Papers

Adapting a pretrained Vision-Language-Action (VLA) model to a new robot, environment, or task requires demonstrations that are collected locally and often discarded. Federated learning is a promising approach to exploiting such distributed demonstrations by learning a shared policy. However, whether it can adapt large pretrained VLAs remains an open question, and a lack of reproducible benchmarks for pretrained VLAs and reusable training frameworks makes existing results difficult to compare. In this paper, we conduct a systematic study of federated fine-tuning of three modern pretrained VLA policies on the 40 simulated tasks of the LIBERO manipulation benchmark, and on six real-world tasks in two real-robot experiments, with demonstrations collected across two and three sites, respectively. Our study analyzes the key choices in this setting, spanning multiple federated parameter scopes, three aggregation algorithms, and evaluation under distribution shift. Based on the study, we derive a series of lessons, including the dominance of the federated scope over the choice of aggregation algorithm and the difficulty of matching centralized fine-tuning on physical robots, where cross-site heterogeneity is stronger than simulation captures. We also highlight opportunities for federated VLA learning, such as the ability to match centralized fine-tuning on heterogeneous data, to remain at least as robust as centralized fine-tuning under distribution shift, and to personalize, with each client federating part of the policy and keeping the rest local, which helps where the policy's pretraining is weak but leaves no usable global model. We open-source \decentvla{}, the model- and runtime-agnostic testbed behind the study, to facilitate future research and fair comparisons in federated VLA learning.

Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising route to automating UX testing by simulating realistic user behaviour. However, existing simulation approaches typically lack multimodality and require time-consuming manual review to extract actionable insights. We formalise UX improvement recommendation from simulation data as a structured natural language generation and ranking problem, and establish an evaluation protocol using expert annotation and LLM-as-a-Judge. We present AMUSER, a multimodal framework which simulates user behaviour and automatically generates prioritised UX improvement recommendations from resulting data. We evaluate AMUSER on commercial websites and show that its recommendations substantially outperform those from text-only simulation (NDCG@3 = 0.758 versus 0.359) at an 89% lower simulation cost. Our results suggest an asymmetric role of multimodality: visual access during simulation improves recommendations through richer traces, while providing visual inputs during recommendation generation can modestly degrade quality. We also discuss practical deployment lessons from applying AMUSER to commercial websites.

Modern streaming pipelines run hundreds of candidate encodes per asset to support per-title encoding, shot-based optimization, and context-adaptive ABR ladder construction. These techniques have moved perceptual quality metrics into the critical path: SSIM and VMAF now guide encoding decisions rather than passively monitor them. We measure that SSIM evaluation accounts for 7-35% of x264 encode time at production speed presets, with the cost ratio rising as encoders run faster. We propose ApproxSSIMate, a low-complexity method for estimating SSIM from PSNR combined with reference-sequence statistics computed once per sequence and reused across every candidate encode. This decouples quality estimation from the encode-decode-compare loop, enabling perceptual quality feedback in live encoding and amortizing quality measurement across candidate encodes in per-title workflows. We validate the approach across H.264/AVC, H.265/HEVC, and AV1 on the Objective-1-fast dataset and release the implementation as free and open-source software.

We study a one-player token game on an $N\times N$ board where tokens slide along diagonals or duplicate onto neighbouring ones to form a combinatorial rectangle $R\times S$. A conserved integer weight $W'$ and a strict monovariant guarantee $O(N^2)$-length solutions, placing the game in $\mathsf{NP}$. We prove that reaching a final position factors this $2N$-bit $W'$ into two $N$-bit factors $V,M < 2^N$ that encode the rectangle's rows and columns. Consequently, solving the game for a balanced-semiprime target is equivalent to integer factoring. However, if the target rectangle is known, the solution reduces to two polynomial-time steps: a forced downward chip-flow and a $0/1$-polynomial factorisation leveraging Cohn's theorem. The game's entire difficulty is thus isolated to the initial number-theoretic split. Supplying the popcounts of the factors as a promise preserves this asymptotic hardness but bounds the target search space. We exploit this constrained space using a learned policy/value network and an AlphaZero-style Monte-Carlo tree search, empirically probing the limits of neural look-ahead on a factoring-equivalent environment.

Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compact features to overcome a local observation trap that no single agent can escape: occlusions, finite sensor range, and environmental degradation. The field has matured across architectural, communication, embodied, resilience, and trust dimensions, yet existing surveys examine these dimensions in isolation and rarely expose their dependencies. This review offers a unified synthesis through two complementary lenses. The first is a five-dimensional taxonomy spanning collaboration stage, communication paradigm, fusion architecture, learning strategy, and application domain. The second is three cognitive synergy conditions, Semantic Disambiguation, Pragmatic Information Exchange, and Proactive Informational Foraging, that turn cognitive synergy into operational criteria. Across these lenses we survey collaboration architectures and topologies, neural-communication co-design that treats the channel as a differentiable pipeline component, embodied action-perception loops via multi-agent reinforcement learning, and resilience mechanisms for synchronization, uncertainty quantification, and label-efficient learning. We then map these advances onto four operational domains, V2X, unmanned aerial, industrial logistics, and smart cities, and onto the safety-privacy-utility triad. To counter benchmark saturation and evaluation fragmentation, we propose GCI-Bench, a five-pillar scoring protocol with a maturity model that makes the trade-offs of collaborative methods comparable across studies. A critical reflection on reproducibility, the sim-to-real gulf, and conditions under which collaboration degrades performance identifies open challenges and charts directions toward general collaborative intelligence under real-world uncertainty.

Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in embodiment, environment and task, human intelligence itself may transfer across this gap. This naturally raises a fundamental question: can the intelligence of vision-language models (VLMs) similarly generalize from the digital world to the physical world for robotic control? We investigate this question through RoboDawn, a human-intuitive interface that exposes robotic control to an agentic VLM through a compact set of discrete translation, rotation, and gripper commands. Using this interface, the VLM controls a robot in a closed loop: it observes the current visual state, reasons about the next action, executes it, and adapts subsequent decisions to the resulting state. Furthermore, we introduce an in-context learning (ICL) scheme that uses a few demonstrations to ground the VLM in both interface usage and task-solving strategies. Experiments on RoboTwin 2.0 C2R and RoboDojo demonstrate that RoboDawn achieves strong performance without task-specific robot training. In the zero-shot setting, RoboDawn outperforms several strong policies trained on benchmarkspecific robot data, while a single in-context demonstration further yields substantial performance gains and establishes state-of-the-art (SOTA) results. On RoboTwin 2.0 C2R, the success rate increases from 53.2% zero-shot to 73.6% one-shot, exceeding the solid baseline {\pi}0.5 (46.0%). Similar gains are observed on RoboDojo, where success rate improves from 35.67% zero-shot to 47.17% one-shot. The same framework also transfers to real-world robots, performing block-in-basket and block stacking on Franka.

This study develops a prescribed-time performance-shaping control method for curvature tracking of a single-segment flexible arm actuated by three antagonistic tendon pairs. A Cartesian curvature representation is introduced to avoid the undefined bending direction at the straight configuration and to establish an explicit six-tendon kinematic mapping. A cubic performance boundary contracts smoothly from an initially admissible error bound to a nonzero terminal accuracy bound within a prescribed time. Based on this boundary, a dual transformation combining static symmetric error scaling and time-varying behavior shaping maps the tracking error into a fixed unit box. The resulting controller guarantees boundary invariance, prescribed-time entry into the terminal accuracy region, and subsequent asymptotic convergence. Numerical evaluations with Python and OpenCR–MuJoCo, together with a supervised reduced-order experiment on a two-section, four-channel platform, provide complementary validation. Across six experimental trials, no violation of the prescribed boundary is observed, and the proposed controller reduces the mean terminal curvature RMSE by 32.5% relative to a matched baseline, with comparable terminal-band entry times. These results support the feasibility of the proposed approach in the reduced-order experimental setting.

Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a delegated action solely from producing-domain controls and records. This paper develops Trustworthiness as a Service (TaaS) through a synthesis of trustworthy-AI governance, agent security, distributed trust management, identity, provenance, assurance, and control-plane research. The analytical unit is a cross-domain reliance proposition that names the issuer, subject and action, relying party, administrative boundary, evidence dependencies, adverse condition, and required verification or adjudication semantics. The three-condition structural-externalization diagnostic identifies propositions that depend on multiple domains, require producer-independent reliance, and must remain reviewable after revocation, failure, conflicting records, or dispute. For such propositions, the paper specifies a trust-evidence envelope: an immutable workflow manifest linked to append-only, issuer-attributed attestations for task-scoped authority, policy and execution decisions, provenance, validity, disclosure, status, challenge, and recovery. A topology-neutral logical reference model assigns these functions to explicit roles and trust domains. Three analytical scenarios and the TaaS-Eval protocol proposal define manifests, independent consumers, hard gates, adversarial evidence tests, metrics, and reproducible artifact reporting. By composing established identity, authorization, provenance, assurance, and governance mechanisms around a bounded delegated action, TaaS provides a reusable profile for cross-domain reliance. It makes evidence dependencies, independent verification, challenge, and recovery explicit, supporting interoperable governance and future evaluation without treating producer assertions as ground truth.

The medications prescribed to a patient often change during a hospital admission as clinicians start, stop, or continue therapies. We study whether models can predict which medication classes are added or removed between 24 hours after admission and discharge. Metrics that compare the complete discharge regimen can reward models for copying medications that remain unchanged, even when they identify no actual changes. We therefore introduce a leakage-controlled benchmark that predicts net ATC3 additions and removals using only prior completed admissions and information available within the first 24 hours of the current admission. Addition candidates are classes not active at 24 hours, whereas removal candidates are classes active at that time. We also introduce R-GEAN, an asymmetric candidate-scoring network with independent addition and removal predictors. Across 240,480 admissions from 82,286 patients, R-GEAN achieves the highest predefined summary of addition, removal, changed-regimen, and action-pattern performance, termed the edit composite (0.464), compared with 0.435 for the strongest primary comparator. Reimplemented RETAIN, GAMENet, and MICRON baselines obtain 0.428, 0.420, and 0.288, respectively. R-GEAN's advantage is concentrated in correctly identifying medication classes no longer active at discharge, while rare additions and admissions with multiple medication changes remain difficult. Rankings based on micro-F1 over the reconstructed discharge regimen and the edit composite correlate weakly across the evaluated models (Spearman r = 0.20). The continuation baseline achieves the highest complete-regimen score despite predicting no additions or removals. These results show that complete-regimen and edit-level evaluation measure different aspects of medication prediction. The benchmark evaluates observed prescribing changes, not treatment appropriateness

In this paper, we study graph editing problems on geometric intersection graphs. For a tuple $\mathcal{S}=(S_1,\dots,S_n)$ of geometric objects in some Euclidean space, let $G_\mathcal{S}$ be their intersection graph. We study the problem of finding a tuple $D=(d_1,\dots,d_n)$ of movement vectors such that the resulting intersection graph $G_{\mathcal{S}+D}$ (after moving, for every $i \in \{1,\dots,n\}$, object $S_i$ by $d_i$) has a predefined property and the total movement distance $|D|$ is minimum. In the weighted version, we are also given a weight vector $w=(w_1,\dots,w_n)$ with positive entries, and the objective is to minimise the total weighted movement distance $|w \cdot D|$. We first consider the property locally dense, which we define as containment of a $k$-clique. Given $n$ weighted intervals, we solve the problem with respect to this property in $O(k^{1/3} n \log^{1+\varepsilon} n)$ time for any $\varepsilon>0$. We then consider $k$-connectivity for $1\le k \le n-1$. Given $n$ unweighted unit intervals, we solve the problem in $O(n^2 \log n)$ time and, for $k=1$, in $O(n\log n)$ time. For $k=1$, we prove strong NP-hardness on intervals of arbitrary length and on weighted unit disks (with only two distinct weights), and weak NP-hardness on weighted intervals (even when lengths equal weights).

Parkinson's disease alters gait and bilateral coordination, but machine-learning performance also depends on how continuous gait signals are represented. This study investigates whether preserving anterior-posterior center-of-pressure (AP-COP) information at fixed locations across normalized stance provides a compact and informative representation of plantar-force gait signals. Bilateral vertical ground reaction force recordings from 165 participants in the Gait in Parkinson's Disease Database were evaluated using repeated fully nested participant-level cross-validation. We propose AP-COP10, comprising AP-COP position and bilateral asymmetry across five stance windows. AP-COP10 achieved an AUC of 0.894 and outperformed three harmonized literature-derived COP representations under the same evaluation pipeline. The complementary 25 non-AP-COP descriptors alone achieved an AUC of 0.856, while the complete 35-feature representation achieved 0.908. Removing AP-COP10 from the complete representation produced a statistically supported loss in discrimination, whereas adding the complementary descriptors to AP-COP10 yielded only a small, unsupported improvement. Feature competition indicated that the most informative stance-indexed descriptors were concentrated in early and early-mid stance, while source-study holdout and sensor-perturbation analyses supported the robustness of the representation. These findings indicate that stance-indexed AP-COP retains discriminative information that is not readily recovered by broader engineered gait descriptors, supporting compact and interpretable representations for machine-learning analysis of pathological gait.

We extend the high-order Zipped Finite Element Method to three-dimensional polyhedral elements. The construction relies on a local sub-tetrahedralization obtained by triangulating the polygonal faces and connecting the resulting vertices to a suitable interior point. High-order shape functions are constructed as linear combinations of standard finite element basis functions, with coefficients chosen to ensure exact polynomial reproduction on the faces and in the element interior while preserving global C0-conformity. We further introduce a QR-based strategy as a systematic alternative to the heuristic procedure that was adopted for the two-dimensional case. The QR-strategy is more systematic and robust than the heuristic strategy, while being independent of the spatial dimension and avoiding geometric alignment tests and problem-dependent tolerances. The resulting method is formulated for a diffusion-reaction problem and numerically assessed through three-dimensional convergence tests, confirming the expected optimal polynomial order of accuracy.

Mobile gas-sensing inspection requires a mobile platform to reliably reach ordered sampling poses. We present MIRA-PRM, a mission-informed probabilistic roadmap that combines geometry-, mission-flow-, and inspection-conditioned sampling with locally adaptive connectivity and evidence-gated refinement. Eight development campaigns comprising 142,448 planner runs evaluated mission scaling, repeated-query adaptation, finite node budgets, target distributions, local map repair, ablation, cross-family comparison, and parameter sensitivity. MIRA-PRM maintained 100% seed-level success as ordered targets increased from two to eight, and achieved 97.67% seed-level success under a 40-node ceiling, compared with 67.17% for PRM and 86.50% for PRM*. Local repair reduced event time by 79.9-81.9% and node additions by 90.8-94.3% relative to rebuilding. On a separate frozen holdout of 12 maps, 48 ordered missions, and three seeds per map-mission unit, MIRA-PRM produced 96/144 validated successes, versus 82/144 for PRM, 89/144 for PRM*, and 70/144 for LE-HG-PRM. On paired common-success runs, MIRA-PRM reduced wall time by 16.89% relative to PRM* and 81.01% relative to LE-HG-PRM, but was 52.23% slower than PRM; paths were 0.54-1.86% longer. All validated paths passed independent full-segment checks and clearance non-inferiority. The results support a reliability-oriented trade-off in structured simulations and motivate external-map and physical mobile-sensing validation.

Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely within a single trajectory. A planning step may require frontier-class reasoning while a subsequent formatting step needs only a 7B model. We formalize step-level model routing as a sequential assignment problem over agent trajectories and propose AgentRouter, a lightweight classifier (12M parameters, <5ms overhead per step on an A100 GPU) that maps each trajectory step to one of four model tiers using five features extractable at routing time. Trained on 50,000 annotated agent trajectory steps spanning planning, coding, research, and data analysis tasks, AgentRouter achieves 72% cost reduction relative to frontier-only baselines, retaining 97.3% of frontier-only quality (less than 3% degradation in end-to-end task completion); per-step routing accuracy reaches 91% on minimal-complexity steps and 85% on efficient-tier steps, with 76-82% on the harder mid-range and frontier tiers. On the same benchmarks, RouteLLM and FrugalGPT (applied per-step) achieve only 31% and 44% cost reduction respectively, because their single-turn training signal misses trajectory-level quality dependencies.

While compressed-sensing regularizers enable interpretable reconstruction of 4D Flow CMR through transparent variational objectives, their hand-crafted nature is too restrictive under high acceleration. State-of-the-art learning-based approaches mitigate this, but typically encode regularization implicitly through unrolled network modules, which limits their interpretability. To address this limitation, we propose CLEAR, designed to combine the interpretability of compressed sensing with the flexibility of learned models. To the best of our knowledge, it is the first learned regularizer for a 4D reconstruction task. In the ultra-accelerated \(10\times\)–\(50\times\) regime of the CMRx4DFlow2026 challenge, CLEAR outperforms compressed sensing locally low-rank (LLR) and the popular variational network FlowVN, while using less than 10k parameters and preserving an interpretable regularization structure.

Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent systems amplify this threat through three mechanisms absent from single-model settings: inter-agent message passing creates injection channels invisible to perimeter defenses, shared tool access enables privilege escalation across agent boundaries, and trust propagation allows a compromised agent to influence upstream orchestrators. We construct a threat model enumerating 14 attack vectors across four categories: direct injection via user input (3 vectors), indirect injection via tool outputs (4 vectors), inter-agent injection via message passing (4 vectors), and cascading injection through orchestrator manipulation (3 vectors). Testing all 14 vectors against a 6-agent production-representative system, we find that 67% of agents are vulnerable to at least one scope violation even with system-prompt-level guardrails, and indirect injection via tool outputs succeeds in 43% of attempts. Four architectural defenses reduce overall injection success from 31.2% to 4.2%: message signing with provenance tracking (inter-agent injection down 91%), input/output sanitization at agent boundaries (indirect injection down 78%), privilege-scoped tool access per agent role (privilege escalation eliminated entirely), and anomaly detection on inter-agent communication patterns (84% of cascading attempts caught).

Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable scalar scores because they directly map complex, subjective video quality into a single score without explicit evaluation criteria. This leads to scalar drift, where the scoring scale collapses or shifts across different prompts, making the reward unreliable for RL. Drawing inspiration from professional human annotation engineering, we address this problem with RewardVerse, a rubric-based video reward framework that introduces a dynamic rubric as an intermediate representation between the evaluation query and the scorer. Instead of unconstrained direct scoring, RewardVerse first generates explicit evaluation criteria and then performs rubric-guided scoring, providing a stable semantic anchor that mitigates scalar drift. To efficiently optimize this collaborative pipeline, we propose Rubric-Guided Policy Optimization (RGPO), a two-stage training algorithm. RGPO first warms up the scorer using self-evolving seed rubrics and then jointly optimizes the rubric generator to produce query-adaptive evaluation criteria while continuously aligning the scorer with human ratings. Extensive experiments on the 16-dimensional EvalVerse benchmark and external datasets demonstrate that RewardVerse mitigates scalar drift, achieves state-of-the-art performance on both pointwise and pairwise evaluation, and provides a robust and interpretable reward signal for RL in video generation.

Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtasks to other agents, and pay for metered resources. Deploying such agents safely requires five capabilities that today live in separate systems: persistent identity, scoped delegation, peer trust, discovery, and payment. Existing approaches root these in centralized authorities or cover only subsets, so authority, trust, and payment fracture exactly where autonomy needs continuity: when a key rotates or a delegation must be revoked. We present NostrAgent, a decentralized architecture that unifies all five over Nostr relays using three custom event kinds: Kind 38100 identity declarations authenticated by BIP340 Schnorr signatures with pre-rotation commitments, Kind 38101 scoped delegation chains whose every hop verifiably narrows granted capabilities, and Kind 38102 peer attestations forming a Sybil-deterrent trust graph, with Lightning HTTP 402 (L402) binding payment to agent identity. Identity remains operator-sovereign without any registration authority; relays are substitutable transport rather than a trust root; and every authorization decision is replayable offline from signed events. We evaluate a Python prototype with a mixed-method design: ATAM quality analysis with a two-round mini-Delphi panel, STRIDE threat modeling across three trust boundaries, eleven benchmarks with non-parametric statistics, and 19 failure modes. Results show sub-millisecond offline verification, linear delegation-chain scaling, and Lightning-settled L402 at 157 ms median on regtest. 17 of 19 failure modes pass empirically, one is bounded analytically, and one is disclosed as an architectural limitation. NostrAgent demonstrates an auditable prototype substrate for trustworthy agentic systems without centralized trust roots.

Token selection for instruction tuning is coupled: supervision utility depends on retained context, and vice versa. Existing methods largely optimize prompt compression or response supervision separately. Combining selectors can value supervision using removed context, or context using excluded supervision, creating selection-state mismatch. BRIDGE (Budgeted Response-Prompt Interaction via Directional Gradient-guided Efficient Token Selection) models selection-conditioned token utility through a shared validation-directed surrogate objective. BRIDGE routes response utility to supporting prompt tokens through attention, then alternates budgeted selection to revalue each side under the other's retained subset. Updates reuse precomputed interactions without repeated model scoring, while structure-aware projection promotes coherent supervision spans. Across three model families and three task domains, BRIDGE performs best overall among evaluated selection methods. Its MATH advantage over independent selection grows with compression, reaching 1.66 percentage points on Llama-3.2-3B.

Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-rendering correctness. However, existing IQA models rely on fixed definitions and heavy supervision, making them difficult to extend to open-ended perceptual dimensions. We identify holistic bias as an important limitation: when scoring an unseen dimension, models reuse generic quality priors, leading to scoring errors and rank inversion. To address this, we propose PACE (Perceptual Agentic Collaborative Evolution), a training-free multi-agent framework that formulates open-ended IQA as explicit protocol construction. Given a target dimension, PACE uses collaborative agents to construct an evaluation protocol composed of verifiable Visual Question Answering (VQA) probes, grounding evaluation in concrete visual evidence rather than holistic impressions. The resulting protocol is calibrated using only four human-annotated images per dimension, while a dual-track scoring mechanism aligns model perception with human scoring scales. Across traditional IQA, structural fidelity, context-aware aesthetics, and newly defined open-ended dimensions, PACE consistently improves its MLLM backbone, achieving competitive performance across diverse IQA settings, and reduces the Holistic Override Rate (HOR) from 44.4% to 8.6%.

Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and missing details in under-constrained regions, resulting in degraded reconstruction and unstable rendering. To tackle these issues, we propose D$^{3}$GS, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance. D$^{3}$GS first recovers a high-resolution, metric depth map via diffusion-based completion and DPT (Dense Prediction Transformer) refinement, providing robust Gaussian initialization and geometric constraints. Then, a DINO-guided view-consistent learning is introduced to augment Gaussian attributes with structural features, improving multi-view consistency. Finally, a diffusion-based Gaussian refinement module injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation. Experiments on DTU, LLFF, and Mip-NeRF 360 show that D$^{3}$GS achieves consistent and substantial improvements over strong baselines, with ablation studies validating the effectiveness and complementary roles of each component.

Given a directed graph with positive edge weights and two vertices s,t, a next-to-shortest s-t path is a shortest simple s-t path among those whose length is strictly larger than the shortest-path distance. The problem was introduced by Lalgudi, Papaefthymiou and Potkonjak in 1996; it is NP-hard when zero-weight edges are allowed, and its complexity on positively weighted digraphs remained open for almost three decades until Chen, Wein and Zhang recently gave a polynomial-time algorithm running in O(n^4 m^3 log n) time. We give a substantially faster algorithm within their optimal-middle-segment framework. The core idea is to split the problem into "choosing a prefix" and "completing it". Given a prefix P: s -> A made of shortest-path edges, delete the vertices used by P, forbid leaving A along shortest-path edges, and the best completion is one shortest-path computation. The difficulty lies in choosing P: even for a fixed A, deciding whether some shortest prefix admits a completion is NP-complete. We do not solve these fixed-A subproblems one by one. Fix any globally optimal next-to-shortest path; its middle segment induces a boundary edge x -> c in the shortest-path DAG. For the correct triple (A,B,x), the optimal path certifies c as a feasible next hop, and we prove that every feasible next hop that is not earlier than c in a topological order can be combined with the same middle segment into another globally optimal path. Hence only the feasible next hop of maximum topological index is kept per triple, giving O(n^3) representatives, all generated by a two-dimensional DAG dynamic program with a local reward. The total running time is O(n^3 (m + n log n)), and O(n^3 m) on unweighted graphs. The proof rests on an uncrossing lemma: the last intersection between a reference prefix and the candidate's partner suffix can always be moved strictly earlier, which cannot go on forever.

Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for a fixed budget of attention. A detective does not work that way. They sort what happened when, and they keep a map of who relates to whom, so a clue from chapter one can meet a question asked at the end of the book. We test whether a frozen knowledge graph can give a small local model that same freedom. Thirty detective novels and 234 multiple-choice questions are answered by one fixed qwen3.5:9b reader under nine conditions: five graph routes, a recent-window baseline, whole-book compression, ordinary vector retrieval, and a question-only control. The strongest graph route reaches 53.85% (126/234) against 46.15% for the recent window, 51.28% for compression, 51.71% for vector retrieval and 40.17% for question-only. On the subset that no model can answer without the book, the graph route reaches 42.86%. None of the fifteen graph-baseline contrasts survives Holm correction, so we present the result as exploratory evidence about a design. Two structural findings survive scrutiny better than the headline number: annotated evidence concentrates in the topological core of these graphs (2.35x enrichment, pooled), and the two graph-building pipelines differ so much in annotation coverage (16% versus 73% of clue paragraphs) that pooled accuracy alone would hide which bottleneck is being measured.

We present reference implementations of four published primal heuristics for mixed-integer programming inside the open-source solver HiGHS (Huangfu and Hall, 2018): Feasibility Jump (Luteberget and Sartor, 2023), fix-propagate-repair (FPR; Salvagnin, Roberti and Fischetti, 2025) with its LP-guided dive-time variant, LocalMIP (Lin, Zou and Cai, 2024), and the first-order-LP feasibility pump Scylla (Mexi et al., 2025). They share one integration interface with per-heuristic budgets and patiences, and each runs in parallel on independently seeded workers. The evaluation is on the mipfeas benchmark (Bussieck and Dirkse, 2026), 233 instances at 600 s, against a separately built unpatched HiGHS on the same machine. The primal integral improves by 23.7% over the full set and by 12.9% on the instances not used for tuning: the patched solver reaches a good solution sooner. At the time limit it is slightly ahead. It finds a solution on 4 instances where the unpatched solver finds none, against 1 the other way, and its final gap is smaller, significantly so only over the full set. Scylla and the LP-guided dive produced no accepted incumbent in any full-limit run that carried them and ship disabled; their implementations remain. The implementation is released as open source.

Prior studies on wideband physical layer security (PLS) have mostly focused on either far-field or near-field communication systems. In this paper, we investigate PLS in a more general and practical mixed near-field and far-field wideband communication scenario, where a base station (BS) equipped with an extremely large-scale array (XL-array) serves multiple legitimate users in the far field, while a near-field eavesdropper attempts to intercept confidential information at close range. Specifically, we formulate an optimization problem to maximize the secrecy rate of all legitimate users across all subcarriers by jointly designing the transmit beamforming and artificial noise (AN), subject to per-subcarrier power constraints. To gain useful insights into the unique characteristics of mixed-field wideband PLS, we first analyze a special case with a single legitimate user and an eavesdropper. Interestingly, we show that the secure transmission regions in mixed-field wideband systems are not the same across all subcarriers, as revealed by subcarrier-specific secrecy conditions derived from the Fresnel integrals. Moreover, we theoretically demonstrate that introducing frequency-selective AN into the system offers two key benefits: 1) it transforms originally insecure subcarriers into secure ones, and 2) it substantially improves the overall secrecy performance. For the general multiuser setup, we propose an efficient two-stage hybrid beamforming algorithm to jointly design the transmit beamforming and AN, ensuring secure transmission under mixed-field conditions. Building on our analytical insights, we further develop an efficient and low-complexity algorithm that designs the AN beamformers by directly aligning them with the eavesdropper's channel, thereby eliminating the need to optimize AN beamformers across all subcarriers.

Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. We develop a cross-linguistic psychometric profiling framework and evaluate nine LLMs using seven psychological instruments, with five repeated administrations per model and language in Chinese and English. Items unresolved after a prespecified retry procedure are retained as NA. Joint analysis of scored and NA responses captures response tendencies and boundaries of self-report applicability. LLMs exhibit structured, model-specific profiles despite a shared alignment-shaped pattern of higher prosocial and self-regulatory responses and lower dominance, disengagement and harmful-intent endorsement. NA responses are structured rather than uniformly distributed, indicating where outputs are treated as inapplicable, refused or cannot be mapped to valid response options. Language condition and provider origin are associated with profile configuration and answerability, whereas repeated administrations show high reproducibility and permit recovery of model identity. Human-reference and prompt-robustness analyses further indicate that these signatures are context dependent. Joint analysis of psychometric profiling and answerability offers a framework for quantifying deployment-level behavioural signatures.

Federated learning (FL) enables collaborative model training without centralizing private data, but performance often degrades under feature skew: clients share labels while the conditional input distributions $p_i(x\!\mid\!y)$ vary due to latent, client-specific appearance factors. We propose Joint Domain-Class Federated Learning (JDFL), a lightweight, optimizer-agnostic extension that makes this latent domain variation usable without sharing raw data. JDFL first infers domain clusters called pseudo-domains from brief local update signals. It then expands the classifier head to output $M\times C$, joint (domain-class) logits. This allows the model to represent domain-conditioned appearance while keeping a shared backbone. To train the expanded head we introduce two complementary supervision strategies based on simple intuitions: a similarity-aware soft-labeling that transfers evidence between nearby inferred domains while allowing domain-specific specialization, and a per-sample randomized target assignment that perturbs supervision across the joint outputs and serves as a low-cost training-time regularizer. JDFL integrates with existing standard FL methods (e.g., FedAvg, SCAFFOLD) with minimal changes. Empirically, both supervision modes consistently improve global test accuracy on standard domain-shifted image benchmarks; ablations and sensitivity studies show the gains stem from the proposed supervision and parametrization rather than mere capacity increase.

The Pfaffian number of a graph is the minimum number of Pfaffians needed to obtain its perfect-matching polynomial by linear combination. In 2009, Norine conjectured that every Pfaffian number is a power of four. Miranda and Lucchesi disproved this conjecture in 2011 by constructing a graph of Pfaffian number six, and conjectured instead that every nontrivial Pfaffian number is even. We disprove their conjecture by proving that the Pfaffian number of $K_{3,3}\sqcup K_{3,3}$ is 13. We also construct a connected cubic bipartite matching-covered graph with Pfaffian number 13.

Reach-and-attach of soft robotic arms with passive suction requires accurate targeting and sufficient contact speed, yet geared actuators can impose a speed limit that improved trajectory tracking alone cannot overcome. This paper proposes an embodied snap controller that separates slow servo-driven preloading from rapid elastic release, enabling a compliant arm to move beyond its direct tendon-driven speed limit. Octopus biology motivates the controller's section-wise organizational prior, rather than reproduction of the octopus nervous system. A learned policy shared across three sections selects preloads, aim, tendon slack, and release timing, determining where, how, and when to load and release the body. The policy is optimized offline using a hardware-validated recurrent model within experimentally supported bounds. Across five optimization seeds and 400 unseen simulated targets, attachment success is $(73\pm4)\%$ at a $5\text{ cm}$ lateral tolerance, and the shared policy reaches the matched centralized controller's mean final reward after a median $17\%$ of the common evaluation budget. Hardware characterization achieves tip speeds of 1.56-1.64 m/s, at least $108\%$ above direct tendon-driven release. In 18 open-loop hardware trials across six placements, 17 exceed the 1 m/s snap threshold and nine retrieve the object, with successful retrieval at five placements. These results demonstrate a practical division of responsibility in the control problem: learned control prepares the body, and passive body mechanics execute the rapid movement needed for dynamic reach-and-attach.

Vision-language models (VLMs) provide a compelling foundation for reasoning-driven mobile navigation, offering rich contextual understanding and strong generalization from large-scale pretraining. Most existing navigation frameworks rely on imitation learning and therefore require substantial labeled trajectory data, limiting their scalability and robustness. In this work, we propose a parameter-efficient approach to fine-tune a pretrained VLM for autonomous navigation using an Imperative Learning paradigm. By optimizing against differentiable geometric cost fields rather than labeled trajectories, our model learns to generate collision-free paths exclusively from stereoscopic depth observations. We introduce a unified end-to-end navigation pipeline for natural-language-driven robotic control. This system leverages a shared VLM backbone with task-specific Low-Rank Adaptation (LoRA) modules, effectively bridging the gap from semantic target selection to low-level trajectory planning. Our approach achieves competitive Success weighted by Path Length (SPL) in unseen environments while updating less than 1% of the model's total parameters. Qualitative real-world experiments validate sim-to-real generalization and stable path planning without fine-tuning on real-world data. These results highlight a practical approach for deploying VLM-based agents on mobile robots, enabling high-level semantic navigation without the prohibitive requirement for large-scale, labeled trajectory data.