arXiv:2601.03390v2 Announce Type: replace Abstract: As Byzantine Fault Tolerant (BFT) protocols are increasingly adopted for user-facing applications such as payments and smart contracts, it is crucial that they provide low latency. To reduce latency, some BFT consensus protocols use a leaderless, speculative, fast path where clients broadcast requests directly to replicas, enabling end-to-end commit latency of two message delays ($2\Delta$). However, such a fast path is extremely fragile: concurrent requests can cause replicas to diverge when they receive requests in different orders, triggering costly recovery procedures. This paper presents Aspen, a leaderless speculative BFT protocol that handles concurrent requests while achieving near-optimal latency of $2\Delta + \epsilon$. The $\epsilon$ term is a short waiting delay introduced by Aspen's best effort ordering layer, which uses loosely synchronized clocks and network delay estimates to provide a tentative order. To make its fast path even more robust to intermittent divergence, Aspen adds extra replicas ($n = 3f + 2p + 1$) as well as novel recovery mechanisms that allow the system to tolerate divergence while preserving safety and performance. In experiments with geo-distributed replicas, Aspen reduces the median latency of requests by $1.1\times$--$3.8\times$ compared to state-of-the-art BFT protocols, while sustaining up to $0.75\times$ the peak throughput of throughput-optimized designs.
Science Journals
arXiv:2601.04015v3 Announce Type: replace Abstract: This article seeks to determine the extent to which the principle of persistence is observed by repositories and the organizations that operate them. We also evaluate the impact that negative repository persistence levels may be having on the scholarly record. We do this by interrogating and combining data about European repositories from several repository registries and web scraped sources, including the Internet Archive's Wayback Machine, thereby creating a unique dataset of historic repository locations and their OAI-PMH endpoints. We then use this data as the basis for text mining CORE, a vast corpus of scholarly outputs, to determine the extent to which impersistent European repository content has permeated the scholarly literature. Our findings indicate over a fifth of European repositories (> 20%) could be classified as 'dead', with an even greater proportion (> 40%) of the machine interfaces associated with these repositories similarly dead. Problematically, our analysis indicates that circa 12,000 unique scholarly works cite, refer to, or actively used this repository content, amounting to circa 19,000 unique repository locations, all of which are now unretrievable from their stated resource location. Partly owing to limitations in available repository registry data and the existence of 'zombie' repositories, there are reasons to conclude that the total number of scholarly works referring to dead repository content is far higher. We also find evidence of dead repository content entering the current scholarly record, a phenomenon we describe as 'dead on arrival' referencing. We consider the implications of these observations, proffer explanations, and propose possible policy interventions to address the issue of repository persistence. Our dataset also enables us to make several observations about the nature of impersistent repositories, their profile, and their decay rate.
arXiv:2601.04509v2 Announce Type: replace Abstract: Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hardness. Recent learning-based methods typically model MILP instances as variable-constraint bipartite graphs and use Graph Neural Networks (GNNs) for representation learning, yet their locality limits representation power. We propose an attention-driven neural backbone that adopts an element-centric view of variables and constraints, with dual attention performing parallel intra-type self-attention and inter-type cross-attention. Across three representative tasks at the instance, element, and solving-state levels, our model consistently outperforms conventional GNN-based architectures, highlighting attention-based, element-centric modeling as a powerful foundation for learning-enhanced combinatorial optimization.
arXiv:2601.09498v2 Announce Type: replace Abstract: We investigate Dobrushin coefficients of discrete Markov kernels that have bounded pointwise maximal leakage (PML) with respect to all distributions with a minimum probability mass bounded away from zero by a constant $c>0$. This definition recovers local differential privacy (LDP) for $c\to 0$. We derive achievable bounds on contraction in terms of a kernels PML guarantees, and provide mechanism constructions that achieve the presented bounds. Further, we extend the results to general $f$-divergences by an application of Binette's inequality. Our analysis yields tighter bounds for mechanisms satisfying LDP and extends beyond the LDP regime to any discrete kernel.
arXiv:2601.12704v2 Announce Type: replace Abstract: The present study investigates the numerical solution of Black-Scholes partial differential equation (PDE) for option valuation with multiple underlying assets. We develop a physics-informed (PI) machine learning algorithm based on a radial basis function neural network (RBFNN) that concurrently optimizes the network architecture and predicts the target option price. The physics-informed radial basis function neural network (PIRBFNN) combines the strengths of the traditional radial basis function collocation method and the physics-informed neural network machine learning approach to effectively solve PDE problems in the financial context. By employing a PDE residual-based technique to adaptively refine the distribution of hidden neurons during the training process, the PIRBFNN facilitates accurate and efficient handling of multidimensional option pricing models featuring non-smooth payoff conditions. The validity of the proposed method is demonstrated through a set of experiments encompassing a single-asset European put option, a double-asset exchange option, and a four-asset basket call option.
arXiv:2601.15212v2 Announce Type: replace Abstract: Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and memory overhead, incompatibility with regularization, and suboptimal LR choices. In this work, we introduce the ZENITH (Zero-overhead Evolution using Norm-Informed Training History) optimizer, which adapts the LR using the temporal evolution of the gradient norm. Image classification experiments spanning 6 CNN architectures and 6 benchmarks demonstrate that ZENITH achieves higher test accuracy in lower wall-clock time than baselines. It also yielded superior mAP in object detection, keypoint detection, and instance segmentation on MS COCO using the R-CNN family of models. Furthermore, its compatibility with regularization enables even better generalization.
arXiv:2601.16211v3 Announce Type: replace Abstract: Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning asymmetry can promote object-driven shortcut learning. Our analysis with proposed diagnostic metrics shows that existing methods overfit to training co-occurrence patterns and underuse temporal verb cues, resulting in weak generalization to unseen compositions. To address object-driven shortcuts, we propose Robust COmpositional REpresentations (RCORE) with two components. Co-occurrence Prior Regularization (CPR) adds explicit supervision for unseen compositions and regularizes the model against frequent co-occurrence priors by treating them as hard negatives. Temporal Order Regularization for Composition (TORC) enforces temporal-order sensitivity to learn temporally grounded verb representations. Across Sth-com and EK100-com, RCORE reduces shortcut diagnostics and consequently improves compositional generalization.
arXiv:2601.22032v2 Announce Type: replace Abstract: End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited improvements. This limitation is compounded by the inherent ambiguity of driving: each scene typically provides only a single human trajectory, making it difficult to learn multimodal behaviors. In this work, we propose Drive-JEPA, a framework that integrates Video Joint-Embedding Predictive Architecture (V-JEPA) with multimodal trajectory distillation for end-to-end driving. First, we adapt V-JEPA for end-to-end driving, pretraining a ViT encoder on large-scale driving videos to produce predictive representations aligned with trajectory planning. Second, we introduce a proposal-centric planner that distills diverse simulator-generated trajectories alongside human trajectories, with a momentum-aware selection mechanism to promote stable and safe behavior. When evaluated on NAVSIM, the V-JEPA representation combined with a simple transformer-based decoder outperforms prior methods by 3 PDMS in the perception-free setting. The complete Drive-JEPA framework achieves 93.3 PDMS on v1 and 87.8 EPDMS on v2, setting a new state-of-the-art.
arXiv:2607.01630v1 Announce Type: new Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental sequences. We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate. We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two orthogonal mechanisms. For shared backbone representations, DRDN continuously applies masked image modeling (MIM) at every incremental step, with reconstruction gradients routed exclusively through the backbone, encouraging it to retain general visual structure beyond class-discriminative cues. For task-specific discrimination, DRDN employs hierarchical task token expansion across all transformer layers, with a modified per-task attention rule that reduces inter-task interference. We support this design with accuracy degradation analysis and cross-task confusion rate measurements. In the from-scratch ViT CIL setting (no external pretraining), DRDN consistently improves over strong token-expansion baselines with comparable backbone scale. On CIFAR100-B0 (10 steps), DRDN achieves 77.19% average accuracy, outperforming DKT by 1.36 points and DyTox by 3.53 points, with an advantage that grows at longer incremental sequences. Multi-seed validation confirms stability (+/-0.31%). The MIM decoder is active only during training, adding no inference-time parameters or computation.
arXiv:2607.01266v1 Announce Type: cross Abstract: We study binary classification problems whose decision sets are given by definable sets in o-minimal expansions of the real field. Motivated by cell decomposition of definable sets, we introduce traceable sets as a classical proxy for definable decision regions and analyze their approximation by ReLU neural networks. Under uniform bounds on the number of connected components and suitable $C^m$ extensions for the boundary functions, we prove that characteristic functions of traceable subsets of $[-1/2,1/2]^n$ can be approximated in $L^p$ to accuracy $\varepsilon>0$ by ReLU neural networks of size $\mathcal{O}(\varepsilon^{-p(n-1)/m})$, with depth independent of $\varepsilon$ and polynomially bounded weights. This establishes quantitative approximation rates for certain definable collections in o-minimal structures using ReLU neural networks. The same approach also yields the stated approximation rates for a subclass of definable maps $[-1/2,1/2]^n \to \mathbb{R}$. We then combine the approximation capabilities with entropy estimates for ReLU neural network classes to obtain statistical learning rates for empirical risk minimization with hinge loss. For $N$ uniformly distributed samples, the resulting classifiers achieve expected misclassification error of order $N^{-m/(m+pn-p)}$ up to an arbitrarily small polynomial loss.
arXiv:2607.02247v1 Announce Type: cross Abstract: The aggregation with exponential weights (AEW) estimator is not fully understood in the basic setting of model selection aggregation with squared loss. In particular, whether it is minimax-rate optimal in expectation for large enough fixed temperatures and under random design has been an open problem since its introduction, which was explicitly posed by Lecu\'{e} and Mendelson (2013). In this paper, we settle this problem by showing that \emph{without} requiring a Bernstein-type assumption, the AEW indeed achieves the excess risk $T \log (M) / (n+1)$ in expectation, whenever the temperature $T$ satisfies $(L^2/T)\exp(B/T)\leq \mu /2$. Here, the number of dictionary elements is $M$, the estimator has observed $n$ i.i.d. samples from any distribution, and the loss is assumed to be bounded by $B$, $L$-Lipschitz continuous and $\mu$-strongly convex. For squared loss, we show that $T\geq 4 b^2$ suffices when the predictions and labels are $[0,b]$-valued. Because AEW is known to be suboptimal in expectation for temperatures below some constant, this shows that AEW has a sharp phase transition when the temperature is large enough but constant, as conjectured by Lecu\'{e} and Mendelson.
arXiv:2602.00261v2 Announce Type: replace Abstract: Accurate sensing of chemical concentrations is essential for numerous biological processes. The accuracy of this sensing, for small numbers of molecules, is limited by shot noise. Corresponding theoretical limits on sensing precision, as a function of sensing duration, have been well-studied in the context of quasi-static and randomly fluctuating concentrations. However, during development and in many other cases, concentration profiles are not random but exhibit predictable spatiotemporal patterns. We propose that leveraging prior knowledge of these structured profiles can improve and accelerate concentration sensing by utilizing information from current molecular binding events to predict future concentrations. By framing the constrained sensing problem as Bayesian inference over an allowed class of spatiotemporal profiles, we derive new theoretical limits on sensing accuracy. Our analysis reveals that maximum a posteriori (MAP) estimation can outperform the classical Berg-Purcell and maximum-likelihood (Poisson counting) limits, achieving a sensing precision of $\delta c/c = 1/\sqrt{a^2N}$, where $N$ is the number of binding events, and $a > 1$ in certain cases. Thus knowledge of the statistical structure of concentration profiles enhances sensing precision, providing a potential explanation for the rapid yet highly accurate cell fate decisions observed during development.
arXiv:2602.00622v2 Announce Type: replace Abstract: The artificial intelligence revolution is fuelling a paradigm shift in weather forecasting: forecasts are generated with machine learning models trained on large datasets rather than with physics-based numerical models that solve partial differential equations. This new approach proved successful in improving forecast performance as measured with standard verification metrics such as the root mean squared error. At the same time, the realism of data-driven weather forecasts is often questioned and considered an Achilles' heel of machine learning models. How forecast realism can be defined and how this forecast attribute can be assessed are the two questions simultaneously addressed here. Inspired by the seminal work of Murphy (1993) on the definition of forecast goodness, we identify 3 types of realism: a functional realism measured by scoring functions, a structural realism related to the statistical characteristics of the forecasts, and a physical realism that is apprehended through the lenses of our scientific knowledge. This conceptual setting serves as a basis for the design of a new framework for the evaluation of data-driven weather models where falsification arises as a complementary process to the well-established diagnostic and verification tasks.
arXiv:2607.01922v1 Announce Type: new Abstract: Digital in-line holographic microscopy is a computational imaging method useful for characterizing the refractive properties of a sample, i.e. the phase shift and absorption. This indirect measurement technique captures a diffraction pattern and uses reconstruction algorithms to retrieve the optical properties of the sample. Since only the intensity of the diffracted wave is recorded on the sensor, this inversion is not trivial, and simple backward propagation leads to artifacts known in optics as the ``twin-image''. With advances in deep learning, various algorithms have been developed for the reconstruction of in-line holograms, providing computationally efficient alternatives to iterative algorithms. These algorithms rely either on supervised learning, which requires ground truth knowledge, or physics-based self-supervised algorithms that require additional information, like phase diversity, but require multiple holograms for inference. This paper introduces a new self-supervised physics-based deep learning strategy that leverages phase diversity during training and then reconstructs sample's transmission function from a single in-line hologram during inference. We introduce five datasets of simulated and experimental in-line holograms of beads and bacteria. The proposed method produces accurate quantitative reconstructions similar or even more accurate than those obtained by regularized inversion while reducing the computational time by a factor of 1000.
arXiv:2607.01927v1 Announce Type: new Abstract: This paper presents TUDUM (T\"urk\c{c}e D\"u\c{s}\"unen \"Uretken Model), a project pipeline for adapting a Qwen-family 27B thinking model toward Turkish reasoning. The central problem is not only to answer Turkish prompts in Turkish, but to make the explicit reasoning trace itself Turkish. A thinking model may translate a Turkish prompt into an English-centered internal or visible scratchpad, solve the problem mostly in English, and only localize the final answer. TUDUM instead treats the generated ... block as a trainable behavior. The pipeline starts from the project base checkpoint unsloth/Qwen3.5-27B, applies supervised fine-tuning (SFT) on 15,991 Turkish reasoning examples using LoRA adapters, and then applies GRPO-family reinforcement learning on a proxy-filtered Turkish mathematics environment. The results are mixed. SFT made the model shorter and more consistently Turkish in its reasoning behavior, with large reductions in average response length and thinking exhaustion, but reduced benchmark accuracy. RL recovered some mathematical performance, especially AIME24 at the best early checkpoint, yet did not uniformly improve all benchmarks and did not exceed the base model on the reported Macro-6 average. The contribution is therefore best framed as a technically honest Turkish-thinking reasoning pipeline and evaluation, not as a claim of state-of-the-art Turkish reasoning. The released step-50 model is publicly available.
arXiv:2602.01189v3 Announce Type: replace Abstract: We address the problem of reactive motion planning for quadrotors operating in unknown environments with dynamic obstacles. Our approach leverages a 4-dimensional spatio-temporal planner, integrated with vision-based Safe Flight Corridor (SFC) generation and trajectory optimization. Unlike prior methods that rely on map fusion, our framework is mapless, enabling collision avoidance directly from perception while reducing computational overhead. Dynamic obstacles are detected and tracked using a vision-based object segmentation and tracking pipeline, allowing robust classification of static versus dynamic elements in the scene. To further enhance robustness, we introduce a backup planning module that reactively avoids dynamic obstacles when no direct path to the goal is available, mitigating the risk of collisions during deadlock situations. We validate our method extensively in both simulation and real-world hardware experiments, and benchmark it against state-of-the-art approaches, showing significant advantages for reactive UAV navigation in dynamic, unknown environments.
arXiv:2607.01963v1 Announce Type: new Abstract: The movement distribution, and volume of both chyme and gas in the colon, are important metrics to understand colonic function in health, disease, and the effects of treatments and different foodstuffs. Current methods available for assessment of these colonic contents using MRI consist mainly of manual segmentation or semi-automatic segmentation. However, these methods of segmentation are very labour intensive and too slow for clinical applications, require expert knowledge and some semi-automatic methods require use of bowel preparation. MRI scans were acquired in 2 breath holds using mDIXON sequences. We used the 'No New U-Net' (nnU-Net) ML model to automatically segment the colon, including colonic regions (ascending, transverse, descending and sigmoid-rectal). The ML-generated masks were corrected manually and the time taken for correction was recorded. ML segmentations were compared to both manual segmentations and observer corrected ML (CorrML) segmentations. Observer repeatability was also evaluated for both manual and CorrML methods to create a benchmark for the allowable error in the automatic segmentations. Analysis time was significantly reduced (p<0.0001) from 56 mins (+-11 mins (SD)) for manual masks to 11 mins (+-5 mins (SD)) for CorrML masks. Both DICE and ICC values showed excellent agreement between manual, ML and CorrML segmentations for whole colonic volume (ICC = 0.96) whilst regional volumes were good-excellent (ICC = 0.80-0.95). Inter-observer repeatability was improved when using CorrML methods over manual segmentation (ICC manual > 0.89, CorrML > 0.93). Analysis time was reduced by over 80% when using CorrML methods and whole colonic volumes measured by ML would be suitable for use with minimal checks. Hence the methods proposed here would be clinically useful.
arXiv:2607.01246v1 Announce Type: new Abstract: Recent proposals for HTTP-based sustainability disclosure focus on \textbf{what} environmental information should be transmitted at the protocol boundary, for example through response headers, but leave open the practical question of \textbf{how} such per-request values can be generated in realistic deployments. This paper addresses that implementation gap. We present a model-based approach for estimating resource consumption and $CO_2e$ per HTTP request without requiring fine-grained production power telemetry. The approach benchmarks endpoints offline under controlled conditions, derives compact endpoint-specific energy models from observable request features, and evaluates these models online at the HTTP server boundary. We implement this mechanism as an nginx extension that loads a JSON model registry and emits per-request metadata for energy, grid intensity, embodied emissions, and total request-level impact. We show that heterogeneous request classes can be represented with constant, linear, and piecewise models, and that the same approach extends to endpoints whose dominant cost driver is only visible at the application layer through inputs such as token counts. Our evaluation indicates that the approach is operationally feasible and introduces only low runtime overhead.
arXiv:2312.08376v3 Announce Type: replace Abstract: In this paper, we propose a novel locally statistical active contour model (LACM) based on Aubert-Aujol (AA) denoising model and variational level set method, which can be used for SAR images segmentation with intensity inhomogeneity. Then we transform the proposed model into a global optimization model by using convex relaxation technique. Firstly, we apply the Split Bregman technique to transform the global optimization model into two alternating optimization processes of Shrink operator and Laplace operator, which is called SB_LACM model. Moreover, we propose two fast models to solve the global optimization model , which are more efficient than the SB_LACM model. The first model is: we add the proximal function to transform the global optimization model to a general ROF model[29], which can be solved by a fast denoising algorithm proposed by R.-Q.Jia, and H.Zhao; [29] was submitted on 29-Aug-2013, and our early edition was ever submitted to TGRS on 12-Jun-2012, Venkatakrishnan et al. [30] proposed their PnP algorithm on 29-May-2013, so Venkatakrishnan and we proposed the PnP algorithm almost simultaneously. Thus we obtain a fast segmentation algorithm with global optimization solver that does not involve partial differential equations or difference equation, and only need simple difference computation. The second model is: we use a different splitting approach than one model to transform the global optimization model into a differentiable term and a general ROF model term, which can be solved by the same technique as the first model.
arXiv:2411.13121v3 Announce Type: replace Abstract: The growing IoT landscape requires effective server deployment strategies to meet demands including real-time processing and energy efficiency. This is complicated by heterogeneous, dynamic applications and servers. To address these challenges, we propose ReinFog, a modular distributed software empowered with Deep Reinforcement Learning (DRL) for adaptive resource management across edge/fog and cloud environments. ReinFog enables the practical development/deployment of various centralized and distributed DRL techniques for resource management in edge/fog and cloud computing environments. It also supports integrating native and library-based DRL techniques for diverse IoT application scheduling objectives. Additionally, ReinFog allows for customizing deployment configurations for different DRL techniques, including the number and placement of DRL Learners and DRL Workers in large-scale distributed systems. Besides, we propose a novel Memetic Algorithm for DRL Component (e.g., DRL Learners and DRL Workers) Placement in ReinFog named MADCP, which combines the strengths of Genetic Algorithm, Firefly Algorithm, and Particle Swarm Optimization. Experiments reveal that the DRL mechanisms developed within ReinFog have significantly enhanced both centralized and distributed DRL techniques implementation. These advancements have resulted in notable improvements in IoT application performance, reducing response time by 45%, energy consumption by 39%, and weighted cost by 37%, while maintaining minimal scheduling overhead. Additionally, ReinFog exhibits remarkable scalability, with a rise in DRL Workers from 1 to 30 causing only a 0.3-second increase in startup time and around 2 MB more RAM per Worker. The proposed MADCP for DRL component placement further accelerates the convergence rate of DRL techniques by up to 38%.
arXiv:2607.01573v1 Announce Type: new Abstract: We initiate the study of *unate distributions* over $\{\pm1\}^n$ -- a natural analogue of unate Boolean functions -- by considering two basic testing problems that parallel well-studied questions for monotone distributions: - Uniformity Testing of Unate Distributions: We show that $\widetilde{\Theta}(n^{3/2})$ samples are sufficient and necessary, in contrast to the $\widetilde{\Theta}(n)$ sample complexity of the analogous problem for monotone distributions (Rubinfeld and Servedio, STOC 2005; Adamaszek, Czumaj, and Sohler, SODA 2010). - Unateness Testing of Arbitrary Distributions: We give a tester that uses $\widetilde{O}(n^{3/2})$ conditional samples in the subcube conditional model. On the other hand, every tester that draws conditional samples in a similar fashion, namely from $O(1)$-dimensional subcubes, must have an $\widetilde{\Omega}(n^{2/3})$ complexity. In the same model, the complexity of monotonicity testing was recently shown to be $\widetilde{\Theta}(n)$ (Chakrabarty et al., STOC 2025). Our algorithms for both problems significantly outperform the naive approach of reducing to the monotone case, which would incur $\Omega(n^2)$ sample complexity. Our uniformity tester relies on a subroutine that "weakly" learns the hidden orientations of a unate distribution, together with a new correlation bound for these estimates. Both tools may be of independent interest in studying monotonicity and unateness over $\{\pm1\}^n$.
arXiv:2607.01617v1 Announce Type: new Abstract: Large language model (LLM) serving increasingly combines prefill-decode (PD) disaggregation with tensor parallelism (TP) to support large models and long contexts. In conventional 2D/2.5D chiplet architectures, layer-wise prefill-to-decode KV-cache transfer decode-side TP collectives share the same lateral die-to-die (D2D) interconnect, creating mixed-traffic contention on the decode critical path. This contention increases communication latency, prolongs token generation intervals, and degrades end-to-end serving performance. We propose 3DLS, a logic-on-logic 3D-stacked chiplet architecture that separates traffic classes by routing KV-cache transfers through vertical interconnects while preserving decode-side TP collectives on the lateral D2D fabric. 3DLS achieves up to 1.49$\times$ throughput and 60.2\% lower end-to-end (E2E) latency over the shared-fabric planar baseline, and still achieves up to 1.17$\times$ throughput and 31.4\% lower E2E latency over a workload-aware priority-managed planar baseline. These results highlight that physical isolation is an important design principle for future chiplet-based PD-disaggregated LLM serving systems.
arXiv:2607.01602v1 Announce Type: new Abstract: SRAM-based FPGAs provide an attractive platform for energy- and latency-constrained CNN inference at the network edge, yet transient faults can lead to silent errors that compromise reliability. Always-on redundancy (e.g., full TMR) improves correctness but incurs substantial performance and energy overhead, while reactive recovery may introduce unacceptable latency on the critical path. We propose \textbf{ProWAFT}, a proactive workload-aware fault-tolerance framework for FPGA-based CNN accelerators that uses partial reconfiguration to selectively apply TMR across reconfigurable partitions. ProWAFT quantifies workload criticality, models fault propagation and reconfiguration overhead, and selects configurations that minimize a composite objective over latency, energy, and reliability risk. Implemented on a Xilinx Zynq UltraScale+ ZCU104 platform with six reconfigurable regions and evaluated on a 500-task trace derived from ResNet-18, MobileNetV2, and EfficientNet-Lite under time-varying SEU injection, ProWAFT achieves lower composite cost than static TMR and reactive reconfiguration while maintaining high task success rate and near-baseline throughput with low online decision overhead.
arXiv:2607.01605v1 Announce Type: new Abstract: CityGML, the OGC standard for modeling, storage, and exchange of semantic 3D city models, describes urban objects with detailed semantics, geometry, and topology. Yet this richness is difficult to query directly: CityGML's XML encoding is designed for exchange rather than analysis, and relational mappings expose it through schemas requiring expert knowledge. We present pykci (Python Knowledge Graph for Cities), an open-source system that transforms CityGML 2.0 datasets into a compact urban knowledge graph in Neo4j and makes it queryable in natural language. The graph schema covers all thematic feature modules of CityGML 2.0 across all levels of detail and is spatially indexed with an R-tree for efficient geometric retrieval. A complete end-to-end Python pipeline ingests CityGML datasets into the knowledge graph, exports them to OGC 3D Tiles for interactive visualization, and supports lossless round-trip export of all content back to CityGML. For querying, the graph is paired with a large language model through a model-agnostic text-to-Cypher mechanism: the graph schema is supplied as context, and the model translates natural-language questions into Cypher queries executed against the graph. We evaluate both a locally running open-weight model, which keeps sensitive city data on-premise, and a state-of-the-art commercial model for the most demanding spatial and semantic queries. Answers are grounded in exact city data rather than the model's parametric memory, reducing hallucination and providing auditable provenance for every response. We demonstrate the system on open-government CityGML LoD2 datasets from Hamburg, Germany, including complex semantic and spatial queries such as identifying roof surfaces suitable for greening. pykci enables urban planners, GIS practitioners, and citizens to interact with semantic 3D city models without expertise in query languages and database schemas.
arXiv:2511.20274v2 Announce Type: replace Abstract: In the paradigm of computer vision-based precise real-world scene understanding, joint reasoning in terms of contextual understanding about the objects present in a scene, their inter-object relations, and the action being performed is an essential prerequisite. However, prior works have not addressed all three jointly, and no large-scale dataset provides grounded annotations at all three levels across diverse visual scenarios. Hence, this work introduces the SCLARO (Scene-Contextual Localisation of Actions, Relations & Objects) dataset, consisting of 615,805 images spanning indoor, outdoor, and driving scenarios, annotated with global action captions, object bounding boxes, and relation triplets that supply structured scene context beyond a free-text caption. To benchmark the dataset, we propose ScenarioCLIP, a tri-level reference model that jointly encodes global scene context, objects, and inter-object relations using disentangled encoders and EMA-based knowledge distillation. We benchmark across a comprehensive suite of tasks on the SCLARO Dataset, namely zero-shot retrieval, linear probe, object detection, predicate classification, scene-graph classification, and out-of-domain generalisation. ScenarioCLIP's disentangled encoders improve over the previous works, such as PyramidCLIP's shared encoder, most notably at the object and relation levels and on out-of-domain generalisation. Code for the data generation pipeline and ScenarioCLIP is available at https://github.com/scenario-clip/SCLARO-ScenarioCLIP