF) method, which in corporates LSNet to capture global information and act as a feature-gating mechanism. This mechanism can effectively guide the CLIP visual encoder toward generating more comprehensive feature representations. Extensive experiments on several benchmark occluded ReID datasets show that our proposed DPL-ReID achieves the state-of-the art performance. The occlusion instance library are available at https://github.com/stone-qiao/DPL-ReID.
arXiv:2605.19498v1 Announce Type: new Abstract: F\"{o}rster energy transfer underpins modern photonics, yet establishing an analogous vibrational pathway in the mid-infrared (MIR) remains highly challenging, as sub-picosecond intramolecular vibrational redistribution (IVR) suppresses intermolecular coupling. Here we demonstrate vibrational donor--acceptor transfer in the MIR and subsequent upconversion to visible luminescence enabled by sub-2 nm plasmonic nanogaps. The extreme lateral field confinement in metal--molecule--metal ring cavities defined by self-assembled molecular spacers couples efficiently to in-plane molecular dipoles. Continuous-wave MIR excitation selectively populates $-\mathrm{C}\equiv\mathrm{N}$ vibrational donors, and plasmon-enhanced near-field coupling transfers this energy to nearby electronic acceptors, generating anti-Stokes visible emission under low power densities. Upconversion efficiencies exceeding $0.3\%$ are observed, limited by competition between the plasmon-mediated transfer rate and IVR. These results show that extreme plasmonic confinement can redirect molecular vibrational relaxation pathways, opening a route toward vibrational nanophotonics, intermolecular interactions for bioimaging, and room-temperature MIR detection based on molecular degrees of freedom.
arXiv:2605.19488v1 Announce Type: new Abstract: The wakeup problem in distributed computing asks for a symmetric protocol that enables one of several processors to eventually guarantee that all (or, in a more general setting, enough) other processors have acted, using a shared register but no global clock. Dropping the symmetry requirement gives a well-known exercise often phrased in terms of prisoners entering, in an unknown sequence, a room equipped with a single binary switch, and using it to communicate. Kane and Kominers recently analysed a more general version of the latter with multiple parallel and indistinguishable rooms. We answer some open questions of Kane and Kominers regarding the minimum number of switch states needed for the prisoners to solve the problem. We also consider the symmetric ``wakeup'' version of this scenario, and establish exactly for which numbers of processors and registers a solution is possible.
arXiv:2605.19408v1 Announce Type: new Abstract: Manipulating nanoscale light-matter interactions on ultrafast time scales is indispensable for future polaritonic devices. Hyperbolic phonon polaritons (HPhPs) in van der Waals materials enable deep subwavelength confinement of electromagnetic fields in the infrared region and long-distance propagation of polaritonic waves. However, achieving ultrafast imaging and optical control of HPhPs remains a major challenge. Here, we demonstrate the direct observation of transient modulation of HPhPs induced by local photocarrier generation in WS$_2$/hBN heterostructures using ultrafast infrared scanning near-field optical microscopy. We implement grating-based spectral filtering of broadband near-field scattering to simultaneously achieve nanoscale and femtosecond spatiotemporal resolution together with fine spectral selectivity. This ultrafast nano-imaging technique reveals that photocarriers in WS$_2$ modulate the polaritonic field amplitudes and wavelengths of HPhPs in hBN. Theoretical simulations corroborate that these changes arise from photoinduced changes in WS$_2$ dielectric properties. This approach offers a versatile platform for exploring ultrafast polaritonic dynamics at the nanoscale.
arXiv:2605.19343v1 Announce Type: new Abstract: Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approaches, from causal representation learning to foundation models, often struggle with an overlooked challenge: gene expression is dominated by perturbation-invariant information, while perturbation-specific signals are intrinsically sparse. As a result, learned representations either entangle invariant and perturbation-specific information, leading to spurious and non-generalizable predictors, or suppress perturbation-specific signals altogether, rendering them ineffective for prediction. To address this, we propose PerturbedVAE, a general framework designed to resolve this signal imbalance. The framework explicitly separates perturbation-specific information from dominant invariant structure and recovers causal representations to effectively utilize such information for prediction. We further provide an identifiability analysis that characterizes the conditions under which sparse perturbation effects can be reliably recovered, thereby clarifying how the framework can be concretely specified under such conditions. Empirically, PerturbedVAE achieves state-of-the-art performance on a widely used benchmark across multiple evaluation settings, yielding significant gains on out-of-distribution combinatorial predictions and uncovering interpretable perturbation-response programs.
arXiv:2605.19337v1 Announce Type: new Abstract: A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decisions, emit tradable actions, and adapt under market feedback. This paper reframes LLM-based trading agents as expert-system decision pipelines and presents an audit-oriented evidence map of 77 included studies in a protocol-coded snapshot screened through 2026-03-09. A primary empirical subset (n=19) satisfies the minimum boundary of Action Output plus Closed-Loop Evaluation; the remaining 58 included studies are retained as background and design context. The central empirical finding is protocol incomparability: within the primary subset, only 2/19 studies report extractable time-consistent split protocols, 1/19 reports an explicit transaction-cost model, 1/19 documents universe or survivorship handling, 11/19 report execution timing or semantics, 15/19 are coded as R0, and no study reaches R3 reproducibility. We therefore use Architecture-Capability-Adaptation as a working analytical lens rather than a validated taxonomy, and we foreground the evidence ledger, reproducibility audit, and reporting checklist as the main contributions. The resulting survey shows that architectural experimentation is expanding rapidly, while comparable evaluation protocols, execution semantics, and reproducible artifacts remain the field's immediate bottlenecks.
arXiv:2605.19328v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural language commands in diverse environments. Previous research has introduced jailbreak attacks and defenses for embodied AI. Their evaluations, however, rely on ad-hoc datasets, limited metrics, and emphasize attack success while neglecting the trade-off between security and the ability to follow benign commands. Existing benchmarks and evaluation frameworks either target traditional chat-based models or focus on non-adversarial safety evaluation for embodied AI; neither captures the adversarial risks, inputs, consequences, and evaluation criteria necessary for jailbreak attacks in embodied AI systems. In this paper, we address this gap with RoboJailBench, which consists of three core components. We establish a security taxonomy derived from ISO standards, regulatory rules, and documented incidents. This effort yields 18 categories of security violation consequences for embodied AI. We introduce an intent contrast dataset pipeline that augments existing datasets with paired adversarial and benign goals to measure both security and utility. Lastly, we provide an evolving repository with standardized metrics and a unified process for assessing and integrating new attacks and defenses. With this benchmark, we construct a new taxonomy-balanced dataset and augment five existing datasets. We integrate four attacks and two defenses to evaluate their performance on leading embodied VLMs. This benchmark provides the first standardized evaluation framework for jailbreak attacks in embodied AI and supports future research. We release our code, datasets, and artifacts, and maintain a leaderboard at https://purseclab.github.io/benchmark-for-robotics-security.
arXiv:2605.19325v1 Announce Type: new Abstract: Nonnegative matrix factorization (NMF) seeks a low-rank approximation $X \approx UV^T$ with nonnegative factors and is commonly solved using interior methods that enforce feasibility throughout optimization. We show that such constraint-driven approaches can impede progress in the nonconvex landscape, leading to slow convergence or convergence to suboptimal stationary points. We propose an exterior framework for NMF (eNMF) that separates low-rank approximation from nonnegativity enforcement. Our method initializes from the optimal unconstrained factorization and introduces a rotation procedure that maps unconstrained factors to an exterior point closest to the nonnegative orthant. This viewpoint yields an algorithmic framework in which simple iterative updates converge to KKT-satisfying stationary points on the boundary of the positive orthant. The exterior formulation also enables a geometric interpretation of NMF solutions, clarifying equivalence classes of factorizations under permutation and orthogonal transformations. An intriguing numerical result, involving 400 NMF experiments across both real and synthetic datasets, show that in 99% of the cases, different algorithms tend to converge towards equivalent factor matrices. We benchmark eNMF against 9 state-of-the-art NMF algorithms with 9 initialization schemes across 3 real-world and 2 synthetic datasets. eNMF consistently outperforms all 81 competitors, achieving up to 30% lower reconstruction error under equal-time settings and up to 150% speedup under equal-error settings. The downstream experiments further demonstrate substantial performance gains in audio processing and recommendation tasks, corroborating the practical benefits of the proposed exterior optimization framework. Code is available at https://github.com/roychowdhuryresearch/eNMF
arXiv:2605.19322v1 Announce Type: new Abstract: Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from long video sequences incurs prohibitive computational costs, limiting their deployment in real-world scenarios. Existing training-free token compression methods select tokens based on attention magnitude as a proxy for semantic importance, but often overlook positional bias and rely only on short-term temporal locality, leading to redundant spatio-temporal coverage and inefficient token usage. We present DynaTok, a training-free, temporally adaptive and bias-aware token compression framework that allocates token budgets across both temporal and spatial dimensions. Through a lightweight exponential moving average (EMA) memory, the Temporal Budget Allocation (TBA) module dynamically assigns fewer tokens to redundant frames and more to novel frames, capturing long-term temporal variation. The Spatial Budget Allocation (SBA) module complements this by selecting spatially diverse and semantically important features using activation-based attention maps, while leveraging a spatial memory to reduce redundancy from previously selected regions and mitigate positional bias. DynaTok integrates seamlessly with existing Video-LLMs such as LLaVA-OneVision and LLaVA-Video without retraining, and effectively preserves semantic coverage under aggressive compression. Experiments on four representative VideoQA benchmarks-MVBench, LongVideoBench, MLVU, and VideoMME-show that DynaTok retains over 95% of baseline accuracy even with a 90% token reduction, surpassing recent training-free approaches. These results demonstrate that DynaTok provides a principled foundation for efficient and robust video reasoning, paving the way toward real-time streaming video understanding with future Video-LLMs.
arXiv:2605.19279v1 Announce Type: new Abstract: Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for understanding human perceptual mechanisms and developing advanced brain-computer interfaces (BCIs). However, most current methods simply flatten fMRI signals from localized visual cortices into one-dimensional (1D) vectors, mapping them directly into latent spaces such as that of Contrastive Language-Image Pre-training (CLIP). This paradigm not only disrupts the inherent network topology of the brain-leading to limited neuroscientific interpretability-but also overlooks the synergistic contributions of other distributed functional networks in processing high-level visual semantics. To address these limitations, we propose FPED, a Functional-Network Prior-Guided Mixture of Experts (MoE) framework for interpretable brain decoding. FPED explicitly models different functional brain networks as specialized experts and employs adaptive routing to capture their complementary contributions to visual semantic understanding. Unlike conventional homogeneous decoding paradigms, our framework incorporates neurobiologically grounded priors to enable structured and interpretable network-level representation learning. Experimental results demonstrate that FPED achieves highly competitive semantic reconstruction performance with only 0.68B parameters. The learned routing dynamics reveal biologically meaningful correspondence between functional brain networks and modality-specific semantic processing, providing transparent neuroscientific interpretability. This suggests that brain network-aware expert modeling is a promising direction for bridging neural decoding and biologically inspired artificial intelligence.
arXiv:2605.19264v1 Announce Type: new Abstract: Voting methods weighted by stakes are the fundamental governance paradigm in Proof-of-Stake (PoS) blockchains. Such a paradigm is known to be prone to power distortions: a few users possessing large stakes may completely control decision making, even without owning the totality of the stakes. We study this phenomenon through the lens of computational social choice, focusing on the extent of power imbalances in stake-weighted voting when power is quantified using the Penrose-Banzhaf power index. Our work presents both analytical and empirical contributions. Analytically, we demonstrate that while a perfect alignment between power and relative stake ownership is generally unattainable, it can be approximated in expectation under specific conditions. Empirically, using data from a real-world on-chain governance system (Project Catalyst), we provide a more fine-grained understanding of the power imbalances that are likely to occur in current stake-weighted governance systems.
arXiv:2605.19263v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from gradient pathologies, spectral bias, and poor convergence, especially for problems with strong nonlinearity, sharp gradients, or multiscale features. We propose the Curriculum-Guided Gaussian Mixture Physics-Informed Neural Network (CGMPINN), which integrates Gaussian mixture modeling with dynamic curriculum learning. Specifically, a GMM is periodically fitted to the PDE residual distribution to quantify spatially varying learning difficulty. A smooth curriculum schedule progressively shifts training focus from easy to harder regions, while precision-based variance modulation suppresses unreliable clusters during early optimization. This dual curriculum is governed by a shared curriculum parameter and can be combined with self-adaptive loss balancing. We further establish theoretical guarantees, including sublinear convergence of the gradient norm for the induced time-varying loss, uniform equivalence between the curriculum-weighted and standard PDE losses, and a generalization bound with an explicit weighting-induced bias characterization. Experiments on six benchmark PDEs spanning elliptic, parabolic, hyperbolic, advection-dominated, and nonlinear reaction-diffusion types show that CGMPINN consistently achieves the lowest relative $L_2$ and maximum absolute errors among all compared methods, reducing relative $L_2$ error by up to 97.8\% over the standard PINN at comparable cost. Our code is publicly available at https://github.com/Mathematics-Yang/CGMPINN.
arXiv:2605.19260v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iteration step. However, these screenshots exhibit highly non-uniform spatial information density: large regions may carry little information and are visually homogeneous, while key text and icons may require high visual fidelity. Existing approaches to this problem either require additional training or rely on attention-based token compression, ignoring the structured layout and spatial redundancy of GUI screenshots. To fill the gap, this paper proposes AquaUI, a training-free inference-time token reduction method for GUI agent models that utilizes the non-uniform information density in screenshots. AQuaUI constructs an adaptive quadtree on each screenshot input and keeps one representative merged token per leaf of the quadtree. AQuaUI preserves the spatial positions of retained tokens throughout the pipeline to ensure that all position-encoding stages remain consistent. To further improve temporal consistency across multi-step GUI interactions, we propose a conditional quadtree algorithm that leverages the continuity between consecutive screenshots within a single request. Specifically, it refines the current quadtree using previous quadtrees as references, helping preserve fine-grained regions across static or mildly shifted GUI states. We implement AQuaUI on state-of-the-art GUI agent models and conduct experiments on standard grounding and navigational benchmarks. AQuaUI consistently shows improved accuracy-efficiency trade-offs over prior baselines. Notably, on GUI-Owl-1.5-32B-Instruct, AQuaUI achieves up to 13.22% speedup and 29.52% fewer visual tokens while retaining 99.06% of full-token performance, suggesting that the spatial redundancy of GUI screenshots can be exploited at inference without retraining.
arXiv:2605.19254v1 Announce Type: new Abstract: We describe a C implementation of the Las Vegas algorithm of Birmpilis, Labahn and Storjohann from 2020 for computing the Smith normal form of a nonsingular integer matrix. The algorithm computes a Smith massager for the input matrix using $O(n^{\omega}\, \B(\log n + \log \|A\|)\, (\log n)^2)$ bit operations, which is softly equivalent to the cost of multiplying two matrices of the same dimension and entry size. We describe the key implementation techniques that bridge the gap between the theoretical algorithm and practical performance, including BLAS-accelerated modular arithmetic via the Residue Number System and an adaptive batching scheme that collapses the theoretical $O(\log n)$ iterations to $O(1)$ in practice. Experiments on matrices of dimension up to $n = 10007$ show that the implementation's running time scales proportionally to that of a single BLAS matrix multiplication, with both exhibiting the same effective growth rate on a log-log plot.
arXiv:2605.19246v1 Announce Type: new Abstract: Selecting a bundle of items that collectively satisfies constraints is a fundamental task across databases, recommender systems, and text summarization. Unlike traditional retrieval that returns individual or top-k items, bundle retrieval is inherently combinatorial and, in general, NP-hard. Although package queries can efficiently retrieve bundles given a well-formed query, two key user-centric challenges remain: (1) expressing and tuning multi-dimensional bundle intent through a user-friendly interface, and (2) ensuring feasibility when the query yields empty results. We introduce Ex2Bundle, an Example-driven Bundle retrieval framework that enables users to specify their intent through example bundles and automatically synthesizes package queries that capture the intent implicit in those example bundles via aggregate constraints. Ex2Bundle also addresses a challenge unique to bundle retrieval: when inferred aggregate constraints are infeasible over the target data, our data-aware constraint relaxation minimally adjusts the constraint bounds while preserving alignment with user intent. We instantiate a specific application of focused text snippet extraction by example to demonstrate the efficacy of the Ex2Bundle framework. Extensive experiments over real-world datasets and a user study demonstrate that Ex2Bundle improves usability and consistently returns intent-aligned bundles even under distributional shifts of the target database.