Papers

Instruction-guided video editing requires executing a requested change while preserving the source video's appearance and temporal structure. We present SemantiScene-Edit, a video editor that couples a multimodal encoder with a pretrained video diffusion transformer. The encoder jointly processes source frames and the editing instruction, and learnable queries convey their semantic context to the generator through a trainable connector and cross-attention. A complementary visual pathway concatenates source-video latents with noisy target latents before patch embedding, supplying dense spatial and temporal information for content preservation. We train the model with flow matching and a three-stage image–video curriculum comprising semantic alignment, joint adaptation, and high-resolution refinement. To support training, we construct over 1.2 million instruction-conditioned video-editing records covering object addition, removal, replacement, and attribute modification. We also construct a 100-case benchmark for evaluating instruction execution, source preservation, temporal consistency, and visual quality. Comparative experiments show that SemantiScene-Edit effectively follows editing instructions while retaining source content. At inference, the model requires only a source video and a natural-language instruction.

Private 5G networks are a key enabler for flexible industrial automation, especially when used in conjunction with Time-Sensitive Networking (TSN) technology. In this context, radio schedulers must multiplex safety-critical control traffic with bandwidth-hungry sensing streams over a fixed spectrum allocation. This paper proposes a Head-of-Line (HoL) Enhanced Hybrid Lyapunov scheduler for 5G-TSN networks that augments a drift-plus-penalty queue-stability core with an explicit head-of-line delay term and a class-isolation mechanism. The scheduler is evaluated in a 3GPP Indoor Factory scenario with standardized 3GPP fading, spatial consistency, and clutter blockage, using Automated Guided Vehicles (AGVs) generating concurrent URLLC, eMBB, and mMTC flows mapped to dedicated QoS-flow bearers. A fleet-size sweep of 5–30 AGVs on a fixed 20\,MHz carrier reveals a scheduler-independent capacity threshold at approximately 12 vehicles, verified by resource-block saturation. Below the threshold, the proposed scheduler is competitive with the strongest delay-aware baselines and its head-of-line term halves the URLLC deadline-miss ratio relative to the plain Lyapunov formulation. Beyond the threshold, it degrades selectively where the baselines collapse: at $2.5\times$ overload it delivers $1.8\times$ more URLLC traffic than the proportional-fair and delay-budget-aware baselines with a $\approx 4$–$7\times$ shorter 99th-percentile latency, resolving the capacity shortfall in favour of the critical classes instead of spreading it across the traffic mix, at a quantified cost in aggregate cell throughput. The results position Lyapunov-based scheduling as an attractive overload-robustness mechanism for industrial 5G deployments that must remain dependable under unexpected load conditions.

Multi-agent reinforcement learning (MARL) commonly trains decentralized policies from scratch, requiring agents to acquire individual task competence and coordination simultaneously. Yet many multi-agent problems admit a compatible single-agent counterpart in which the underlying task can be learned in isolation. We introduce Multi-Agent Observation Transformation for Existing Single-Agent Policies (MATES), an input-side adaptation framework for tasks whose multi-agent observations preserve the solo-task information while exposing separately identifiable neighbor information. From multi-agent experience, MATES learns a small adapter that maps this observation into the format expected by a frozen single-agent policy, inducing actions suited to the shared environment without updating the single-agent policy itself. MATES leaves the pretrained policy's internal architecture unchanged and retains the objectives and update procedures of the underlying MARL algorithm. We evaluate MATES using both on- and off-policy algorithms on lifelong pathfinding, navigation, and cooperative discovery, spanning discrete and continuous observation and action spaces. Across all evaluated settings, MATES optimizes only 3.5-7.3% as many parameters as full-policy training while consistently outperforming MARL training from scratch. It approaches the performance of full fine-tuning, remains competitive overall with demonstration-based baselines, and retains strong task performance at team sizes not encountered during training. These results provide evidence that, under this observation structure, effective multi-agent behavior can be learned without modifying the policy that encodes individual competence.

The increasing complexity in design and manufacturing has driven the need for advanced techniques for fast modeling problems with large-dimensional parameter spaces. Avoiding high-fidelity finite element models while achieving fast and accurate simulations in such contexts is challenging. Parametric model order reduction (pMOR) has drawn significant attention in recent years. Nevertheless, the curse of dimensionality in parameter spaces has severely limited its effectiveness. The active subspace (AS) approach has been successfully applied to pMOR for systems with many parameters. However, the balance between accuracy and compactness of the reduced model remains problematic for such systems with high-dimensional parameter spaces. It often results in models that are either not small enough or not accurate enough. In this paper, we propose an iterative active subspace (IAS) approach for parametric model order reduction, which, to some extent, addresses the trade-off between accuracy and reduced model size and achieves substantial computational gains compared to the original active subspace method.

Monocular drone navigation requires reaching a goal in an unseen environment from a single forward-facing camera, which offers few cues for depth and scale. World models address this by modelling how observations evolve under actions, but they are built to be executed: the prediction is produced at deployment and fed back into action generation at every control step. We argue that what a policy needs from a world model is not the prediction but the representation required to produce it: in flight the executed action explains almost all of the change between observations, so prediction reduces to reprojecting a static scene under a known displacement. We therefore introduce skytopia, a policy built on an action-conditioned latent world model, and the 3D Gaussian Splatting platform on which it is trained. A forward objective predicts the representation of the next observation from the intended motion, and an inverse objective recovers that motion from the predicted transition. Because the prediction never reaches action generation, the predictor is discarded and one policy serves point-goal, image-goal, and goal-free navigation. Simulation experiments show that skytopia outperforms every baseline under all three specifications, attaining 57.8%, 66.0%, and 49.0% success rate, while discarding the predictor removes 59.4% of the inference cost. The same policy is subsequently deployed on a physical drone without fine-tuning and reaches goals in indoor, open outdoor, and woodland environments.

The Matching-Match puzzle asks whether the vertices of a fixed graph can be colored so that the multiset of color pairs induced by its edges is exactly a prescribed multiset. We study how the complexity of this realization problem depends on the host graph. On the dense side, we give a polynomial-time algorithm for complete $k$-partite graphs for every fixed number $k$ of parts, with arbitrary precoloring and an arbitrary number of colors. We prove a sharp complement-degree threshold: the problem is polynomial-time solvable when $\Delta(\overline G)\le1$, but NP-complete on completely uncolored graphs already when $\Delta(\overline G)=2$. This yields a dichotomy for uniform complete multipartite graphs, and connected diameter two already suffices for NP-completeness. We also prove W[1]-hardness on cographs parameterized by the number of colors. On the sparse side, completely uncolored paths and cycles admit a linear-time characterization by Euler trails and circuits, while counting feasible colorings is $\#P$-complete on both classes. Counting is nevertheless polynomial-time solvable on stars and complete graphs, even with arbitrary precoloring. A decomposition-transfer theorem yields NP-completeness already at tree-depth two. A separate path-decomposition reduction gives a maximum-degree threshold between one and two for completely uncolored disconnected host graphs with unrestrictedly many colors. Components with at most two edges are tractable, while a disjoint union of $P_4$'s is NP-complete. Finally, precoloring restores tractability in several cases: star forests are polynomial when every center is precolored, and two broad precoloring regimes on length-two spiders are polynomial even when the number of colors is unbounded.

Most research on the manipulation of deformable objects focuses on lightweight systems with negligible mechanical response, effectively restricting attention to quasi-static regimes. This assumption excludes a broad class of practically relevant objects, such as hoses, pipes, and wiring harnesses, whose dynamics cannot be ignored during manipulation. In this work, we address this limitation by introducing a closed-loop control architecture that explicitly accounts for object dynamics and recasts manipulation as a shape-regulation problem. Control is achieved by modulating forces and torques applied at multiple fixed points along the object. This approach builds on three methodological contributions: a fully dynamic model of linear deformable objects based on discrete strain parameterizations; an extension of the notion of actuation coordinates to SE(3), yielding a structured and inherently underactuated control architecture; and nonlinear feedback strategies providing explicit conditions for steady-state convergence to desired configurations. Extensive simulations on representative manipulation tasks demonstrate the performance gains enabled by the proposed modelbased formulation. We finally validate the approach experimentally through a real-time closed-loop implementation with online shape estimation, confirming its practical feasibility and effectiveness

In this paper, an abstract framework is introduced for the derivation of reliable a posteriori error estimators for variational inequalities of the second kind. Under certain conditions (local) efficiency of the error estimators can also be derived. The framework is based on the estimation of a residuum which results from an equivalent mixed formulation and from the replacement of the Lagrange multiplier by its (possibly post-processed) discrete counterpart. The approach is applied to an idealized frictional contact problem and a Mosolov type model problem in an $hp$-finite element discretization setup. Several numerical experiments demonstrate the broad applicability of the theoretical findings.

Speech enhancement (SE) models typically rely on supervised learning with paired data examples where clean speech is synthetically degraded. This paradigm limits performance in real-world scenarios where the target environment's specific acoustic characteristics are unknown. We propose a fully unpaired SE framework that uses principled Diffusion Schrödinger Bridges (DSB) to learn a stochastic transport process between a clean and a degraded speech distribution. Algorithms for learning transport maps are computationally heavy since they require simulating differential equations during training, usually at each training step. Therefore, we propose using a high-efficiency Mamba Diffusion Model designed for end-to-end waveform processing. We compare against state-of-the-art methods for speech enhancement, both paired and unpaired, as well as a classical signal processing algorithm. Experimental results show that we are on par or better than the baselines while being orders of magnitude faster during inference. Furthermore, we show that the flexibility of the DSB formulation allows our model to generalize across SE tasks, offering a robust and efficient solution for real-world speech restoration.

Providing safe and effective mobility assistance plays a crucial role in restoring independence and enhancing the quality of life for individuals with motor impairments. In this context, robotic walking assistive devices have recently emerged as promising solutions to provide physically compliant interaction while ensuring user safety and support. This paper presents a novel control framework for an omnidirectional Walking Assistive Robot (I-WANDER) that integrates a Control Barrier Function (CBF) formulation into a Model Predictive Control (MPC) scheme to explicitly enforce collision-avoidance safety constraints while optimizing for energy efficiency and smooth human-robot collaboration. The method was experimentally evaluated with 12 healthy participants performing two different walking tasks using both the proposed CBF-based MPC controller (CB-MPC) and a variable admittance controller (AC). The first task involved structured navigation through a U-shaped corridor, whereas the second consisted of a single-obstacle avoidance task performed blindfolded to ensure the obstacle was unexpected. Comparative results show that the CB-MPC architecture significantly reduces energy consumption and mechanical work (p < 0.01) without compromising motion smoothness, while also decreasing the number of obstacle collisions. Overall, the findings highlight the potential of the proposed control architecture to enhance both safety and efficiency in robotic walking assistance.

Retrieval-augmented generation (RAG) gives large language models (LLMs) access to external knowledge, but its conventional retrieve-concatenate-generate pipeline makes retrieval decisions on behalf of the model. As tool use and agent loops become more reliable, an agent can decide whether to retrieve, what to inspect, and when to stop. This shift exposes a new bottleneck: the agent may not know what a knowledge base contains. Traditional knowledge bases expose documents as anonymous text chunks with limited information about scope, purpose, provenance, or relations. We propose Knowledge-as-Skill, an organization scheme that makes a knowledge base discoverable, navigable, and self-descriptive. It has three layers: a discovery layer centered on SKILL.md; a navigation layer with one index.md per directory; and a knowledge layer containing documents with YAML frontmatter for topic, type, provenance, and lifecycle. The design follows the Open Knowledge Format (OKF) and the Skill protocol without modifying the agent framework. We also provide knowledge-as-skill, a pipeline for converting heterogeneous collections of PDFs, Word files, web exports, and notes into this structure. In a preliminary evaluation on the WixQA enterprise customer-support benchmark, our setup obtains 0.889 Factuality and 0.816 Context Recall, compared with reported Corpus2Skill values of 0.767 and 0.708. It obtains slightly lower Faithfulness, lower Context Precision, and more interaction turns. Because the models, prompts, and knowledge-package construction differ, these results are directional cross-work evidence rather than a controlled comparison.

Equivariant convolutional neural networks are usually built from a group acting globally on the space of signals. This hypothesis is inappropriate for many bounded or stratified domains: an ambient rigid motion may be admissible only on part of the domain, and the boundary introduces geometric types that are invisible to a transitive group action. We develop a theory of groupoid-equivariant neural networks in which the symmetry datum consists of a groupoid, a selected pseudogroup of local bisections, a measure, and input and output representation bundles. For integral channels on the object space, we prove a bisection-equivariant kernel theorem: equivariance is equivalent to a transport constraint on the two-point kernel, and its solutions are classified by one joint-stabilizer intertwiner on each orbit of pairs. As a case study we apply the theory to bounded planar domains. The resulting architecture is implemented through offline nullspace bases and sparse gather–transform–scatter operations. A Poisson–Dirichlet kernel study is used separately to assess boundary-aware inductive bias; the exact inverse is shown to preserve the global symmetries of the rectangle but not general proper local bisections. The numerical results show that the proposed architectures provide significant advantages when symmetries cannot be globally implemented by group actions and provide an accuracy improvement of at least one order of magnitude with respect to the models tested.

Probabilistic time series foundation models (TSFMs) provide coordinate-wise predictive distributions, but these marginals do not determine a joint distribution over multivariate future trajectories. We study training-free coupling of frozen TSFM marginals into multivariate forecast sample paths. Our primary evaluation fixes the empirical marginal sample multiset at every channel–horizon coordinate across methods, isolating the effect of coupling alone. Historical temporal and channel relations substantially improve their corresponding dependence diagnostics. The same pattern persists when the fixed-marginal constraint is removed and paths are sampled directly, and remains present under native multivariate backbone inference. These results support treating dependence reconstruction as a distinct post-processing problem for probabilistic TSFMs.

This article introduces the LUneburg-lens-aided recoNfigurable Array (LUNA), an antenna architecture that unifies multiple-input multiple-output (MIMO) and network-controlled repeater (NCR) functionalities in the Luneburg lens-enabled hardware platform. A Luneburg lens, fabricated from graded-index dielectric materials, passively converts the radiation of a low-gain feed into a highly directional beam without active phase shifting, while a dense passive feed bank and a reconfigurable feed-selection network electronically switch the beam directions with minimal hardware complexity and power consumption. We commence by reviewing the basic principles and application history of Luneburg lenses in radar and wireless communications, which motivates their role in 6G-and-advanced networks. Then, we highlight how a Luneburg lens and a reconfigurable feed array construct both LUNA-MIMO and LUNA-NCR, where the lens and feed bank can be reused across functions and frequency bands. Case studies demonstrate that LUNA achieves the satisfactory spectral and energy efficiency with a few radio-frequency chains, and it also improves positioning performance for sensing tasks. Finally, some open problems and research directions are provided to inspire follow-up research on LUNA.

Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect a model's true decision process and may therefore mislead clinicians. We investigate this problem using a Vision Transformer-based breast MRI classifier trained on the ODELIA Breast MRI Challenge dataset and evaluate multiple saliency methods, including Last-layer Attention, Attention Rollout, Grad-SAM, Gradient Attention Rollout, GMAR, Grad-CAM, and HiResCAM. Our study highlights two often-overlooked challenges in perturbation-based faithfulness evaluation. First, method rankings depend strongly on the perturbation strategy, varying across intensity-based perturbations and transformer-based attention masking. Second, benchmarking saliency methods requires distinguishing between class-specific and class-agnostic explanations. To enable fair comparisons, we introduce non-class-specific variants of gradient-based methods and evaluate both settings separately. Across protocols, Grad-CAM and Gradient Attention Rollout consistently emerged as the strongest class-specific methods, although their relative ranking depended on the evaluation design. These findings expose important limitations of current saliency-based explainability approaches and highlight the need for more robust and standardized evaluation frameworks for trustworthy clinical AI systems.

This paper presents a comparative study of multimaterial topology optimization (MMTO) using the extended SIMP, Discrete Material Optimization (DMO), and generalized shape functions (gSF) approaches. The computational domain is discretized into hexagonal cells. Each cell is connected to its neighbors with edges. This characteristic reduces mesh-related effects on the optimized designs compared with conventional triangular and quadrilateral discretizations. Structural compliance is minimized at the prescribed volume fractions. The method of moving asymptotes is employed to update the design variables. The resulting optimized topologies are compared in terms of material distribution, structural performance, convergence behavior, and the characteristics of the obtained material interfaces. The comparative investigation provides insights into the working principles and performance of the extended SIMP, DMO, and gSF interpolation schemes for MMTO.

NAWE (Neural-Assisted Watermark Extraction) combines an explicit signal-processing watermarking construction with a pretrained neural host predictor. A periodic, perceptually masked watermark carrier provides synchronization, Polar coding supplies redundancy, and denoising followed by subtraction extracts the embedded watermark. The denoiser remains frozen, without watermark-specific training. A one-factor-at-a-time study compares Wiener, BM3D, DRUNet, and GS-DRUNet host estimators. Comparisons with TrustMark, SSL Watermarking, PixelSeal, and WAM show NAWE's lowest geometric and photometric class BER and strong message recovery, while filtering and noise remain limitations consistent with the non-adaptive selection of the watermark extractor. The comparison retains the systems' different payloads and coding.

The idea that emotions in biological systems are analogous to intrinsic colored noise is advanced and justified. A model describing the dynamics of operation of biological networks under the influence of colored noise is suggested. The agents of a biological network can be represented either by biological species, such as humans and animals, or by neurons of the brain, or by the nodes of a neural network. Operational actions, or decisions, in a biological noisy network are based not only on the evaluation of utility of alternatives, but also on the agents emotions. The model is probabilistic, with the choice of alternatives characterized by the related probabilities. At the initial step, the agents make decisions individually and then start exchanging information with each other and imitating the actions of other agents, thus forming a biological network of interacting agents. Numerical simulations are accomplished for a heterogeneous society consisting of three groups of agents, one group possessing long-range memory, the other group, short-range memory, and the third group of super-rational agents acting strictly on the basis of utility, being deprived of emotions. Dynamics of opinions in different groups can be smooth, oscillatory, or chaotic. Altogether, eight types of operation are found, depending on the dynamics of group decisions. Under strong imitation effect, there appears chaotic motion in the evolution of decision choice. It is shown how the Ellsberg paradox can be resolved and how the exchange of information influences the dynamics of this paradox.

Legged robots under sparse waypoint guidance must avoid moving obstacles using partial, rapidly changing LiDAR observations. We present LOOP (Latent-recurrent Occupancy rollOut Policy), a local avoidance policy that connects sparse waypoint guidance to a frozen locomotion controller at 50 Hz. From occupancy and ego-velocity histories, a recurrent predictor forecasts future occupancy over a 1 s horizon by warping the current map with learned flow and visibility gates. These maps guide velocity selection through map-derived features and geometric risk estimates, providing an explicit interface for inspecting and replacing predictions. In encounter-synchronised Isaac Lab evaluations, LOOP achieves 57.1% head-on success at obstacle speeds of 2.5-3.2 m/s, exceeding a retrained reactive baseline by 8.2 percentage points. Comparisons with a rollout-free BEV policy show smaller, scenario-dependent gains from the prediction branch, including improved crossing success and reduced variability across training seeds at the highest head-on speeds. The adapter runs onboard a Unitree Go2 in 14.5 ms per step and completes all 16 real-world crossing trials without collision, demonstrating deployment feasibility.

This paper introduces GRIP, a pose-conditioned refinement framework for pixel-to-point matching and 2D to 3D registration. Given an initial coarse pose estimate, GRIP addresses the structural mismatch between grid based image descriptors and unordered point cloud descriptors by softly rendering learned 3D point features onto the image grid through Gaussian feature splatting. The rendered point derived feature map is then fused with image features by a pixel aligned transformer, enabling visual semantic and geometric cues to interact in a shared 2D representation. The refined features are decoded and propagated to finer resolutions for dense correspondence estimation and final pose refinement. Experiments on RGB D Scenes V2 and 7 Scenes demonstrate state of the art inlier ratio and competitive registration recall, with stronger performance under stricter evaluation thresholds.

Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on heuristic grouping strategies that disregard layer-specific activation geometries. We introduce a principled, training-free framework that sequentially optimizes cross-layer weight pairings and shared-dictionary factorizations. Rather than forcing weights of adjacent layers to share a basis or heuristically merging activation statistics, our approach identifies structurally compatible projections and learns a shared representation that better preserves each layer's distinct calibration geometry. Coupled with structured sparsity, this yields highly efficient weight decompositions without sacrificing functional fidelity. Across diverse architectures, scales, and modalities, our method achieves state-of-the-art results, consistently outperforming independent structured weight decompositions and alternative pairwise weight factorizations, which operate under heuristic grouping strategies. By replacing heuristic engineering strategies with a convergent, optimization-driven pipeline, we establish a theoretically grounded foundation for scalable, transformer compression across different modalities.

Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification problems remain computationally intractable in the worst case: even for common adversarial robustness specifications, verification is NP-complete. Here, we explore the application of solver-level warmstarting for neural network verification to exploit information from previous solutions. We study the effect on running time as several properties are modified, including perturbation radii, input data and the networks themselves, using a pipeline that is generalisable and potentially adaptable to state-of-the-art verifiers. Our results show that warmstarting can significantly reduce verification time in most cases. Moreover, warmstarting enables the successful verification of instances that could not be solved from scratch within the given time limit.

Generative visual models offer a foundation for learning representations of physical dynamics, yet their extension to continuous control raises a fundamental question: do visual prediction and action generation require separate computational pathways? Existing approaches usually introduce trainable action heads or separate action experts to bridge low-dimensional states and high-dimensional visual representations. In this work, we explore whether the visual backbone's existing capacity can also support control when actions are expressed in a compatible representation. Thus, we introduce PatchWAM (Patch World-Action Model), which treats continuous actions as another type of patch through a fixed mapping called Action-as-Patch. This allows a single model to predict both how the robot should move and what the scene may look like afterward. Visual prediction and action generation become parts of the same generative process, without a dedicated action head or separate action expert. Experiments with subsampled training windows show gains over a matched dual-expert control, while benchmark evaluations reach 91.8% success rate on LIBERO-Plus and 96.12% on RoboTwin 2.0 in a full-data setting with additional augmented demonstrations. More broadly, the result suggests that capability need not be added where it can be inherited: the constraint on extending a generative backbone is the interface a new signal is written in, not the capacity to model it.

When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even when a settlement message was dropped and the agent never had a chance: they intervene on agent actions and do not expose infrastructure faults as intervenable variables, so every dollar they explain is charged to a decision. We take a benchmark whose fault process is explicit and replayable, decompose each episode's realised delivery schedule into named, individually repairable messages, and intervene on both the agent's choices and the infrastructure's. A telescoping identity splits any policy's loss exactly three ways: an infrastructure effect, a policy differential against the best implementable policy, and a reference-policy residual. Two of the three can be negative, so none is a share; Shapley then divides the first into signed allocations over individual messages. One result is structural and needs no corpus: an agent-only baseline identifies no infrastructure cause, because its model contains no variable that could name one. What 545 planted episodes across 3 policies measure is the size of that consequence. It misfiles 100% of infrastructure episodes and charges $114,383.40 to the agent. Repairing what it names recovers 0.0% of the available loss; repairing a minimal sufficient set recovers 100.0%. Scoring messages one at a time is not merely imprecise: 27.8% (95% CI: 23.3–32.3%) of episodes do not decompose additively. We evaluate deterministic programmatic policies rather than language-model agents, which is what makes replay exact and which limits external validity to stochastic agents. The prevalence figures are properties of this generator, not field rates.

Web answer synthesis with Mixture-of-Agents (MoA) requires reliable factual support for every atomic claim, yet agreement among agents is not verification. Correlated proposers can repeat a shared misconception, and a correct specialist fact receives little support when the other proposers stay silent. We introduce C-MoA, which decomposes MoA outputs into atomic claims, scores inter-agent semantic support, and calibrates claim retention at the level of whole answers. Under exchangeability and a policy frozen before calibration, it provides distribution-free marginal control of the probability that an answer retains any claim unsupported by the reference labels. Because calibration only selects a cutoff on a fixed ranking and cannot repair shared errors, we also study CONTRA-MoA, an optional extension that adds blinded near-miss tournaments, leave-one-agent-out stability, and availability-aware fusion, and we derive a competence–discrimination law for its verifier. Across 300 splits of the FactScore biography benchmark, the mean rate of fully supported answers (Fact) exceeds all six nominal targets, but only $1.7\%$–$9.8\%$ of supported claims are retained and $30\%$–$75\%$ of answers are empty. At $\alpha=0.10$, mean agreement retains $3.1\%$ of supported claims, about $3.4$ times the $0.9\%$ retained by the best single-proposer score. On the medical Golden Dataset, it retains $37.3\%$ at a mean Fact of $0.898$, slightly below the $0.90$ target, and on NQ mean Fact reaches $0.904$. On a separate balanced FactScore cohort, memory-only counterfactual scoring is close to chance (AUC $0.522$ on 182 claims), and raw maximum fusion lowers the agreement AUC from $0.687$ to $0.652$. These results separate the statistical calibration of factuality from informative claim verification and clarify the role of each in multi-agent Web synthesis.

All the eigenvalues of an integral graphs are integers. Integral graphs are extremely rare. They form an asymptotically vanishing fraction $2^{-\Omega(n)}$ among all graphs on $n$ vertices. It makes the construction of a new family of integral graphs a challenging task. Also, most of the known infinite family of integral graphs rely on Cayley graphs over Abelian groups. In this article, we introduce a new family of integral graphs obtained from the groups. The construction of our graphs from groups is different from the construction of Cayley graphs. A spectral uniqueness theorem is established, which shows that each member of the infinite family is determined by its adjacency spectrum among all finite simple graphs. We also present recursive constructions that generates larger members of the family from smaller ones, providing a scalable class of integral graphs. Finally, we investigate algebraic realizations of these graphs as complements of Proper Prime Order Element Graphs of finite $2$-groups and obtain conditions characterizing such realizations. We also observe that the graphs obtained from different non-isomorphic groups have cospectral graphs.

Dementia care at home increasingly involves connected sensors, medication devices, electronic records, and assistive technologies. Professionals and family carers must still interpret these observations, reconstruct context, coordinate responses, and verify resolution. Sustaining safe care at home while ensuring timely clinical escalation requires continuity between these tasks. Agentic engineering creates a systems opportunity by combining model interpretation with persistent external memory, planning, authorised tool use, and outcome feedback. This paper presents Governed Closed-loop Agent Coordination (GCAC), an architecture for bounded agent participation in community dementia-care workflows. Evidence on coordination failures and policy obligations is translated into traceable system requirements. GCAC separates observation, four governed memory classes, planning, deterministic policy enforcement, execution, and outcome monitoring through a typed event-memory-decision-action-outcome contract. A worked medication-device example explains how these roles maintain context, allocate responsibility, and distinguish an unrecorded dose from a clinically established omission. A reference harness evaluates 18 evidence-derived traces spanning care gaps, service failure, consent change, stale state, duplicate events, untrusted text, and acute-change routing. GCAC satisfies all 18 contract oracles with zero policy-violating tool calls; event-threshold and stateless-planner controls satisfy 2/18 and 1/18, respectively. Six ablations identify the contribution of memory, policy, and versioning. The results establish architectural conformance. Effects on hospital use, quality of life, staff workload, unpaid care, and net costs require prospective evaluation. GCAC provides a testable basis for accountable coordination that preserves human authority over consequential care decisions.

To mitigate the challenges of climate change and intensifying heat stress in urban areas, local adaptation strategies are discussed and introduced in cities worldwide. To understand processes and potential trade-offs of these strategies a Bayesian optimization and surrogate modeling framework was employed to investigate urban parameter ranges of heat mitigation strategies with focus on three thermal metrics: daytime air temperature, Universal Thermal Climate Index (UTCI), and nighttime air temperature. Based on an urban street canyon configuration, it was shown that heat mitigation measures that reduce daytime air temperature and UTCI are often associated with higher nighttime temperatures. This results in a curved Pareto front that reflects the trade-off between daytime and nighttime thermal comfort. Under identical forcing conditions, different urban configurations, varying in geometry, vegetation, and surface characteristics, are shown to alter peak canyon air temperature by up to 5.2~$^\circ$C during the day and 2.6~$^\circ$C at night, while UTCI varies by up to 7.9~$^\circ$C, demonstrating that favorable urban configurations can substantially mitigate microclimatic heat stress. These findings suggest that combining multi-objective Bayesian optimization and surrogate modeling can help bridge the gap between computationally intensive climate simulations and practical decision-making in urban planning. An interactive visualization tool was developed to explore these trade-offs, making the often opposing relationships between urban parameters and the three thermal metrics directly accessible to planners.

Low-resource text-to-speech (TTS) adaptation is constrained by scarce paired data and costly manual transcription. Existing fixed-voice TTS systems can provide relatively accurate pronunciation, but their synthetic speech offers limited speaker diversity and may exhibit flat prosody. Real recordings provide natural prosody and diverse voices, yet their automatic speech recognition (ASR) pseudo-labels may contain transcription errors. We find that supervision order affects content accuracy and speaker similarity. We propose trust-aware progressive adaptation: synthetic-to-real adaptation first establishes text-speech correspondences, then restores reference-speaker control using real speech. Transcript-agreement weighting uses agreement between two fixed ASR systems as a proxy for pseudo-label reliability to limit noisy supervision. Experiments with FireRedTTS3 on Burmese and Lao and OmniVoice on Burmese show improved content accuracy with high naturalness and competitive speaker similarity. Jointly considering supervision order and pseudo-label reliability when combining synthetic and real speech offers a practical path to zero-shot voice cloning in low-resource languages with less manual transcription. Audio demos are available at https://insiderx-pro.github.io/S2R-Adaptation-TTS/

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.