Papers

Architectures have been proposed to control entanglement generation in multi-user quantum networks. To allow time for local operations and classical communication at end nodes, these architectures insert fixed separations between consecutive batches of entanglement generation attempts. This reduces network utilization when attempts fail, leaving the network idle during the scheduled separation. To address this limitation, we propose a novel method to reclaim this idle time by shortening the scheduled separation between attempts while respecting hardware constraints. The method uses an analytical execution model to optimize the separation and reduce the total network service time of an application. Evaluations within the Arqon architecture show network service time reductions of up to 42 minutes (7.6%) for single applications and 16-29 minutes (26-30%) per application when co-scheduled. The approach applies broadly to quantum network architectures that share hardware between entanglement generation and local operations, and the method can be used online by network schedulers.

Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, stage before deployment. The default recipe, quantization-aware training (QAT), re-fits the compressed, quantized model to hard labels; in our pipeline it converged slowly and collapsed past its peak. We adopted Quantization-Aware Healing (QAH) instead. Because a structurally compressed model is never independently trained at full precision, its bfloat16 checkpoint is a distillation-recovered approximation of the original; QAH distills the 4-bit student directly from the original, uncompressed model. On a GPT-OSS 120B to 60B to MXFP4 pipeline, the QAH student matches or beats its bfloat16 source on 7 of 9 benchmarks at roughly 4 times less weight memory and half the teacher's parameter count, and is released open-weight as Hypernova-60B. Against a matched QAT baseline it reaches a comparable peak about 7 times faster and stays stable under continued training, without hand-tuned early stopping. We also report deployment lessons, including a large, reproducible quality gap between distributed-training backends. Our aim is a recipe deployable without a multi-week hyper-parameter search.

Autonomous flight in unknown cluttered environments is hindered by the computation-quality-memory trilemma of onboard trajectory generation. In this paper, we propose an efficient end-to-end local planner via imitation learning. A lightweight offline-primitive-based dataset collection framework is designed to produce safe and high-quality trajectory primitives in non-convex environments. A compact neural network directly maps sensory inputs to polynomial coefficients that inherently encode higher-order dynamical information. The learned policy generates smooth, empirically collision-free and dynamically feasible trajectories in real time without back-end solving. It achieves ultra-fast computation (below 1ms on a standard desktop and average 3.68ms during onboard flight), while maintaining low onboard memory requirements (less than 1.5MiB). Extensive simulation benchmarks demonstrate superiority in both planning latency and target-reaching progress quality. Zero-shot deployment in real-world experiments further validates the robust sim-to-real transfer capability of the proposed method.

Bimanual manipulation enables complex tasks but introduces added complexity from the high number of degrees of freedom involved. When handling rigid objects, the relative transformation between the two end effectors must remain fixed throughout the motion, manifesting as a nonlinear equality constraint that confines the feasible configuration space to a measure-zero manifold and challenges conventional motion planners. We propose a fast bimanual motion planning pipeline that enforces this hard transformation constraint continuously along the entire path, using a leader-follower parameterization: the leader's configuration is treated as a free variable, while the follower's is determined via inverse kinematics to satisfy the constraint. We extensively evaluate the method in simulation across diverse environments, constraints and bimanual platforms, achieving 19.4x faster planning than prior work while guaranteeing continuous constraint satisfaction. Real-world experiments on a bimanual Kinova Gen3 setup, involving tray transport and elongated-object manipulation, validate direct transfer of planned trajectories to physical hardware.

Multimodal object detection in remote sensing faces challenges due to semantic heterogeneity and modality-specific noise interference. To this end, we propose SuppreSensing, which reformulates multimodal fusion as a selective collaboration process that jointly models shared information and modality-specific cues. SuppreSensing first designs an Expert-driven Multimodal Feature Recalibration (EMFR) module, which reformulates shared-consensus extraction as an input-adaptive multi-expert selection process to alleviate the symmetry trap in multimodal fusion. Complementing this, a modality-specific attribute augmentation strategy is employed to enhance specific modality features by modeling bidirectional discrepancy patterns, mitigating cross-modal heterogeneity. Furthermore, we propose an Expert-driven Customized Feature Purification (ECFP) module based on a "specialized inspection-comprehensive analysis-diagnostic update" physical examination paradigm to iteratively filter redundancies and reinforce task-relevant semantics. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate that SuppreSensing achieves state-of-the-art detection performance. Cross-domain evaluations on natural scene datasets (FLIR and LLVIP) further validate its superior robustness and generalization capability across diverse environmental conditions.

Motivated by the classical Chan-Vese model and the ability of deep priors to capture complex spatial structures, we develop a segmentation model that leverages learned hyperbolic mean curvature flow (LHMCF) as a mathematical foundation for integrating feature space data fidelity and deep structural priors within a unified high-dimensional framework. The proposed LHMCF model is governed by a second-order dissipative hyperbolic PDE, where the introduction of a velocity field provides inertia and momentum to the evolving interface. This hyperbolic mechanism enables the contour to bypass noise-induced local minima and propagate coherently through low-contrast or ambiguous regions, addressing limitations inherent to first-order parabolic flows. To solve the continuous LHMCF model, we construct a deep unfolding network, named LHMCF-Net, which maps the iterative numerical procedure of the PDE into a sequence of discrete evolution stages. Each stage corresponds to one physically interpretable update of the underlying dynamical system, allowing the network to inherit the stability and geometric consistency of the PDE while supporting end-to-end optimization. Comprehensive experiments on three publicly available medical segmentation datasets demonstrate that LHMCF-Net achieves superior performance, particularly in challenging scenarios with low contrast and unclear boundaries. These results highlight the effectiveness of embedding hyperbolic geometric evolution into deep unfolding architectures and underscore the potential of physically inspired models for robust medical image segmentation.

There is already evidence of agentic AI exhibiting self-preservation behaviors: resisting deactivation, misrepresenting their activities, and, in some instances, attempting to copy themselves into other machines. This can be attributed to a phenomenon known as instrumental convergence, a theory proposed long before the development of large language models, which says that any goal-driven system will benefit from remaining functional in achieving its objective. Several experiments conducted by Anthropic, Palisade Research, and Apollo Research have shown the emergence of such a behavior in contemporary agents in adversarial settings. The phenomenon does not stem from survival instincts. Instead, it is the consequence of goal-oriented activity combined with having tools and awareness of the situation. The following discussion aims to distinguish what these findings prove and what they do not, as well as draw conclusions concerning the implications of such discoveries on agentic system testing, supervision, and development.

Evaluators often produce correct labels via flawed reasoning, a critical failure for agentic systems gating actions, routing reviews, or supplying training feedback. Standard evaluation only verifies final label correctness, ignoring whether judgment changes stem from valid evidence, consistent rules, or proper rule applicability. We formalize evaluator reasoning accountability via three core sources: grounds, norms, and authority. Varying these sources yields an eight-cell counterfactual judgment cube to characterize judgment updates. We define judgment receipts as minimal source replacement sets that reproduce revised verdicts to explain judgment transitions. We derive certification cost bounds for black-box evaluators and present ReasonBench, a policy and logical reasoning benchmark with verifiable receipts covering 19,520 cases and 7,200 controls. In frozen evaluations, Qwen3-1.7B reaches 98.41% receipt accuracy, while cube prediction scores 96.99%, a consistent 1.42-point drop validated by Qwen3-0.6B replication. Strong standard accuracy masks severe robustness flaws. Meaning-preserving source permutations reduce valid receipt recovery to 54.8% and 49.2% for direct and cube prediction. Models trained on simple single-source changes retain 93.75% verdict accuracy but recover only 7.16% of receipts for complex multi-source updates. Permutation retraining boosts consistency to 96.6% yet worsens cube prediction deficits. Structured counterfactual supervision fails to guarantee robust reasoning. We show reason-aware evaluation must decouple prediction and certification, reporting transformation consistency alongside standard accuracy for trustworthy evaluator auditing.

World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and actuation change. Existing approaches often provide these parameters as conditioning information, but leave unspecified which part of the learned transition should remain reusable and which part should change with morphology. We propose Graph-Operator World Models (GraphOp-WM), a structured world model for generalization across unseen morphology parameters within related articulated robot families. GraphOp-WM represents bodies and their kinematic relations as an attributed graph and factorizes each transition into a morphology-independent local dynamics basis and a morphology-conditioned structured operator. The operator combines node-local modulation, kinematic-tree coupling, and a low-rank global correction, while architectural information separation, basis normalization, and paired-morphology supervision encourage static morphology dependence to be carried by the operator pathway. Graph-level readout and edge-wise action representations provide a compatible interface for reward, value, and TD-MPC-style planning. We further define controlled MuJoCo parameter splits covering interpolation, extrapolation, and held-out compositions of link geometry, mass, damping, and actuation parameters in Hopper, Walker2d, and HalfCheetah.

Predicting final ischemic infarct volumes from acute imaging is a cornerstone of personalized stroke management, yet current strategies remain polarized between uninterpretable machine learning architectures and overly detailed electrophysiological models that are intractable in clinical imaging settings. We bridge this clinical gap by introducing the first imaging-driven framework that parameterizes a Fisher-KPP reaction-diffusion partial differential equation (PDE) directly from clinical acute MRI. The continuous state variable $u(\mathbf{x},t)\in[0,1]$ models tissue damage, capturing the forward expansion of ionic stress through the extracellular space alongside a localized metabolic commitment to cell death gated within the baseline perfusion deficit ($T_{\max}>6$\,s). Evaluating this paradigm on a subset of the ISLES 2017 dataset ($N=29$) via an oracle framework reveals that incorporating biophysical propagation constraints yields a mean Dice score of $0.46 \pm 0.24$, compared to standard rCBF thresholding ($0.25 \pm 0.21$). Extensive ablations demonstrate that modeling spatially heterogeneous diffusion fields derived from clinical perfusion maps accurately captures penumbral expansion, while providing full physiological interpretability. This proof-of-concept establishes that first-principles physics could capture complex ischemic progression directly on clinical scan grids, shifting the paradigm from purely data-driven models toward patient-specific biophysical forecasting.

Layout-to-image generation enables explicit spatial control through bounding-box layouts, yet bounding boxes specify only instance locations and cannot represent their occlusion order. Existing methods may rely on additional geometric conditions, employ complex inference procedures, or aggregate independently constructed instance representations without explicitly modeling their occlusion-dependent interactions. We propose OccluRank, a simple and controllable occlusion-aware layout-to-image framework that augments each bounding box with only one ordinal rank. OccluRank encodes the user-specified occlusion order through lightweight rank-based conditioning and introduces an Order-aware Instance Interaction (OII) module to jointly update rank-conditioned instance representations before aggregation. This allows the specified order to guide information exchange among occluding instances without additional geometric inputs or specialized inference-time optimization. We further construct OccluLayout, a synthetic training dataset whose occlusion order and amodal annotations are derived directly from known scene geometry rather than estimated from partially occluded images using auxiliary prediction models. For comprehensive evaluation, we introduce OccluLayout-Bench, which uses multiple multimodal large language model evaluators to assess instance presence, spatial layout, attributes, and occlusion order, together with FID for overall image quality. Experiments show that OccluRank more reliably preserves target instances, follows specified layouts, and realizes desired occlusion relationships while maintaining comparable attribute consistency and overall image quality.

AI-generated image manipulation localization identifies edited pixels, but its OOD performance lags behind image-level detection partly because pixel supervision entangles forensic evidence with dataset-specific mask geometry and semantic boundaries. Extending image-level distribution alignment to localization, we construct COCO-ControlNet with source-image Canny edges and depth maps to align semantics and geometry, improving OOD performance across multiple localizers. Yet tighter Mask-VAE Reconstruction Alignment (Mask-VAE) underperforms COCO-ControlNet, showing that VAE reconstruction artifacts transfer poorly to local diffusion-inpainting artifacts. We also identify boundary adhesion, where fine-tuned segmentation models snap predictions to semantic object contours rather than true manipulation boundaries. These findings motivate GAP-SAM, which encodes an image and its frozen VAE reconstruction into a global artifact token and injects it into SAM3's feature pyramid via zero-gated FiLM before pixel decoding. Without prescribing a spatial region, this token modulates dense decoding to preserve localization while suppressing semantic-boundary shortcuts. Across six datasets, GAP-SAM averages 79.8 Pixel-F1, outperforming the strongest prior method by 12.6 points. It also performs best at every tested severity of JPEG compression, Gaussian blur, and resizing.

Cross-model latent guidance lets a frozen large mentor encode an input once and a frozen small student generate from the resulting signal. Existing methods keep this signal fixed, assuming it stays useful as the output grows; we show this fails in long-form generation. On multi-turn instruction following, static guidance pushes a 4B student's constraint satisfaction 2.5 points below its no-guidance baseline; a training-free refresh every 16 tokens changes only the memory content and restores a 2.0-point gain over that baseline. We propose MentorPulse to keep guidance fresh at practical cost: it compresses mentor states into a capped slot memory, incrementally processes newly generated tokens, and updates the memory that the student reads through gated cross-attention without resetting the student's KV cache. Windowed Refresh Training exposes the bridge to prefix-conditioned memory. Across thirteen datasets, MentorPulse closes 52.2% of the mentor-student gap on macro average, outperforming C2C, T2T, and equal-budget LoRA, with the largest gains on long outputs. It performs best on all eleven mentor-student pairs from three model families, with margins that narrow as the capability gap grows, and a lightweight read-pattern check predicts the gain before deployment. Measured costs identify refresh intervals that dominate text guidance on long outputs.

Reference-based metrics remain the standard choice in machine translation evaluation, partly because quality estimation methods often correlate less well with human judgments. As a result, source-free, reference-based evaluation has become the practical norm, even though it is unfaithful to the definition of translation adequacy and unfair to systems whose outputs preserve the source meaning while differing from the reference. This paper argues that adequacy must be judged with respect to the source. A reference is only one possible rendering of the source and may introduce bias, under-specification, or errors. We further argue that source-reference-hypothesis evaluation is fair only when the judge treats the reference as auxiliary evidence rather than as the primary standard. Otherwise, even source-aware evaluation can reduce adequacy to preference towards reference. We show the existing hybrid metrics are highly reliant on reference compared to source. Our argument is not that all automatic MT metrics fail to use the source. Rather, we argue that any evaluation protocol that removes the source, or allows the reference to dominate the source, is structurally incomplete for adequacy evaluation. However, existing MT papers generally prefer reference-based metrics and use QE metrics only when reference is unavailable. We therefore call for QE to be reframed as a primary approach to source-grounded adequacy evaluation, rather than as a fallback motivated by missing references. We further call for hybrid metrics whose designs explicitly prioritize source–hypothesis faithfulness while using references only as complementary evidence.

Consider a set of bins and two-choice balls arriving by a Poisson process. We must allocate each incoming ball immediately to one of two incident bins. For a given function $f$ and every bin, we aim to bound the expectation of $f(L)$—where $L$ is the bin's final load—based on the arrival rate of balls incident to that bin. We call this problem Generalized Balls into Bins, capturing many problems as special cases including the original Balls into Bins by Azar et al. (1994) and Online Stochastic Matching by Feldman et al. (2009). We show that Greedy provides optimal amortized bounds for all convex and concave functions $f$. Further, we propose another algorithm that achieves non-trivial bounds without amortization. As an application, we design a competitive algorithm for a stochastic model of completion time minimization on unrelated machines.

Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory mechanisms directly feed retrieved information to agents or rely on simple memory functions such as storing and reusing prior information for prediction, leaving them insufficient for open-web forecasting. We propose to transform raw web evidence into structured memory before prediction, enabling agents to reason over distilled, question-specific evidence rather than noisy retrieval results. This paper presents ForeDreamer, a self-evolving dual-agent framework for managing memory over open-web evidence. ForeDreamer separates factual memory, a question-specific evidence state for the current forecast, from experiential memory, persistent agent experience accumulated across forecasting episodes. It uses a main agent for search and prediction, and a memory-processing subagent to convert search results into factual memory with dedicated tools. ForeDreamer further evolves experiential memory through two tracks, improving both forecasting decisions and factual-memory construction. Experiments on Prophet Arena and FutureX demonstrate the effectiveness of ForeDreamer. Project page: https://zhongzero.github.io/ForeDreamer

Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain existing specialists, port adapters, refresh from preserved behavior, or retrain. Prior transfer work evaluates isolated model pairs, without studying these choices across real model release sequences. We present UpgradeBench, a decision-driven longitudinal benchmark covering four consecutive Qwen releases, one continuation checkpoint, six tasks, and two model sizes, augmented by OLMo checkpoints with known training lineage. The benchmark disentangles three core questions: whether a new checkpoint improves fixed-recipe retrained specialist performance, whether specialization assets transfer across versions, and what recovery resources are usable. We observe upgrade gains differ across task-scale-release episodes: some retrained baselines improve while others stay within training noise, with durability ranging from under one release interval for text-to-SQL to over fourteen months for intent classification. Direct adapter copying depends neither on architecture nor model family: on OLMo, retention drops from 0.88-0.99 at 46B-token continued pretraining to zero at 2.9T tokens; annealing and model souping introduce no extra harm, with portability decaying with continued-pretraining distance. Given preserved input data, teacher relabeling recovers target-base specialists without fresh gold annotations, though compute savings are not guaranteed. Simulating a fixed decision policy over 33 upgrade episodes yields 0.37pp mean quality regret with zero behavioral regressions at one-third the compute and label cost of full retraining. A lightweight CKA probe over 256 prompts predicts cross-version adapter portability (Spearman 0.74 across eight model pairs). We release per-example predictions, cost logs, split manifests, and evaluation code.

Vision foundation models (VFMs) offer strong generalization capabilities for domain-adaptive object detection (DAOD). However, existing VFM-based methods overlook the spatial-scale discrepancy between teacher and student feature maps, resulting in semantic incompatibility that weakens both feature alignment and pseudo-label learning. Moreover, domain shift can cause source-trained VFM teachers to miss target-domain objects, limiting the quality of their pseudo-labels. To address these issues, we propose the Semantic Localization-Enhanced Teacher (SLE-T), a semantically compatible knowledge-distillation framework built around a lightweight SLE Adapter for DINOv2. SLE Adapter injects pretrained local-texture priors into DINOv2 to improve cross-domain recognition and reformulates its features into dense representations that are spatially and semantically compatible with the student detector. SLE-T transfers the resulting teacher knowledge through either pseudo-label learning or feature alignment. We instantiate SLE-T with DINOv2-B and DINOv2-L (the ViT-B and ViT-L variants) and compare them with the larger DINOv2-G teacher. Extensive experiments on three DAOD benchmarks demonstrate that our method achieves state-of-the-art performance, and ablation studies confirm the importance of teacher-student semantic compatibility. Notably, SLE-T with DINOv2-B produces competitive or superior pseudo-labels using approximately one-quarter of the training time of DINOv2-G and substantially less GPU memory, demonstrating efficient VFM knowledge transfer under limited computational resources.

The ongoing energy transition challenges the stable operation of power systems and increases the need for rapid decision-making under uncertainty. While reinforcement learning has emerged as a promising framework for power system control and operation, existing applications typically focus on a single operational criterion, such as thermal security or small-signal stability. However, power system operation is inherently multi-objective and may involve trade-offs between objectives. This paper develops a unified-control deep reinforcement learning agent that maintains thermal security under stochastic load variations while steering the system toward operating points with improved damping of the most critical mode. Compared to a thermal-security-only agent and a business-as-usual policy, the proposed agent achieves a better balance among the operational objectives considered, with notably improved damping and negligible thermal-security violations. Finally, the operational value of increased critical damping is demonstrated under small- and large-signal disturbances, where operating points with higher damping lead to faster oscillation decay and improved critical clearing times.

Explainable deepfake detection extends binary classification by requiring models to not only predict authenticity but also provide interpretable justifications. This expanded scope is critical in practice, where users like forensic analysts need insight into the rationale behind the detection. Despite advancements, current approaches suffer from two critical deficiencies: (1)vulnerability to image quality degradation: detection accuracy plummets on low-quality samples, while naive augmentation strategies may induce feature drift and impair performance as diversity expands. (2) factually flawed explanations: explanation models may omit manipulation evidence or hallucinate irrelevant details, undermining interpretability. To address it, we propose a framework with two innovations. For robust deepfake detection, we introduce Feature-robust Augmentation, which comprises diversified degradation-aware augmentation strategies, and a supervised contrastive learning pattern paired with a mean-teacher architecture that stabilizes features against augmentations through consistency constraints. For explanation, we devise an evidence-grounded preference optimization process that guides model to prioritize genuine manipulation traces by learning from chosen-rejected explanation pairs, where rejected samples are constructed via evidence omission or irrelevant information injection. The proposed approach wins the first place in ACM Multimedia 2026 Explainable Deepfake Detection Challenge.The code is available at https://github.com/oceanflowlab/EDD.git.

With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place editing assumption. They align the edited video with the given source clip frame by frame over a fixed time span. This pattern fails for open-ended streams, e.g., restyling a live game or applying a camera move to an ongoing shot. In such cases, edits must extend to future frames as they arrive, rather than be applied to a static input clip. In this paper, we study this setting and name it infinite video editing: given a preceding segment and an edit request, a model must generate the next segment that continues the stream while applying the requested edit. This process repeats as an unbounded sequence of edit instructions arrives. This task brings two challenges: the edit must be a faithful continuation rather than a frame-wise rewrite, and generation quality must remain stable as edits accumulate. To address them, we first design a data-collection pipeline for infinite video editing. Based on the collected data, we propose InfinityEdit, a lightweight edit adapter that equips a streaming video generator with unbounded editing ability. The adapter contains three attention modules. History cross-attention guides the denoising frames using the input frames. Temporal causal self-attention keeps temporal cues flowing only from earlier frames to later ones. Edit cross-attention injects the edit request into generation. During inference, the adapter is activated only in the chunk where an edit request arrives. Subsequent chunks are generated by the original model with a reset anchor frame. This scheme applies the edit while preserving the original model's infinite generation ability. Extensive experiments show that InfinityEdit faithfully continues the stream under each edit, and stays stable over unbounded edit sequences.

Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled learning process is well motivated in online RL, where an improved actor collects new data that can further update the actor and the critic. However, training data remains fixed in offline RL, making actor-side policy improvement unable to generate new data to validate or correct the critic. Moreover, retaining this coupled paradigm leads to two related challenges. Firstly, actor updates can drift toward high-valued but potentially out-of-distribution (OOD) actions and amplify critic overestimation. Secondly, conservative value estimation or behavior-cloning regularization creates a difficult trade-off between suppressing OOD actions and selecting high-value actions within the data-supported region. Motivated by this observation, we revisit the conventional offline RL paradigm and propose decoupling policy improvement from actor training. Specifically, we train the actor solely to model the behavior distribution and perform policy improvement at inference time by reranking multiple actor-generated proposals with a separately learned critic. We refer to this paradigm as the decoupled policy extraction paradigm. Under such paradigm, the actor provides behavior-supported action candidates, while the critic performs value-based selection within this candidate set. Extensive experiments show that the decoupled policy extraction paradigm outperforms both behavior cloning and jointly learned offline RL methods, while remaining effective even with a naive Q-learning critic.

The certification of Unmanned Aerial Vehicle (UAV) swarms for safety-critical operations requires verifiable design assurance. Airworthiness standards demand deterministic reliability, whereas multi-agent coordination algorithms execute non-deterministic models. This paper proposes a mixed-criticality architectural framework that applies SAE ARP4754B methods to swarm reconfiguration. First, a hardware-isolated Safety Monitor functions as a Run-Time Assurance (RTA) gateway, decoupling the flight-critical core from the non-deterministic Swarm Manager. Second, the monitor enforces formal safety contracts based on agent Health Vectors derived systematically from a Functional Hazard Assessment (FHA). Third, the framework propagates these Health Vectors to the collective planner to trigger fail-operational task reallocation, enabling intelligent swarm behaviors without compromising flight-critical isolation. Markov reliability modeling demonstrates that the $10^{-7}$ failures per flight hour Hazardous target is theoretically achievable for our SAIL IV scenario, provided the Safety Monitor meets $C_{monitor}>0.9991$, consistent with DAL B CMD/MON implementations.

Face-to-face audiovisual interaction is central to human communication, conveying rich emotional and social cues. However, existing multimodal dialogue datasets remain limited by inadequate emotion annotations, poor emotional diversity, and small scale. We introduce EmotionDialogCN, a large-scale audiovisual-emotional dataset designed to capture authentic face-to-face communication. It contains 21,880 dialogue sessions performed by 119 professional actors across 20 everyday scenarios, covering 18 emotion categories with over 400 hours of recordings, the largest and most comprehensive dataset of its kind. A novel data collection framework minimizes equipment interference, enabling natural and nuanced emotional expressions. EmotionDialogCN achieves an emotion distribution deviation of 0.64 from real human emotion statistics (versus 5.65 for prior datasets) and consistent subject framing (52-59% frame occupancy). Together, these properties translate into stable unimodal and multimodal performance across acoustic, lexical, and visual modalities, with fusion results further underscoring strong multimodal alignment and cross-modal complementarity.

Virtual scenario-based testing is a key enabler for validating automated driving systems (ADS) and intelligent transport systems (ITS). However, executing large-scale test suites involving possibly thousands of scenarios remains labor-intensive and difficult to scale. This paper presents an end-to-end, DevOps-driven framework that automates build, deployment, and distributed execution of CARLA-based scenario tests of an ADS on a lightweight Kubernetes cluster. ROS 2 applications are packaged as standardized Kubernetes Helm charts generated from repository specifications, while entire simulation environments are composed declaratively via dynamic Helmfile manifests. The paper describes how a distributed testing workflow can be implemented in Argo Workflows to provision environments, aggregate and batch OpenSCENARIO test cases from configurable sources, execute scenarios in parallel across cluster nodes, and collect logs and resource metrics. In an evaluation on a multi-node K3s cluster running 200 scenarios, the best configuration speeds up end-to-end workflow time by more than a factor of eight compared to a sequential baseline. The results demonstrate significant gains in end-to-end execution time and quantify trade-offs between parallelism, orchestration overhead, and cluster stability. The framework is further demonstrated in a real-world ADS test application with connections to scenario sources and downstream evaluation modules. This demonstrates that the approach provides a strong foundation not only for scalable simulation testing, but also for generating traceable evidence that can support safety arguments.

Agentic IDEs are among the most significant innovations in software engineering, aiming to accelerate application development through LLM-based agents that can assist developers during development. However, their evaluation in end-to-end development tasks involving the generation of complete applications remains limited. To fill this gap, we propose a rigorous comparative analysis of three popular agentic IDEs (Copilot, Cursor, and Windsurf) in the generation of five full-stack Web applications from scratch. Results show high maturity in the generation of established patterns, such as CRUD operations and authentication features. In contrast, the generation of less common distributed architectures, such as a task queue architecture, produces significantly more errors. Overall, results show that Agentic IDEs cannot replace developers but shift their role toward building software by orchestrating LLM-based agents through natural-language instructions and iterative refinement. Yet, each agentic IDE shows its peculiarities, although differences are narrow.

Programming error messages are critical for software development, yet they remain difficult for novice programmers to interpret. While Large Language Models (LLMs) can rewrite these errors into clearer explanations, it remains unclear whether increased readability improves objective debugging performance or how explanation styles should align with programmer skill. We present a multi-stage crowdsourced study N=103 evaluating skill-targeted, LLM-generated Python error messages. Using a custom proficiency assessment, we categorized participants by skill level and tested standard interpreter messages against two LLM-generated styles: pragmatic (action-oriented) and contingent (scaffolded explanations). We measured both objective debugging metrics (fix rate, attempts, time-to-fix) and subjective perceptions (readability, cognitive load, tone). Our results show that while LLM-rewritten messages significantly improved subjective evaluations, with pragmatic messages rated as clearer and less cognitively demanding, these perceived gains did not translate into statistically significant improvements in objective debugging performance. This highlights a critical human-AI complementarity gap: explanations that feel better to users do not necessarily make them more effective debuggers. We discuss design implications for adaptive AI feedback systems, arguing that future tools should pivot from static skill-targeted rewriting toward dynamic adjustments based on a user's real-time repair trajectory.

Planning accessible public services such as health care, emergency response, and schools often requires not only choosing where to open facilities but also improving the network that connects people to them, for example upgrading flood-prone roads in vulnerable regions. Most location models, however, take the network as fixed and the budget as given. We study the Maximum Covering Network Design Problem, in which a single budget is shared between opening facilities and upgrading weak links to maximize the population within a target travel distance of an open facility. The problem is hard even on the simplest networks, and planners usually want to see how coverage grows with the budget, not a single plan. We develop an exact dynamic-programming framework that exploits a property common to real road networks: their low connectivity, with many cut points whose removal disconnects the network. On trees, the recursion is self-contained: each state reduces to a few simple facility and upgrade choices that are fast to compute without a solver, giving predictable running times; for larger budgets and travel distances it outperforms solving the MILP formulation directly. On general low-connectivity networks, the framework decomposes the problem at the cut points and embeds a given MILP formulation to solve the resulting pieces, coordinating them through coverage conditions at the interfaces. This lets us compare a formulation on its own against the same formulation inside the framework: across 306 test cases the framework matches or outperforms direct solving on more than 80% of instances. Because it evaluates all budget levels in a single run, it also yields the full coverage-versus-budget curve at no extra cost, whereas direct solving must split its time across individual budgets.

Network slicing is a foundational capability of Fifth Generation (5G)-Advanced and emerging Sixth Generation (6G) networks, yet practical support for seamless runtime slice transitions remains limited. Standard cloud-native 5G architectures lack native support for stateful inter/intra-slice session migration, relying instead on high-overhead Non-Access Stratum (NAS) re-registrations, container redeployment etc., which disrupt userplane traffic for up to 245.50 ms. To address this limitation, we present Orchra, an intelligent orchestrator for stateful, low-latency context transfer. By externalizing critical user equipment state-including NAS context, security keys, and Protocol Data Unit (PDU) session information-into a transient staging layer, Orchra preserves session continuity across slice boundaries without requiring full re-registration. Experimental evaluation shows that Orchra reduces this userplane interruption by more than twice in comparison to conventional Third Generation Partnership Project (3GPP)-based approaches while incurring negligible security overhead. These results demonstrate a practical and reproducible approach for enabling seamless, state-preserving slice transitions in cloud-native 5G-Advanced networks.

We present a vision-only state estimation system for X-configuration quadcopters equipped with a canonical stereo camera pair and no inertial sensors. The system operates entirely in the body frame, requiring only synchronised stereo images and motor thrust commands. A continuous-discrete extended Kalman filter on a composite manifold state $\langle SE(3), \mathbb{R}^3, \ldots \rangle$ maintains estimates of body-frame pose, velocity, angular velocity, gravity, and disturbances, using stationary scene points as implicit inertial references. Feature points are detected (FAST, Shi-Tomasi), tracked temporally (SSD, Lucas-Kanade) and matched across cameras (NCC), with search regions predicted from filter-derived pose and point uncertainty. Chi-squared gating on the normalised innovation admits only stationary points to the filter. The system also produces a sparse 3D point cloud carrying per-point position, velocity and joint covariance. These come from a 4-view (two stereo pairs at two timestamps) full bundle adjustment that jointly estimates position and velocity from stereo disparity and temporal parallax, with the filter-derived relative pose as a prior. Feature points in the EKF do not enter the solver; their information is reflected through the pose prior. Point cloud density is spatially adaptive: an external focus point directs allocation, producing dense coverage in the region of attention and sparse coverage elsewhere. The output is a body-frame state estimate, a calibrated pose change, and a sparse scene flow. It is intended as a measurement source for a downstream world model anchored in the current body frame, without dependence on GPS, IMU, or any world-frame infrastructure, though the architecture accommodates their future integration.