Papers

Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR systems perform well, end-to-end (E2E) models often struggle with information loss and hallucinations on extended audio. For the BeTraC 2026 challenge, the ASLP team presents a fully E2E multimodal system that generates structured SOAP notes directly from audio, bypassing intermediate transcripts. We constructed a 1.41-million-sample multi-task corpus and applied a multi-stage pipeline: domain pre-training, supervised fine-tuning, and reward optimization. Evaluating the architecture under both Lightweight (3B) and Heavyweight (30B) constraints reveals that each training stage progressively enhances performance. Furthermore, scaling to 30B parameters substantially boosts concept extraction and summarization quality. Ultimately, our E2E systems consistently outperform representative cascaded ASR+LLM baselines, proving the efficacy of direct multimodal optimization for clinical documentation.

Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity attribute cannot be inferred from semantics alone and is confounded by camera ego-motion. We introduce \method, an online framework that augments query-based video segmentation with region-level dynamicity prediction. It jointly produces the original segmentation outputs and a dynamic or static state for each predicted region. At inference, DynEoMT uses only the current frame and propagated queries, without optical flow, depth, camera pose, previous RGB frames, or feature maps. Because established video segmentation benchmarks do not annotate this attribute, we also introduce a class-agnostic offline supervision pipeline using camera-compensated optical flow and confidence-aware temporal filtering. Across VIPSeg, OVIS, YouTube-VIS 2022, and VSPW, DynEoMT achieves balanced accuracies of 84.3, 68.0, 68.6, and 87.6, respectively, while largely preserving segmentation performance. These results show that segmentation-region dynamicity can be learned from propagated queries, enabling its online prediction without a dedicated motion-processing pipeline at inference. The complete code will be released as open source to enable full reproduction of the method and experiments.

We study the allocation of indivisible chores with subsidies under negative dichotomous valuations, where the marginal disutility of every chore is either zero or one. This is the chore analogue of the dichotomous goods model of Barman et al. (2022), for which a subsidy of at most one unit per agent is known to suffice for envy-freeness. Our main contribution is to show that the same optimal guarantee holds for chores under no structural assumption beyond binary marginals. For every instance with negative dichotomous valuations, there exists a complete allocation $\mathcal{A}$ and a subsidy vector $p\in\{0,1\}^n$ with $\sum_{i\in N} p_i\le n-1$ such that $(\mathcal{A},p)$ is envy-free. Moreover, $\mathcal{A}$ is EF1 even before subsidies are paid. The subsidy bound is tight, and both the allocation and the subsidies can be computed in polynomial time in the value-oracle model. Unlike in the corresponding goods setting, a natural incremental extension approach does not work for chores. Our proof instead exploits key properties of an envy-free partial allocation and its associated equality graph to complete the allocation and determine which agents require subsidies. As a further extension of the main theorem, we establish the same optimal unit-subsidy guarantee for objective mixed instances with signed binary marginals, where every item is a good for all agents or a chore for all agents; these valuations need not be additive. The key step is to prove that the goods-side extension argument of Barman et al.~\cite{BKNS22} remains valid even when the previously allocated bundles contain chores. Finally, even for negative dichotomous chore valuations, we show that the unit-subsidy guarantee cannot, in general, be maintained if Pareto optimality is also required.

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatial coverage is typically obtained by synthesizing full-sphere videos or constructing explicit 3D representations. Motivated by the complementary roles of global context and selective local acuity in visual perception, we present AlayaVista, a camera-controllable streaming video world model that decouples panoramic world evolution from perspective observation synthesis. Given a single perspective image, AlayaVista constructs a 360-degree scene prior using a pretrained panorama expansion model and then evolves the scene as a camera-conditioned panoramic latent state. A latent viewport renderer maps this state to the requested perspective video latents, while a perspective refiner restores details, suppresses artifacts, and performs super-resolution. To support efficient streaming, we adapt the panoramic generator to chunk-autoregressive generation and distill both panoramic generation and perspective refinement into few-step processes. To provide the supervision required by this design, we construct MUGEN, a large-scale real-world panoramic video dataset containing 1,318 hours of videos at resolutions of at least 4K, together with rich semantic and geometric annotations.

Although flexible resource aggregators (FRAs), represented by electric vehicle aggregators (EVAs) and load aggregators (LAs), possess inherent flexibility to mitigate three-phase unbalance, the key challenge lies in how to effectively incentivize them to actively participate in unbalance mitigation. To address this, this paper proposes a generalized Nash bargaining (GNB)-based chance-constrained coordinated operation model for the distribution system operator (DSO) and FRAs. In this framework, the DSO and FRAs cooperate to mitigate three-phase unbalance, where FRAs provide flexibility to reduce the DSO's unbalance mitigation costs, and the DSO offers economic incentives to FRAs in return. Bargaining power is tailored according to each participant's contribution to unbalance mitigation to ensure fair profit allocation. Moreover, a scenario-based chance-constrained formulation is integrated to handle photovoltaic (PV) output uncertainties. To solve the model, a distributed proximal decomposition algorithm (PDA) is introduced for the independent model, while the coordinated model is decomposed into a social welfare maximization subproblem and a payment bargaining subproblem, with an improved bilinear Benders decomposition algorithm developed to solve the former. Numerical results validate the effectiveness of the proposed method in mitigating unbalance, ensuring fair profit distribution, and enhancing robustness against uncertainties.

In an integrated sensing and communications (ISAC) system, targets may intercept information. We address this specific security issue in a full-duplex ISAC system with malicious eavesdroppers aiming to intercept uplink (UL) and downlink (DL) communication exchanges between the dual-functional radar and communication base station and legitimate communication users. We formulate an optimization framework to maximize the sum secrecy rate for both DL and UL, considering power budget constraints for sensing and communications. The optimization problem is non-convex, so we introduce an iterative joint Taylor-block cyclic coordinate descent (IJTB) method to approximate it as a convex problem. The IJTB method alternates between sub-problems: one for UL beamformers and another for UL power allocation, artificial noise covariance, and DL beamforming, using Taylor approximations to simplify optimization. Simulations demonstrate the effectiveness of our approach compared to standard benchmarks.

Periodic Bloom-filter transmission can impose substantial overhead in communication-constrained distributed systems. Lossless compression preserves membership behavior but provides a single transmission size, whereas established OR folding produces smaller representations with higher false-positive rates (FPRs) while preserving the no-false-negative property. This paper investigates channel-aware selection among OR-folded representations. The sender retains an unchanged canonical filter, constructs a catalog satisfying a maximum FPR, and selects the FPR-qualified representation with the largest retained length supported by the communication resources available at each reporting opportunity. Unlike folding driven principally by cardinality and false-positive constraints, selection is driven by time-varying communication conditions. Using two phishing URL datasets, the framework is evaluated under Five-State Markov Capacity, Gilbert–Elliott burst-error, and Rayleigh block-fading models. Channel-aware folding improves communication efficiency and receiver freshness relative to complete-filter and lossless-compression baselines when communication opportunities vary substantially. Under the more favorable Gilbert–Elliott model, it remains competitive in efficiency while maintaining the freshest receiver state. These results show that FPR-qualified folded views provide useful transmission operating points when a recent lower-fidelity update is preferable to delaying a larger representation.

When reinforcement learning (RL) is used for post-training automatic speech recognition (ASR), the reward almost always lives in the text space: it compares a hypothesis with the reference and never checks whether the hypothesis is supported by the audio. On highly regular speech this licenses a shortcut - guessing from a strong language prior rather than listening. Once the acoustics degrade, the shortcut runs unchecked and emits fluent but ungrounded words, i.e., insertion errors. We propose an acoustic-fidelity reward: a GRPO reward augmented with a separately pretrained, permanently frozen, non-autoregressive character-level wav2vec2-CTC acoustic judge, used strictly at training and absent at inference, where a single model decodes greedily. Trained on LibriSpeech and evaluated across a six-tier difficulty gradient including real AMI meeting speech (33,282 utterance-condition instances), the method reduces insertion errors by 28.3% on close-talking AMI-IHM and 22.3% on far-field AMI-SDM, while lowering WER on AMI-SDM from 35.89% to 34.71% and showing no detectable WER difference on the other five tiers, against a schedule-matched WER-GRPO baseline. The insertion reduction holds under a meeting-level clustered bootstrap. Four prespecified analyses support content-conditioned insertion calibration: output collapses 85-90% on unintelligible audio that preserves energy and voice activity; the gain is not recovered by the evaluated 32-best CTC rescoring configuration, yet RL internalizes it into a single greedy decoding run; and policy-only confidence yields lower insertion-AURC in all four evaluated settings. We frame this as a mechanism paper, demonstrated in one instantiation: a 7B speech LLM with a 0.3B CTC judge.

Generative AI writing assistants are becoming integrated into collaborative text editors; however, it is unclear how much information about a user's prompting activities should be shared with collaborators. We explore the effects of different levels of prompt information sharing within collaborative text editors: not sharing anything, sharing a placeholder to indicate AI use; sharing details about how the resulting text was generated; and sharing everything, including how the prompt was formulated, in real-time. Sixteen participants wrote persuasive essays in pairs using all four techniques. Results suggest a strong preference for techniques that share more information about prompting activities for increased awareness. Our work shows that collaborative text editors should share more information among writers on when, how, and where AI is used.

Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the pseudo-labels that are then used to update the model. In the cold-start regime, where at most a few labels per class are available, this coupling is ill-posed, since the classifier cannot supervise itself before it has learned. To address this problem, we propose VAST (Veracity-Aware Semi-Supervised Training), which decouples these two stages. Probabilistic beliefs over the unlabeled set are first inferred directly from the geometry of a frozen self-supervised embedding and only then distilled into an inductive classifier. The construction rests on the Veracity Matrix, a kernel-based structure that aggregates label evidence across the data manifold and admits an interpretation as a Dirichlet posterior under a per-observation powered-likelihood model. Additionally, we introduce Veracity Propagation, a self-terminating belief-spreading step that extends coverage beyond the kernel neighborhood of the labeled set. Under a controlled protocol in which all methods receive identical frozen embeddings and labeled sets, VAST outperforms the strongest graph-based SSL baselines at every operating point across three datasets, with statistically significant gains in 7 of 9 comparisons, while producing a deployable inductive classifier rather than requiring transductive graph inference. Compared with end-to-end confidence-gated SSL, we further find that these methods underperform in this setting and, in our experiments, do not consistently exceed labeled-only performance.

Cleaning water bodies such as swimming pools and lakes typically demands significant manual effort or reliance on costly, sensor-intensive robotic systems. This paper presents EcoBoat, a low-cost autonomous surface vehicle built on a modified hull, designed to collect floating debris in both indoor and outdoor water bodies. For indoor environments, EcoBoat uses ultrasonic sensors to detect boundaries and obstacles, combining random-walk motion with boundary-following behavior. For outdoor environments, it relies on GPS-based geofencing paired with a random-walk strategy for area coverage. A key design feature is a Tesla-valve-inspired collection basket that allows debris intake during forward motion while preventing its escape during turning or braking. Field experiments in pools and lakes validated the design through iterative refinement, demonstrating that a minimalist sensing and computation approach can achieve effective, versatile debris collection across diverse water bodies.

Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been filtered out, and that none of the tested data-level defenses reliably removes or detects such a bias, even when the defender knows what to look for. To shed light on the hidden traces these biases leave, we embed a dataset's completions with Sentence-BERT, subtract the embeddings of clean reference completions, and compare the result to an open vocabulary of candidate topics. This simple signature identifies the topic of the bias with a Matthews correlation coefficient of 0.83 when the attacker's teacher model is known, and 0.46 when it is not. We also observe that different teacher models appear to express the same bias through different vocabulary.

Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to detect patterns of truthfulness and factuality. A less-studied approach is to identify feed-forward neurons correlated with hallucination. In this empirical study, we propose a method to rank feed-forward neurons at the final prompt token and use it to investigate the feasibility of utilizing them for hallucination detection in the first forward pass. Using a neuron selection dataset built from CounterFact for identifying neurons correlated with hallucination, we transfer the selected neuron identities to train hallucination classifiers on other factual question-answering datasets. Our work provides empirical evidence that probes trained using the features from sparse sets of selected neurons perform on par with probes trained on internal representations. We also analyze the distribution of selected neurons and the effects of layer depth and neuron budget on detection performance. Our results show that randomly drawn neuron sets are also competitive at larger budgets, suggesting that signals correlated with hallucination are distributed across many neurons, while selection can help in extremely sparse sets.

A new robustness metric $\nu$ was recently proposed as a substitute for the structured singular value $\mu$ to better capture robustness to sparse diagonal uncertainty, but its computation has remained an open problem. In this paper, we show that computing $\nu$ is equivalent to maximizing the spectral radius of a nonnegative matrix product. This equivalence allows us to transfer existing results on spectral-radius maximization to $\nu$, including a refined upper bound and conditions under which the bounds coincide. We then provide reformulations and structural results that enable an algorithm to solve the nonconvex optimization problem for nontrivial problems using global solvers. This also enables identification of the most fragile parts of the system. Our results do not yet provide a scalable solution for computing $\nu$, but they are an important step toward computability and interpretability.

Set reconciliation, where two parties each holding a large set of elements aim to identify their set difference, is a fundamental task in many areas. Time (computation cost) and space (communication cost) are two important metrics in this problem, and much existing work optimizes one at the expense of the other, creating a clear trade-off. We study this trade-off through algorithmic upper bounds and matching space lower bounds. On one side, we propose XYZ-Sketch. For sufficiently large $d$, XYZ-Sketch achieves high-probability reconciliation for sets whose differing elements are uniformly random, using only $(1+\varepsilon)d$ elements for communication, while achieving $O(\log(1/\varepsilon))$ insertion time and expected $O(d\log V\log^{3/2}(1/\varepsilon))$ decoding time, where $d$ and $V$ denote the size of the difference between two sets and the universe size, respectively. On the other side, we establish a broad fixed-support canonical model and prove a matching space lower bound, establishing the asymptotic optimality of XYZ-Sketch. Our proof also establishes an extremality theorem resolving Walzer's conjecture. Experiments demonstrate the practical advantages of XYZ-Sketch, and the source code is available at https://github.com/djwj233/XYZ-Sketch.

Parkinson's disease (PD) manifests early neuromotor impairments that become observable in controlled hand-drawn patterns such as spirals and meanders, where tremor-induced oscillations, stroke irregularity, and curvature instability reflect underlying motor degradation. In this work, we present an explainable framework for PD screening from offline hand-drawn patterns that integrates discriminative visual modeling with clinically grounded reasoning. The predictive model captures distributed structural distortions and fine-grained texture variations. It is evaluated under subject-disjoint protocols to ensure reliable generalization. To move beyond black-box classification, we introduce a multi-stage explainability pipeline that combines visual attribution with structured symptom abstraction. Salient regions are identified using attention- and gradient-based localization, followed by extraction of clinically meaningful motor descriptors quantifying contour roughness, curvature irregularity, stroke variability, and tremor-frequency energy. These descriptors are subsequently translated into coherent clinical rationales through a language-based reasoning module, linking model evidence to established PD symptomatology. By bridging visual attribution and clinical interpretation, the proposed framework advances interpretable document intelligence for neurological screening using hand-drawn patterns. Experimental results on publicly available Parkinson's disease handwriting datasets demonstrate competitive predictive performance and clinically consistent explanations.

Blind image inpainting, aiming to recover contaminated images in the case of unknown masks, is a challenging task. Motivated by the perspective of human vision and knowledge, blind image inpainting can be decomposed into two stages: mask estimation and image inpainting based on the estimated mask. The two-stage idea exhibits evident advantages in enhancing inpainting quality and augmenting the generalization capability of unknown real-world contamination by explicitly employing the estimated mask for image inpainting compared to one-stage scheme. This two-stage idea has also been intuitively implemented. However, existing two-stage methods excessively emphasize the unilateral relationship of mask estimation to image inpainting, and may overlook the mutual relations between them. Specifically, mask estimation can provide more contextual semantics for image inpainting to strengthen the understanding of semantics, and image inpainting can offer more contextual details (e.g., textures and edges) for mask estimation to improve the learning of details. In this work, we propose a novel Context-Aware Mutual Learning (CAML) framework for blind image inpainting that joints mask estimation and image inpainting to mutually exploit contextual information. In the CAML framework, we design the Inpainting-Guided Context-Mutual (IGCM) learner to acquire the complementary contextual details from image inpainting for assisting mask estimation, and the Estimation-Guided Context-Mutual (EGCM) learner to strengthen the understanding of contextual semantics from mask estimation for assisting image inpainting. Ablation studies validate the efficacy of our CAML. Extensive experiments show that our CAML achieves state-of-the-art performance on both blind image inpainting and additional vision tasks, i.e., snow removal, shadow removal, and watermark removal, indicating its superiority.

When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that adding independent, competent advisers makes the majority more reliable. The theorem, however, has a latent dimension when viewed from the user's vantage: adding advisers also makes disagreement more visible. A binomial model reveals that this “visible dissent” becomes nearly inevitable as the number of advisers grows, and that reliability and disagreement approach certainty at rates that cross at an adviser accuracy of 4/5 (0.8); below it, visible dissent eventually becomes more likely than a correct majority. Even ideal panels of independent and competent advisers can be correct in aggregate but appear divided; such disagreement does not by itself indicate aggregation failure. The way advisers split also provides a common basis for predictive multiplicity, reconciliation load, and reliance miscalibration. These results separate aggregation from disclosure and turn the latter into testable questions about how disagreement should be presented and interpreted.

Deepfake detection systems often exhibit significant performance degradation when deployed on unseen manipulation methods, limiting their reliability in real-world multimedia environments. This lack of generalization poses critical challenges for misinformation mitigation, digital forensics, and human-centric AI systems. Existing detectors perform well on the forgery methods they are trained on, but their accuracy drops sharply on unseen pipelines. To bridge this generalization gap, we propose WAVIE (Wavelet Augmented Vision Intermediate Embeddings), an end-to-end architecture that combines complementary spatial and frequency cues on top of a frozen CLIP backbone. WAVIE projects intermediate transformer embeddings through a lightweight learnable module, applies a three-level Daubechies-6 (db6) discrete wavelet transform (DWT), refines the low-frequency branch while preserving the high-frequency branch, reconstructs the feature via inverse DWT, and performs classification. Trained only on FaceForensics++, WAVIE achieves AUROC = 0.852 on Celeb-DF-v1, 0.852 on Celeb-DF-v2 and 0.831 on WildDeepFake (WDF) at the frame level, outperforming several state-of-the-art generalization baselines. Extensive ablation studies confirm the importance of both the wavelet module and the intermediate-feature aggregation for cross-dataset performance, highlighting the necessity of jointly leveraging spatial and frequency domains. These results position WAVIE as a strong baseline for deepfake detection in the wild.

We study the algebraic structure of principal ideal codes and CSS-type stabilizer constructions over the ring $ R_q=\mathbb Z_q[i],$ where every prime divisor of $q$ is congruent to $1$ modulo $4$. Although such ring-based constructions have recently been considered in the context of classical and quantum error correction, the precise relationship among principal ideal cardinalities, Hermitian duality, algebraic cosets, and stabilizer syndromes requires further structural analysis. We obtain cardinality formulas for principal ideals and their annihilators. For a length-one principal ideal code $C=\langle\alpha\rangle$, we show that its Hermitian dual is $ C^{\perp_H}=\operatorname{Ann}(\sigma(\alpha)). $ For nested codes satisfying $ C_2^{\perp_H}\subseteq C_1\subseteq C_2, $ we determine the corresponding CSS-type stabilizer and prove that the kernel of the physical $X$-error syndrome map is $ \ker(\operatorname{Syn}_X)=C_2. $ Consequently, $C_2/C_1$ parametrizes logical $X$-operator classes and $R_q^n/C_2$ parametrizes physical $X$-error syndrome classes. Using this syndrome quotient, we construct a transversal of $C_2$ in $R_q^n$ whose elements have pairwise distinct physical $X$-error syndromes. The corresponding $X$-type error family is correctable by stabilizer syndrome measurement, yielding a syndrome-based recovery procedure that is consistent with the stabilizer structure. Explicit examples illustrate the resulting duality, cardinality, and syndrome structure.

The computation of row echelon form is one of the main bottlenecks in the F4 algorithm. Several state of the art implementations use a probabilistic algorithm attributed to Monagan, Pearce, and Steel to accelerate this computation. Despite this, no bound on the probability that the algorithm returns an incorrect result appears to be available. In this paper, we provide such a bound. Furthermore, building on this result, we propose a Las-Vegas variant of the F4 algorithm and show experimentally that it can outperform deterministic F4 on some classical examples.

Existing humanoid locomotion systems primarily focus on stability and task execution, while integrating expressiveness with explicit locomotion control remains challenging. We propose EMoG, an emotion-modulated gait generation framework for expressive humanoid locomotion. EMoG introduces an emotional-style code with continuously adjustable intensity. Conditioned on this code and physical commands, a lightweight MLP generates expressive, command-consistent periodic gait trajectories in real time, which are tracked by a unified reinforcement learning policy for physical execution. To support training, we collect a large-scale emotion-annotated gait dataset from professional performers and develop an automated pipeline to extract physically consistent periodic gait cycles. EMoG also integrates an LLM-based parser that converts free-form language into emotional style and motion parameters for interactive control. Experiments demonstrate that our system achieves continuous gait-style modulation with perceptible expressive cues while maintaining command tracking. EMoG provides a practical approach to parameterized emotional-style walking for human-robot interaction.

Speech Large Language Models (Speech LLMs) have shown strong performance across diverse tasks, yet their utility for pathological speech analysis remains underexplored. In this work, we investigate the effectiveness of internal representations from encoder and decoder components of Speech LLMs for Parkinson's Disease (PD) detection across multilingual and cross-lingual settings. Our findings reveal that encoder representations consistently outperform their decoder counterparts in most models and settings and that pathological cues may be progressively attenuated as audio representations are projected into the language model space. We further show that generative outputs are less reliable for clinical tasks compared to internal representations. To leverage information spread across multiple layers, we propose a Squeeze-and-Excitation (SE)-based dynamic layer aggregation framework, which surpasses best-layer selection in multiple experiments, suggesting that PD-relevant acoustic cues are distributed across transformer layers rather than concentrated in one.

A differentiable digital signal processing (DDSP) autoencoder reconstructs a monophonic harmonic sound through three types of synthesis parameters: fundamental frequency, loudness, and timbre features. To handle mixtures of harmonic sounds within the DDSP approach, we have previously proposed a DDSP mixture model (DDSPMM). It represents a mixture as the sum of source signals synthesized by the decoders of pretrained DDSP autoencoders. Although DDSPMM enables direct estimation of synthesis parameters of each source from mixtures, it does not explicitly model temporal variations in the synthesis parameters and can produce excessive temporal fluctuations. In this paper, we propose a method for estimating synthesis parameters with temporally plausible trajectories by incorporating a denoising diffusion probabilistic model (DDPM) into the DDSPMM-based estimation. The DDPM is trained as a generative model of synthesis parameters. During estimation, the proposed method guides the DDPM reverse diffusion process with the reconstruction error between the observed mixture and the mixture synthesized by DDSPMM from the current estimates. Experiments on woodwind and string instrument ensembles showed that the DDPM-based regularization improves synthesis parameter estimation by imposing temporal plausibility on the estimated trajectories.

We present a learning-based approach to kinodynamic online motion planning for an Unmanned Aerial Vehicle (UAV) operating at a fixed altitude in unknown dynamic environments, where real-time avoidance of both static and dynamic obstacles must be achieved under conditions of extreme partial observability. The UAV is controlled with a single degree of freedom (yaw only), resulting in constrained, nonholonomic motion similar to fixed-wing platforms. The proposed framework integrates a behavior grid map representation with Deep Reinforcement Learning (DRL), using Proximal Policy Optimization (PPO) for stable policy learning in continuous control. The key idea is the co-design of a state representation and control policy that enables reliable navigation using only three low-cost directional range sensors, without reliance on dense sensing modalities such as LiDAR or vision-based systems. The behavior grid map dynamically aggregates sparse measurements into a structured local representation that supports real-time decision-making for obstacle avoidance and target reaching. Extensive simulations across environments of varying sizes and obstacle densities demonstrate that the proposed standard and enhanced methods achieve higher success rates than PPO variants and Model Predictive Control (MPC) (94% vs. 79–90% in small-scale high-congestion scenarios, and 83% vs. 62–71% in large-scale high-congestion scenarios), while maintaining real-time performance. Real-world experiments across four scenarios further confirm practical feasibility, with consistent target-reaching behaviour and no collisions under the tested conditions.

Generative artificial intelligence raises a central question for scientific training and organization. Is research shifting from deep specialization toward broad individual knowledge? We examine this proposition across papers, cited knowledge, contributor histories, and teams using 47,959 articles from six fields over 2010-2025, 51,736 resolved cited works, and chronologically reconstructed prior publication histories for 1,754 randomly selected index contributors. From 2010 to 2022, team size increased by an estimated 37.3% (95% confidence interval [34.4%, 40.3%]), while paper topic breadth declined by 0.0144 on a 0-1 hierarchical distance scale. Cited knowledge was stable to modestly broader, revealing a divergence between focused outputs and the reach of knowledge inputs. Established contributors' prior breadth increased by 0.0190 [-0.0078, 0.0459] by 2019-2022, within a +/-0.05 equivalence bound assessed in sensitivity analysis. In mature citation windows, one standard deviation of focal depth was associated with 8.2% higher 1 + FWCI [1.9%, 14.9%]; average breadth and interaction associations were smaller under the specified equivalence bounds. Post-2022 deviations from earlier trends were not systematic, and recent changes did not vary clearly with baseline AI intensity across 83 subfields. The findings support a differentiated structure of scientific expertise in which focused individual accumulation coexists with expanding collaboration and sustained access to diverse knowledge inputs.

Reporting the Fisher geometry of a trained variational quantum model is routine; quoting the shot budget that would establish it is not. Certifying an empirical Fisher matrix to relative Frobenius error $\varepsilon$ under coordinate-wise parameter shift costs $\Theta(B p^{2} V/(\varepsilon^{2} G))$ circuit executions, where $V$ is the measured readout variance and $G$ the measured squared gradient norm, with uniform allocation optimal in that class. One constant reproduces the cost of two circuit families whose exponents differ by a full power of $p$. The exponent is an identity in how $nV$ and $nG$ scale with the register, holding family by family to $0.001$ across 624 matrix-product-state cells once the finite-$p$ prefactor is removed. The cubic cost is therefore a finite-size window, set by whether the readout light cone grows with the register. A product family to 256 qubits gives $1.966$ (95% CI $1.934$–$1.997$); a brickwork entangler falls from $2.853$ below ten qubits to $1.715$ beyond sixty-four; a blocked entangler gives $1.984$ at a fixed cone width against $3.034$ at a proportional one. Fixed device connectivity fixes the cone, so a cubic budget from a small simulation overestimates a large machine, on top of hardware multipliers $2.07\times$ ($1.41$–$3.02$), $2.38\times$ and $1.91\times$ on ibm_marrakesh, ibm_fez and ibm_kingston. Cost-optimal readout weights cut the measured shot budget by $2.67\times$ ($1.33$–$4.00$) on hardware, flat from four to twelve qubits. A discrepancy model fitted on cheap circuits transfers its mean inside the calibration grid and, at six larger sizes named before the data, does not: nominal 90% intervals cover 36%, and split conformal is the only rung that stays near nominal.

Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. While agents have proven their value in incident summarization and telemetry signal extraction, their effectiveness as autonomous control-loop engines heavily relies on their long-horizon reliability. One such setting is the datacenter fabric, where an agent must respond to alarms and operator intents while abstaining from high-risk actions that may cause or extend downtime. Abstention, however, presupposes that an action's impact is known pre-execution, which necessitates a per-action ground truth that NetOps agent benchmarks do not provide. We construct such a ground truth for the network repair task of NetArena. A symbolic replay of the emulated network, validated against the environment at every turn, yields the exact value of every action. From the action-level value, we derive two pre-execution targets, namely whether an action reduces the repair distance (progress) and whether it increases it (harm). We show across 10 agent models, that agent verifiers leveraging internal signals predict both harm and progress more reliably than a baseline using observable signals only. Perspectively, we aim to use these signals as safety feedback to an agent harness to abstain from risky actions and protect the target system.

Recent advances in multimodal foundation models have intensified the need to understand how different modalities share, preserve, and complement information. Mutual Information (MI), the Information Bottleneck (IB), and Partial Information Decomposition (PID) provide complementary perspectives, yet existing studies often treat them as isolated tools. This survey presents an information-theoretic perspective connecting these principles as progressively refined views of multimodal information processing: MI characterizes inter-modal dependency, IB explains task-oriented information preservation under compression, and PID decomposes preserved information into redundancy, uniqueness, and synergy. We review 170 recent studies (2018–2026) and 12 foundational works, organizing multimodal learning around four challenges: cross-modal alignment, information-efficient fusion, interaction-type characterization, and scaling to multimodal foundation models. Rather than using application domains as primary taxonomy axes, we interpret healthcare, robotics, recommendation systems, affective computing, and wireless communications as empirical validations of these information principles. Beyond taxonomy, we organize existing multimodal paradigms within a single information-theoretic coordinate system – the Generalized Multimodal Information Lagrangian – in which they occupy exact or approximate parameter corners, and whose unoccupied regions name candidate method families the literature has not yet built. We further discuss how emerging multimodal foundation models instantiate these principles at scale and identify open challenges including scalable information estimation in high-dimensional settings, standardized evaluation across information-theoretic methods, combinatorial complexity of multimodal PID, and the transition from post-hoc information analysis toward information-aware multimodal learning.

Person re-identification (ReID) is essential for multi-camera surveillance and tracking, yet remains difficult due to viewpoint and illumination changes, occlusion, background clutter, and low resolution imagery. We propose a generative AI integrated multimodal ReID framework designed explicitly for robustness under missing cues and low latency deployment. The key idea is a cost aware early-exit cascade that prioritizes inexpensive, high confidence evidence and only triggers expensive modalities for ambiguous cases. Our system integrates (i) global visual embeddings from segmented person regions, (ii) automatically generated fine grained semantic attribute descriptions generated by vision-language models (VLMs), and (iii) optional facial embeddings when face observations are reliable. To optimize the balance between accuracy and latency, we use a cost aware early-exit cascade instead of fusing all modalities. Specifically, we first inspect the top-k retrieval results to determine whether the query is unambiguous. If the best match is clearly separated from the remaining candidates, we stop early and return the result to minimize latency; in ambiguous cases, we keep multiple hypotheses and invoke additional modalities (face/semantic) with adaptive reliability weighting to refine the decision. We report person re-identification performance using mAP and Rank-1 accuracy on the Market-1501 and DukeMTMC-reID benchmarks. The proposed adaptive early-exit cascade resolves 60.7% of DukeMTMC-reID queries and 68.4% of Market-1501 queries without invoking semantic reasoning, reducing computational overhead while maintaining competitive retrieval performance.