Papers

Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense attention is computationally expensive for high-resolution imagery, while conventional feature fusion and coarse decoding may inadequately separate genuine changes from appearance variations or preserve object boundaries. We present Bitemporal Mamba-Diffusion for Change Detection (BMD-CD), which combines temporally structured state-space modeling with logit-space diffusion refinement. BMD-CD converts deep bitemporal features into region tokens and arranges them in explicit temporal partitions before bidirectional state-space propagation. Its Bitemporal Ordered Mamba Operator enables long-range cross-temporal interaction with linear sequence complexity, while Orthogonal Feature Disentanglement forms a change-oriented output and a complementary rotated output using learned pairwise rotations and unchanged-region consistency. Multiscale decoding then produces coarse change logits, which are refined through a five-step Conditional Diffusion Decoder operating directly in logit space. Experiments on LEVIR-CD, WHU-CD, DSIFN-CD, CDD, and S2Looking demonstrate strong performance across diverse change-detection settings. BMD-CD achieves F1 scores of 93.7%, 96.0%, 97.8%, and 99.0% on the four standard benchmarks and improves 3-pixel Boundary-F1 to 87.7% and 91.4% on LEVIR-CD and WHU-CD, respectively. The full model requires 32.09 GFLOPs and 47 ms per 256 x 256 image pair, while also showing zero-shot transfer to ValaisCD and B-FLAIR-test. Our code is available at https://github.com/Aparup2139/Public_WACV/

Static chart images are widely used in scientific publications, business reports, and presentations, yet recovering both the underlying data and visual design from chart images remains a labor-intensive manual process, making them difficult to reuse. While prior work has primarily focused on data extraction, the extraction of visual design specifications, including colors, marker shapes, and axis configurations, remains underexplored. To identify a suitable model for chart reconstruction, we systematically benchmark five multimodal large language models (MLLMs) across five basic chart types on both data and design extraction tasks. Our evaluation shows that textual and categorical information can generally be extracted reliably, whereas numeric and spatial information remain challenging. Among the evaluated models, GPT-5.4 achieves the best overall performance and is adopted as the backbone of our system. Guided by these findings, we present ChartRevive, a mixed-initiative system that combines MLLM-based extraction with an interactive verification interface, supporting users to efficiently inspect, correct, and refine reconstructed charts through overlay-based verification and real-time rebuilding.

Robot navigation methods tend to avoid contact, and consequently search for collision-free trajectories. For robots with high inertia and limited maneuverability, however, avoiding contact can require substantial steering effort and time, even when interactions with surrounding surfaces could be safely exploited. In this paper, we develop a planning method that deliberately uses controlled wall reflections to generate trajectories that can be easier and more efficient to execute than purely collision-free motion. We consider planar navigation in environments where a mobile robot is permitted to bounce off surrounding surfaces. To represent the resulting alternatives, we construct a reflection-augmented state graph in which paths are partitioned into distinct classes according to the sequence of walls used for reflection. This representation enables systematic enumeration of reflection strategies and identification of the lowest-cost path within each class. We show that, although a reflecting path cannot be shorter than the shortest collision-free path, it can reduce execution time and actuation effort by replacing costly changes in heading with controlled environmental interactions. The planned trajectories are executed using a contact-aware sampling-based controller with the robot's full dynamics. In our experiments, we demonstrate that in our simulated test scenario, the best reflecting class can reduce time and control effort. Our results show that controlled contact can provide dynamically advantageous navigation strategies that are excluded by conventional collision-avoidance formulations.

We consider the problem of learning risk scores to prioritize individuals for scarce resources or interventions, from historical observational data affected by unobserved confounding. Decisions about who receives scarce resources are often guided by risk scores based on recorded characteristics, such as responses to a survey. These risk scores are increasingly being learned directly from observational data: historical records of individuals' characteristics, allocation decisions, and outcomes. Standard methods such as inverse propensity weighting (IPW), which corrects for the bias introduced by the historical allocation policy, can be used to learn accurate risk scores if the historical decision process is fully explained by the recorded characteristics. In practice, however, historical decisions often depend on unrecorded information, causing learned risk scores to systematically under-prioritize exactly the individuals whose unrecorded circumstances drove past prioritization. We propose a method for learning risk scores that are robust to this kind of unobserved confounding, building on IPW. Since propensity weights cannot be reliably estimated under unobserved confounding, we instead treat them as belonging to an uncertainty set determined by the observable data and domain-informed estimates of the degree of confounding, combining sensitivity analysis from causal inference with Wasserstein distributionally robust optimization. The resulting robust risk score learning problem admits a sample-based approximation that we reformulate as an exponential cone program compatible with off-the-shelf solvers. We demonstrate the effectiveness of our approach on semi-synthetic data derived from datasets in the UCI Machine Learning Repository. Our method improves calibration by up to 29.2% over traditional benchmarks and up to 11.1% over the state of the art, without compromising other metrics.

Infrastructure-based radar systems offer robust and long-range solutions for traffic monitoring, yet their detection and tracking performance under real-world conditions remains insufficiently evaluated. This study introduces DRaT (Drone and Radar Trajectories), a dual-modality dataset of naturalistic vehicle trajectories collected at a highway merging segment in Fort Worth, Texas, to systematically assess radar sensing performance against drone-derived ground truth. The performance is evaluated at three levels: individual vehicle detection, trajectory tracking, and macroscopic traffic parameter estimation. For individual vehicle detection, the radar achieves an overall precision of 78% and a recall of 57%, with degraded performance under congested traffic conditions and at longer distances. At the trajectory level, the radar demonstrates reasonably strong tracking performance (IDF1 = 0.699), maintaining reliable vehicle identities when tracks are successfully established. For macroscopic traffic flow metrics, the radar accurately estimates space-mean speed (MAPE < 4%) but underestimates density and volume by approximately 23% due to missed detections. The paper also discusses practical deployment considerations and potential downstream applications of roadside radar sensing systems. To support reproducible research on infrastructure-based sensing systems, we have open-sourced the DRaT dataset on Zenodo: https://zenodo.org/records/20171110.

Text-to-image retrieval with frozen dual encoders degrades when the query names a small, visually subordinate object in a cluttered scene: a single global image embedding underrepresents the localized visual evidence. We present MINER, a training-free inference framework that augments a frozen dual encoder's global image embedding with a small bank of region-level embeddings and a hubness-correcting similarity rescoring, recovering visual evidence that global pooling underweights. To evaluate this setting, we introduce ROCS, a benchmark built from high-clutter subsets of Flickr30K and MS COCO whose images are re-captioned to name a single low-salience object. Experiments on CLIP, SigLIP, and SigLIP 2 show that MINER improves retrieval on every backbone, on ROCS and on the standard splits. Analyses show that these gains come primarily from broader spatial coverage rather than precise crop placement, revealing a simple and general way to recover localized evidence from frozen representations. Code: https://github.com/aalquwayfili/MINER. Dataset: https://huggingface.co/datasets/aalquwayfili/ROCS.

The stochastic block model is a paradigmatic model of networks with community structure. Yet percolation in the model has been studied primarily in cases with a fixed block structure, even though in real networks, the community structure may evolve as the network grows. Here we study percolation in sequences of stochastic block models in which the numbers and sizes of communities, as well as the intra- and intercommunity connection probabilities may all change with the network size. We analyze five such sequences using two methods: linearized self-consistent equations for the locally tree-like models and a branching process at the community scale for the models with nonvanishing clustering. We find that the critical average degree is not generally equal to $1$, even in locally tree-like sequences, because the transition depends on how connections are distributed across the evolving community structure. We also show that the community-scale branching process accurately predicts the transition when intercommunity connections are sufficiently sparse, even in the presence of nonvanishing clustering, while a geometric stochastic block model sequence demonstrates the limitations of this method when correlations between intercommunity connections cannot be neglected. These results extend percolation studies in the stochastic block model to more realistic scenarios with evolving community structure, and may provide new methods to derive the upper and lower bounds for the percolation threshold in geometric long-range percolation.

Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics that ignore cross-level coherence and error structure. In this paper we make two contributions to address this problem, (i) we introduce SurgHiBench, the first hierarchy-aware evaluation suite for surgical video understanding, with three tasks measuring recognition, consistency, and severity across granularity levels. We evaluate a general-purpose CLIP model, a Euclidean surgical model, and, as second contribution: (ii) HyperSurg, a new hyperbolic model that enforces phase-step containment via entailment cones, across four (existing) datasets spanning three procedure types. The suite reveals that two models with the same accuracy can produce predictions of very different error severity, ranging from sibling confusions within the correct phase to unrelated cross-phase predictions. Hyperbolic geometry shifts predictions toward the correct procedural neighborhood, and these gains scale with the tree-likeness of each dataset's annotation hierarchy, providing a principled indicator when hierarchy-aware geometry helps.

Single-image super-resolution of Sun's photospheric magnetograms enables consistent analysis across heterogeneous space-based instruments and supports long-term studies of solar magnetic field evolution. We address the super-resolution task from SOHO/MDI (low-resolution) to SDO/HMI (high-resolution) line-of-sight (LOS) magnetograms using a modified RRDBNet architecture initialized by ESRGAN pretrained weights. Through systematic per-image diagnostic analysis, we identify image complexity as the dominant predictor of reconstruction errors. To exploit this finding, we introduce an adaptive stratified specialist ensemble (SSE) of three specialist networks with uncertainty estimation, where each specialist network is trained by images from three different complexity strata using a weighted random sampling strategy. During inference, a lightweight router based on input image statistics assigns each test image to the appropriate specialist network. Our experimental results demonstrate the good performance of the proposed ensemble and its superiority over closely related methods.

We prove quantum soundness of the total-degree diagonal line-vs-point test using the individual-degree soundness theorem of Ji, Natarajan, Vidick, Wright, and Yuen. A random change of coordinates yields projective polynomial decoders of total degree at most $md$. The uniform-line slice of the test bounds the weight of outcomes of degree greater than $d$, which are removed by a common relabeling. This reduction does not yield a dimension-independent soundness bound: the $\operatorname{poly}(m)$ dependence of the individual-degree theorem persists, as discussed in Section 1.2 of arXiv:2009.12982.

Federated Learning enables decentralized model training by exchanging model updates–rather than raw data–with a central parameter server (PS). While most of the existing defenses primarily assume static or independently acting adversaries, we reveal a new class of dynamically adaptive attacks that systematically bypass such protections. We propose Fed-ADR, a holistic attack framework in which a malicious orchestrator server (OS) dynamically coordinates a heterogeneous set of adversarial clients, including both targeted and untargeted attackers. Through real-time coordination by the OS, malicious clients strategically adapt their gradient updates to evade defenses deployed by the PS, while either severely degrading global model performance or steering training toward adversarial objectives.To mitigate this threat, we offer a detection mechanism that estimates each client's true gradient from historical updates, enabling real-time detection of coordinated malicious behavior without additional overhead. We further introduce an in-situ recovery mechanism that restores global model performance without restarting training, preserving convergence and minimizing recovery time. Comprehensive experiments on MNIST, Fashion-MNIST, and CIFAR-10 benchmark datasets demonstrate that Fed-ADR's attack scheme can reduce global accuracy from over 90% to below 10%, bypassing several state-of-the-art defenses. When our detection and recovery modules are employed, they identify malicious clients and restore accuracy to over 90% within a few rounds, at a substantially lower cost than retraining from scratch–achieving a reduction of at least 20x in computational overhead.

Heterogeneity across Collaborative Perception (CP) agents is a major challenge for emerging CP frameworks due to domain gaps from differing sensors, architectures, and training data. Prior works mitigate this challenge by aligning features in a unified space via model retraining or per-agent-type interpreters. These strategies (a) require access to neighbor configurations, (b) do not fully address real-time CP deployment, and (c) generalize poorly to unseen agents joining at run time. To overcome these challenges, we present PEARL, a Prompt-Embedding framework for Anonymous and Real-time Lightweight heterogeneous CP. PEARL supports multiple CP interpreters and selects one for a new-joining agent in real time using two lightweight, multi-scale interpreters trained in parallel: a sparse-detection (LWSD) interpreter that aligns salient regions for cooperative detection, and a dense, domain-invariant (LWDDI) interpreter that produces agent-invariant features for fast interpreter selection. Both interpreters use low-rank visual prompts to reduce computation, storage, and model complexity. Extensive experiments on simulated (OPV2V, V2XSet) and real (DAIR-V2X) datasets show that PEARL generalizes across simulated and real-world cooperative driving scenarios. Its real-time model-selection strategy yields an 8.2% Average Precision (AP) gain over a random-selection baseline while running in 1.67 ms on average. Although primarily designed for real-time CP, PEARL also outperforms state-of-the-art heterogeneous CP frameworks under traditional offline training by 5.6% AP on average while reducing communication cost by up to 34.7 times. Equally important, PEARL does not require sharing agents' configurations or model settings, thereby protecting information that may be proprietary or private. These results establish PEARL as a scalable and practical framework for heterogeneous collaborative perception.

Greenhouse climate management aims to improve crop production while limiting energy use. This requires knowing how a crop will respond before conditions are changed. A crop digital twin can support this decision only if it represents how plant physiology and structure develop together. A unified framework was developed to simulate lettuce growth from the physiology of individual leaves. Each leaf received the conditions at its position in the canopy and contributed carbon through photosynthesis. Part of this carbon was used for maintenance and the remainder supported growth, distributed among leaves by their age, size and local environment. The predicted leaf mass, area and age generated an evolving three-dimensional plant in NVIDIA Isaac Sim. Ray tracing calculated the radiation intercepted by each leaf and returned it to photosynthesis, so structure and growth influenced each other over time. Against greenhouse measurements, the relative root mean square error was 9.5% for total dry weight and 9.2%, 12.7% and 13.1% for leaf number, canopy diameter and largest-leaf area, respectively. A 30% decrease in incident radiation reduced final dry weight by 10.4%, while the same increase raised it by 6.9%, and adding 200 ppm carbon dioxide raised it by 46.1%. Within a simulated 40-plant block, interior plants accumulated 8.6% less dry weight than border plants with identical initial states, and the leaf-specific tipburn index rose in the enclosed leaves over the period in which tipburn appeared on the greenhouse plants. Resolving individual leaves therefore explains how local exposure changes plant growth within the greenhouse. The framework provides the forward plant model needed for a bidirectional digital twin, where observations of the physical plant can update predictions and support greenhouse climate decisions.

The Minimum Sum Vertex Cover (MSVC) problem asks for an ordering of the vertices of a graph that minimizes the sum, over all edges, of the time at which each edge is first covered. We study the problem through the structure of vertex covers and obtain new approximation and exact algorithms, together with conditional lower bounds. For graphs of maximum degree $\Delta$, we show that a simple ordering algorithm based on a minimum vertex cover achieves approximation ratio $R_\Delta \le {(\sqrt{\Delta}+1)}/{2}$. For $d$-regular graphs, we give a polynomial-time $1.184$-approximation by combining Max-$k$-Vertex-Cover approximation with a structural bound on optimal prefixes. On the exact side, we give an algorithm parameterized by the vertex cover number $k$ running in $2^{O(k\log k)} + O(n+m)$ time, improving the previous dependence on $k$, where $n$ and $m$ are the number of vertices and edges in the graph, respectively. We also develop a separator-based exact algorithm running in $ 2^{O(\sqrt n \log n)}$ time on planar, bounded-genus, and fixed-minor-free graph classes. Finally, we prove that Minimum Sum Vertex Cover is NP-hard on planar graphs and, assuming ETH, admits no $2^{o(\sqrt n)}$-time exact algorithm on $n$-vertex planar graphs. Thus our planar upper bound is tight up to logarithmic factors in the exponent.

A face recognition model links two images of a person recorded on separate occasions when their embedding similarity exceeds an operating threshold. We consider making chosen identities unlinkable across separate occasions while the model remains in service for the rest of the population. Deleting their images and retraining does not achieve this, since the model recognises identities never observed in training. Therefore, the embedding space must be altered against these identities, the process of which we call open-set adversarial forgetting. We propose three loss functions, one that disperses an identity's embeddings from their centroid, and two that map each image onto its own near-orthogonal target, learnt with the classifier head or fixed in advance as an almost-orthonormal frame. Each is fine-tuned alongside the classification objective on a subset of each identity's images. We evaluate them against four methods from prior work in verification and identification, at two forget scales and three backbones. Every loss acting on the embedding geometry makes the forget identities nearly unidentifiable. The orthonormal frame alone achieves strong forgetting, which holds wherever an image of that subset enters the comparison and leaves distinct forget identities unlinkable. It also surpasses a concurrent unsupervised method at a higher retain rate.

Image quality assessment predicts a mean opinion score (MOS), but for image aesthetics the mean hides the individual, so personalized assessment must start from the few images a new user rates. Fitting each person from scratch fails with ten ratings; networks fine-tuned per person carry over poorly to new kinds of images. We present Undertone-P, which learns from other raters a Gaussian prior over per-person regression weights on read-outs of frozen vision-language model (VLM) judges: the probability-weighted rating and the hidden state at the score token. Since people differ from the crowd in ways other raters reveal, a few ratings need only choose among those ways: a new user costs one closed-form solve, and no network is trained. On Ryu and Yanaka's PARA benchmark, the prior alone reaches a Spearman correlation of .640, above the best published 10- and 100-rating results (.581 and .620); 10 and 100 of a person's ratings raise it to .648 and .676. These ratings add most where tastes depart from the crowd: with 100 ratings, +.067 for the raters who agree least with it and +.206 on LAPIS artworks, against +.037 overall. Without labels, the judges' expected scores predict PARA's MOS at .835 (best published model we ran: .694). PARA-trained networks still lead under PARA's original protocol, likely through a stronger end-to-end MOS model.

Generalized planning aims to compute a plan that solves all instances of a planning domain. Recent work has used LLMs to automatically generate and debug such generalized plans in the form of Python programs and achieved perfect test data coverage for several domains. However, whether these generalized plans are actually complete, i.e. solve all instances of the domain, could only be determined by manual evaluation. Here, we present an approach for automatically generating generalized plans in Lean together with proofs of their completeness relative to a specification of the domain constraints provided as input. We introduce a semantic-preserving PDDL-to-Lean conversion, and use an LLM to generate both the generalized plan and the formal proof that it solves every instance satisfying the domain constraints. The correctness of the completeness proof is determined by Lean's kernel. We evaluate our approach on 13 commonly used benchmark domains, using GPT-5.6-Sol as the LLM. For 12 of the domains we obtain generalized plans together with valid completeness proofs. This is a major advancement of the state of the art in automatic generalized-plan completeness proofs.

Generative visualization increasingly embeds large language models within direct manipulation and multisensory interaction. Speech, gaze, touch, gesture, sound, and haptics can make probabilistic inference feel like familiar, deterministic tool use. I call this gap a deterministic-affordance mismatch: deterministic interaction cues persist while AI weakens predictability, locality, reversibility, or provenance. Reading the malleable interfaces of Iron Man 2 against systems from Blade Runner 2049, I propose productive friction, including cross-sensory renderings whose detail reflects model uncertainty. Four frictions expose the inference boundary, match action to effect, make stochastic branches tangible, and attribute sensory agreement.

Dark pools are designed to provide pre-trade privacy, liveness, and post-trade confidentiality - concealing order flow before execution and limiting information leakage after. Decentralized dark pools, such as Renegade, aim to replicate these properties without custodial risk, using secure multi-party computation (MPC) and zero-knowledge proofs for private order matching and verifiable settlement. We show that Renegade's cryptographic guarantees do not deliver these dark pool properties in practice. MPC-with-abort ensures correctness but not fairness: a party may learn the match result and abort without penalty, breaking pre-trade privacy. We demonstrate that the protocol's discovery layer further leaks trading intent before MPC even begins, and that sustained probing via selective abort can probabilistically reconstruct counterparty order history, threatening post-trade confidentiality. We also show that the absence of input-consistency checks prior to MPC execution enables a griefing attack using invalid state commitments requiring no real token holdings that continuously locks honest users' wallets and wastes compute, breaking liveness under sustained conditions. We further analyze over 700,000 Renegade transactions on Base and probe the P2P layer, finding that the network is effectively centralized: 88% of traffic routes through a handful of relayers, with only four nodes sustaining the P2P layer. Since relayers hold their users' wallet state in plaintext, this concentration means the system operates as a centralized orderbook in practice - reproducing off-chain the information asymmetry that dark pools are designed to eliminate. Together, our results show that cryptographic privacy does not imply dark pool security: pre-trade privacy, liveness, and post-trade confidentiality each require additional protocol-level guarantees beyond MPC correctness.

Surgical robots require highly dexterous and compact robotic systems capable of operating effectively within confined anatomical spaces. However, due to limited access provided by a single incision, the miniaturization and maneuverability of these robots still need to be improved. In this paper, we propose the design and modeling of a single-port three-arm robotic tool containing one major cannula (7.14 mm outer diameter (OD)) and three steerable minor cannulas (1.93 mm OD). By integrating the proposed 12 degrees-of-freedom (DoFs) steerable robotic tool with a 7-DoF robotic arm, this robotic system can potentially achieve multi-arm manipulation capability. We present the design of the steerable robotic tool consisting of tendon-driven joints controlled by a compact actuation system, derive the kinematic model, and validate both the static and kinematic models through experiments. The performance is evaluated with the root mean square error (RMSE) and mean absolute error (MAE) computed between the experimental data and the kinematic model.

Robotic embodiment encompasses the sensing, kinematics, dynamics, geometry, actuation, and control through which an agent physically interacts with the world. These properties vary across robots and change over time. We argue that general embodied intelligence requires learning that accumulates across these differences. Prevailing methods that engineer correspondences to bridge embodiment differences offer immediate practical gains, but their assumptions limit the scope of transfer in the long run. Instead, a more general approach should discover representations that support transfer to a larger range of embodiments as experience grows. We propose embodiment diversity as a promising axis of scaling, and identify broad learned priors as a complementary ingredient. We call for evaluations that better characterize embodiment gaps and transfer performance. More broadly, cross-embodiment learning connects the practical challenge of learning from heterogeneous robot experience with a broader scientific pursuit inspired by nature - physical intelligence that adapts and co-evolves with its embodiments to gain agency over its behavior and physical forms.

Automatic tagging is a core task in Music Information Retrieval (MIR), yet most tagging systems exploit only audio. Live music performance is inherently multimodal, as semantic labels such as instruments, regional styles, and dance forms are encoded simultaneously across acoustic, visual, and embodied performance cues. This is especially true of culturally specific repertoires such as Greek traditional music, which remain underrepresented in MIR benchmarks. In this paper, we investigate whether the use of dancer pose provides complementary information for automatic tagging in Greek traditional music beyond audio. Using the Lyra dataset, we extend prior audio-only work by extracting aligned video features and pose-derived skeleton streams, enabling an experimental setting for multimodal auto-tagging. We further introduce an automated pipeline for extracting primary-dancer skeleton sequences from in-the-wild dance footage, combining dance-scene detection, multi-person tracking, dancer selection, pose estimation, and quality filtering. We compare unimodal, all bimodal combinations, and trimodal systems using multiple fusion strategies. Audio remains the strongest single modality (AST: macro ROC-AUC 0.821), while skeletons, though weak in isolation, enhance performance through multimodal fusion. The best trimodal system improves macro ROC-AUC by about 4 percentage points over the strongest audio baseline.

Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit set poorly positioned for the classifier. We separate these causes with an exact-mass linear program and two learned post-hoc repairs. Every reweighted prediction has an equivalent centered logit translation, but only translations in a message-induced displacement set are realizable by reweighting. Across eight datasets, eight GNN backbones, and ten splits, mean accuracy rises from 62.6% for the frozen models to 63.8% with reweighting and 65.3% with set-conditioned translation. A parameter-matched node-only translator reaches 64.6%, showing that translation explains most of the gain while the message set supplies a smaller additional benefit. Although oracle reweighting can correct many errors, label-free reweighting captures little of this potential: local evidence is often present but hard to select, and relaxing the evidence constraint is more effective than learning within it.

The growing adoption of blockchain technologies, particularly the Ethereum platform, has amplified the critical role of smart contracts in decentralized applications. However, the increasing complexity and financial value of these contracts make them prime targets for cyber attacks. In this work, we present a transformer-based approach for the detection of vulnerabilities in smart contract fragments written in Solidity. Leveraging the representational power of pre-trained Large Language Models (LLMs), we construct a robust pipeline that includes the definition of a ground truth dataset, labeling code fragments as vulnerable or safe. We then fine-tune a BERT-based architecture on this dataset, enabling the model to capture the syntactic and semantic patterns specific to Solidity code. Our fine-tuned model demonstrates strong performance, achieving an F1 score of 92%, and highlighting the effectiveness of LLM adaptation in enhancing smart contract security through deep contextual understanding.

Multi-passage corpus poisoning often repeats one target claim across similar documents, creating correlated lexical and semantic patterns that similarity- and conflict-aware defenses can suppress jointly. We introduce DnD (Divide and Doubt), a targeted attack based on two principles: distributing support for the target answer across stylistically diverse passages, and including a passage that casts doubt on evidence for the reference answer. The first disperses poison-passage representations in embedding space, while the second strengthens target adoption when multiple poisoned passages are retrieved. We evaluate DnD on two open-domain QA datasets across three LLMs and nine RAG configurations, under both black-box and white-box access to the retriever. Across these settings, DnD matches or outperforms prior attacks in most configurations, with its largest gains against clustering- and conflict-aware defenses.

Elongate multi-legged robots use coordinated body waves and distributed legs to move through cluttered terrestrial environments. However, as housing actuators for independent leg control can require bulky body segments, their non-streamlined body and limb structure makes it difficult to achieve swimming capability comparable to their terrestrial locomotor performance. At the water surface, we found that the multi-legged robots we tested unexpectedly moved backward: their body waves traveled in the same direction as their displacement, i.e., swimming with a direct wave. We found similar behavior in the centipede Lithobius forficatus, which swims with a direct body wave and periodic leg movement. To study how distributed legs contribute to direct-wave swimming, we analyze animal kinematics and develop a multi-legged robophysical model that allows independent variation of leg morphology and stiffness, body-wave direction, and leg coordination. Robophysical experiments show that direct body waves produce consistent forward motion under the tested conditions and that swimming performance depends on body–leg coordination. Additionally, directionally compliant legs increase displacement from approximately 0.08 to 0.21 body lengths per cycle relative to rigid legs under matched anti-phase actuation. These findings clarify how distributed appendages contribute to surface swimming and establish gait and morphology design principles for extending multi-legged field robots from terrestrial locomotion into aquatic environments.

Organizations increasingly use LLMs for policy, compliance, risk, and operational decision support, requiring evidence validation, review routing, version control, and auditability. We introduce Policy-as-Skill (PaS), a modular runtime that packages these functions as executable, versioned policy capabilities. Thirteen methods are evaluated with a fixed Gemma4 backend on 600 development tasks. PaS+Audit achieves 53.8% exact accuracy, macro-F1 0.346, review F1 0.854, citation precision 1.000, policy-reference recall 0.984, and audit completeness 1.000, outperforming LLM+RAG on most governance and review metrics. Deterministic control raises aggregate accuracy to 61.2% but is strongly task dependent, supporting selective rather than universal rule-based intervention.

NADI 2026 is the seventh edition of the Nuanced Arabic Dialect Identification (NADI) shared task series and the second dedicated to multidialectal Arabic speech processing. This edition comprises five tasks and eight subtasks spanning Automatic Speech Recognition (ASR), Spoken Dialect Identification (SDID), Text-to-Speech (TTS), Spoken Language Translation (SLT), and Spoken Language Understanding (SLU). NADI 2026 emphasizes realistic evaluation through low-bandwidth, mixed-dialect, code-switched, out-of-domain, and zero-shot settings, while introducing TTS, SLT, and SLU to the series for the first time. The shared task attracted 21 participating teams from at least 13 countries, with 48 test-phase submissions and 14 submitted system-description papers. Results show that out-of-domain generalization remains a major bottleneck and highlight the effectiveness of recent Arabic-specialized speech models, multimodal dialect identification approaches, and ensemble methods. Overall, NADI 2026 provides a broader and more challenging benchmark for robust Arabic dialect speech processing.

As serving capacity demand surpasses that of training, serving efficiency becomes increasingly important. Prefill-decode (P/D) disaggregation improves serving efficiency through specialization and isolation of the two phases. These benefits rest on a static partitioning. Phase demand, however, is not static. We observe that in a large LLM fleet the ratio of uncached input to output tokens has peak-to-mean ratios up to 4.7x at minute timescales, and that in a public agentic trace the hourly ratio spans a median 24.5x within a single day, while reassigning a replica takes tens of minutes. Agentic traffic sharpens the mismatch. Sizing each pool at its ninety-fifth percentile leaves up to 17% of cluster capacity unused; sizing below it converts the same imbalance into queueing and unrealized throughput. We present Crossflow, which makes this boundary elastic without changing node roles. Each decode node publishes a short-lived, revocable lease that bounds local-prefill compute, KV capacity, transfer work, and projected output. Across public and internal traces, Crossflow improves token throughput by 16.2-17.4% on geometric mean over static P/D, and by up to 43.4% at high load, while reducing mean TTFT at every evaluated point.

We systematically investigate breather solutions in the modified Korteweg-de Vries (mKdV) equation via numerical simulations. We show that the breather solutions are stable under a variety of perturbations, including amplitude changes, modifications of internal parameters, and perturbations of the nonlinearity of the equation. Our results are not only consistent with the known analytical studies on the stability of breathers in integrable systems, extending them further, but also provide numerical evidence that such breather-type structures can persist and remain stable over the simulated time scales in some non-integrable settings with symmetric potentials.