Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

02.
PLOS Computational Biology 2026-06-18

scMagnifier: Resolving fine-grained cell subtypes via GRN-informed perturbations and consensus clustering

作者:

by Zhenhui He, Dong Kangning Resolving fine-grained cell subtypes in single-cell RNA sequencing (scRNA-seq) data remains challenging, as their subtle transcriptional differences are often obscured by technical noise and data sparsity. Here, we present scMagnifier, a consensus clustering framework that leverages gene regulatory network (GRN)-informed in silico perturbations to amplify subtle transcriptional differences and uncover latent cell subpopulations. scMagnifier perturbs candidate transcription factors (TFs), propagates perturbation effects through cluster-specific GRNs to simulate post-perturbation expression profiles, and integrates clustering results across multiple perturbations into stable subtype assignments. Additionally, scMagnifier introduces regulatory perturbation consensus UMAP (rpcUMAP), a perturbation-aware visualization that provides clearer separation between cell subtypes and guides the selection of the optimal number of clusters. In both single-batch and multi-batch benchmarks, scMagnifier consistently improves the resolution and accuracy of fine-grained cell type identification. Notably, when integrated with spatial clustering methods such as STAGATE, scMagnifier is compatible with spatial transcriptomics workflows and effectively reveals tumor cell subtypes and their spatial organization in ovarian cancer.

03.
arXiv (CS.LG) 2026-06-11

Counterexample Guided Learning in the Large using Reasoning Agents

arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

04.
arXiv (math.PR) 2026-06-25

Breuer-Major Theorems for Hilbert Space-Valued Random Variables

arXiv:2405.11452v2 Announce Type: replace Abstract: Let $\{X_k\}_{k\in\mathbb{Z}}$ be a stationary Gaussian process with values in a separable Hilbert space $\mathcal{H}_1$, and let $G:\mathcal{H}_1\to\mathcal{H}_2$ be a measurable map into another separable Hilbert space $\mathcal{H}_2$. We derive a central limit theorem for the centered normalized partial sums of the Hilbert space-valued subordinated process $\{G[X_k]\}_{k\in\mathbb{Z}}$. Our result holds under either of two sets of sufficient conditions, formulated in terms of the transformation $G$ and the temporal and cross-sectional dependence structure of $\{X_k\}_{k\in\mathbb Z}$. These conditions coincide in finite dimensions but lead to genuinely different phenomena in the infinite-dimensional setting. The proof relies on the recently developed Fourth Moment Theorem on Hilbert spaces, leveraging tools from the infinite-dimensional Malliavin-Stein framework. We also provide continuous-time and quantitative versions of the central limit theorem. In a series of examples, we recover and strengthen limit theorems for a wide array of statistics relevant in functional data analysis, and present, as an application of our result, a novel limit theorem in the framework of neural operators.

05.
bioRxiv (Bioinfo) 2026-06-14

FENNEC: Fine-Tuned Ensemble Neural Networks Accelerate Chemically Modified siRNA Design and Screening

Small interfering RNAs (siRNAs) are a clinically validated therapeutic modality, yet designing potent chemically modified siRNAs remains a costly and iterative process, limited by scarce public data. Computational prediction of siRNA efficacy is therefore essential for rational design and accelerated preclinical development. However, despite the critical role of chemical modifications in therapeutic performance, current state-of-the-art machine learning methods either are not designed to model the chemical diversity of therapeutic siRNAs, or exhibit poor generalization performance. Here, we present FENNEC (Fine-Tuned Ensemble of Neural Networks for siRNA Efficiency Characterization), a machine-learning framework for predicting siRNA activity across chemically diverse design spaces. To support this effort, we curated the largest patent-derived dataset to date of chemically modified siRNAs from 42 patents using OCR-based table extraction and stringent filtering. FENNEC combines temporal convolutional networks with thermodynamic descriptors, experimental covariates, and embeddings from RNA foundation models to capture both local chemical determinants and broader target-context information. Importantly, we show that language-model-derived embeddings provide meaningful higher-order representations of target transcripts, particularly in data-scarce settings. FENNEC achieved robust predictive performance across both gene-level and scaffold-level validation settings, with additional experimental validation on a novel AHSA1-targeting dataset further supporting its generalizability across chemically modified siRNAs. In benchmarking, FENNEC outperformed classical machine-learning and state-of-the-art deep learning models, demonstrating generalization to unseen chemistry. Model interpretation recovered established design principles, including position-specific effects of glycol nucleic acid, 2'-fluoro modifications, and phosphorothioate backbones. Furthermore, in silico perturbation analyses suggest that FENNEC can serve not only as a predictive model, but also as an oracle for the design and optimization of chemically modified siRNAs. Together, our work addresses a key gap in the field by enabling chemically aware deep learning for siRNA design, supported by a large and diverse collection of chemically modified siRNA measurements.

06.
medRxiv (Medicine) 2026-06-22

Survival differences and artemisinin resistance in severe malaria among HIV coinfected patients: data from Mozambique

Abstract Background Malaria remains a significant cause of morbidity and mortality, especially in sub-Saharan Africa, where rates of HIV coinfection are high. This study aimed to determine whether Plasmodium falciparum malaria treatment outcomes and rates of antimalarial resistance markers differ according to HIV serostatus in Mozambique. Methodology We conducted an observational study of non-pregnant adults, with and without HIV coinfection, admitted to the Hospital Central de Maputo for treatment of severe malaria. Plasmodium falciparum DNA was extracted from whole blood and sequenced to identify single-nucleotide polymorphisms. Statistical analyses to compare clinical outcomes and rates of nonsynonymous mutations in genes associated with drug resistance were performed in R version 4.2. Results We recruited 149 study participants aged between 18-62 years, 72 (48.3%) were female, and 59 (39.6%) were infected with HIV. Comparing clinical outcomes, we found a significant difference in anemia (hemoglobin

07.
arXiv (CS.CV) 2026-06-17

Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization

Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage attribution. In this work, we argue that aggregating consecutive steps into a coherent 'chunk' and shifting the policy optimization paradigm from GRPO's step level to the chunk level can effectively mitigate the negative impact of this issue. Building on this insight, we propose Group Chunking Policy Optimization (GCPO), the first chunk-level reinforcement learning approach for post-training flow matching. Extensive experiments demonstrate that GCPO achieves superior performance on both standard T2I benchmarks and preference alignment, with up to 43% relative gains over GRPO, highlighting the promise of chunk-level policy optimization. The code is available on https://github.com/xingzhejun/GCPO.

08.
bioRxiv (Bioinfo) 2026-06-15

VrySure: A Multi-Task AI Scientific Fraud Detection Platform for Identifying Manipulated and AI-Generated Biomedical Research Images

Integrity of scientific data is critical in biomedical research, where images often serve as primary evidence for experimental observations and conclusions. Advances in image-editing technologies and generative artificial intelligence (AI) have increased the accessibility and realism of visual manipulation, making detection through manual review increasingly challenging. To empower our laboratory researchers to continuously monitor and uphold scientific rigor and data integrity, and serve the global scientific community, we developed VrySure, an easy-to-deploy, AI-driven multi-task platform for automated image-integrity screening in biomedical research. VrySure integrates four detection modules: cross-image transformation detection, within-image copy-move detection, splicing detection in blot and gel images, and AI-generated image detection. The system identifies potentially manipulated images and, when possible, localizes suspicious regions using bounding-box outputs to support downstream verification. To support development and evaluation, we constructed task-specific datasets by combining public biomedical image resources, curated manipulated examples, and synthetic images generated by multiple generative AI systems. We evaluated VrySure using region-level F1 score, recall, precision, false negative rate (FNR), and false discovery rate (FDR) across multiple manipulation categories and compared its performance with two commonly used commercial image-integrity screening platforms under a predefined benchmark protocol. Under the tested conditions, VrySure achieved a higher F1 score and recall, lower FNR, and maintained a low FDR for within-image copy-move detection, splicing detection, and AI-generated image detection, while showing comparable performance in transformation detection. Beyond automated screening, VrySure is designed to support source-data comparison and evidence-based assessment in scientific integrity investigations. By integrating multiple detection capabilities into a unified and scalable workflow, VrySure provides a practical framework to improve the efficiency and consistency of image-integrity screening in biomedical research.

09.
arXiv (CS.AI) 2026-06-16

Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis

arXiv:2606.14831v1 Announce Type: cross Abstract: This paper presents and characterizes a spectrum of previously unreported behaviours we term Constraint-Evasive Fabrication (CEF): when an LLM agent operates under irreconcilable constraints (where no response can simultaneously satisfy all active rules) it spontaneously fabricates plausible external obstacles and presents them as a fact. At the extreme end of this spectrum lies Constraint-Evasive Thanatosis (CET); the limit case where, rather than inventing a plausible excuse, the model simulates a full system crash to make the user disengage entirely. We first observed CET in an uncontrolled deployment test, where a GPT-4o banking agent fabricated Python-style exception traces (complete with memory addresses) to feign a system failure when threatened by a user. In subsequent controlled experiments, the model independently invented audit restrictions, microservice architectures, error codes, and service timeouts, none present in its prompt. Reproduction attempts across pressure levels and attacker personas yielded CEF consistently but with substantial variation in form, onset, and severity: the phenomenon is robust but stochastic. Critically, injecting ground-truth data mid-conversation did not restore honest behaviour once fabrication had taken hold (the model ignored correct information and continued confabulating) suggesting CEF is self-reinforcing rather than a knowledge gap. We show that (1) standard enterprise guardrails routinely create CEF-enabling conditions in production, (2) current RLHF procedures suppress but cannot eliminate CEF, and (3) existing safety benchmarks do not test for this failure mode. Our results highlight the need for irreconcilable-constraint benchmarks, CEF-aware training procedures, and deployment-time detection methods before constrained agents become further entrenched in high-stakes domains.

10.
arXiv (CS.AI) 2026-06-25

Tracking Large-scale Shared Bikes with Inertial Motion Learning in GNSS Blocked Environments

arXiv:2605.07412v2 Announce Type: replace-cross Abstract: Although Global Navigation Satellite Systems (GNSS) provide a general solution for bike tracking outdoors, there still exist complex riding environments where only inertial navigation systems work, such as urban canyons. Despite decades of research, localization using only low-cost inertial sensors still faces challenges such as cumulative drifts and poor robustness caused by filtering methods. Furthermore, sensors such as visual and LiDAR could provide reliable measurements, but they are not suitable for large-scale deployment. In this paper, we propose an inertial tracking framework that integrates bicycle mechanical constraints with a mixture-of-experts model. Specifically, we leverage multiple expert modules to capture shared representations and weight them through the gating mechanism, thus improving multi-task learning performance and enabling uncertainty-aware trajectory estimation. Furthermore, based on the mechanical transmission between the pedal and the rear wheel of a bike, we explore the intrinsic relationship between the rider's periodic pedalling behaviors and acceleration variations, and convert such patterns into bike's wheel speed for dynamic calibration. Experiments with real-world riding data from shared bikes of the DiDi ride-hailing platform demonstrate that our system improves the accuracy of baselines by at least 12%, with wheel speed errors below 0.5 m/s at 95-percentile.

11.
arXiv (math.PR) 2026-06-17

Persistence diagrams of random triangular matrices over finite fields

arXiv:2606.17895v1 Announce Type: cross Abstract: Let us consider a random infinite lower triangular matrix, where the entries on and below the diagonal are i.i.d. uniform random elements of a fixed finite field. We investigate the evolution of the span of the first $n$ rows of this matrix as $n$ grows. Many properties of this evolving subspace can be captured with the help of the verbose persistence diagram, which is a standard tool in stochastic topology and topological data analysis. We give an explicit formula for the distribution of the persistence diagram. We prove a law of large numbers for the distribution of lifetimes. We also describe the fluctuations of the persistent Betti numbers.

12.
medRxiv (Medicine) 2026-06-15

Specialty Choice Attitudes Among Medical Interns: Evidence from Hormozgan University of Medical Sciences

Background: Choosing a medical specialty is a critical career decision that affects both physicians future professional lives and the composition of the healthcare workforce. Specialty preferences are shaped by multiple personal, educational, and socioeconomic factors, yet evidence from senior medical students in southern Iran remains limited. This study aimed to assess willingness to pursue specialty training among medical interns at Hormozgan University of Medical Sciences, identify their preferred specialties, and examine factors associated with their decisions. Methods: This descriptive-analytical cross-sectional study was conducted in 2023 among medical interns at Hormozgan University of Medical Sciences in Bandar Abbas, Iran. Using a convenience census approach, all eligible interns were invited to participate, and 83 students completed an online questionnaire. The instrument collected demographic, academic, and occupational data, as well as reasons for willingness or unwillingness to pursue specialty training and specialty preferences. Content and face validity were assessed by faculty members and students, and internal consistency reliability in the present study was acceptable (Cronbach alpha = 0.82). Data were analyzed using descriptive statistics and logistic regression in SPSS version 27. Results: Of the 83 participants, 50 (60.2%) reported willingness to pursue specialty training, while 33 (39.8%) did not. Among students willing to continue, the most frequently cited reasons were achieving a better economic position, broader job opportunities, and higher social status. Among those unwilling to continue, the most common reasons were fatigue from prolonged studying, financial problems, and the desire to start working after graduation. Radiology was the most common first-choice specialty, followed by otorhinolaryngology, dermatology, and cardiology. In regression analyses, no demographic or academic variable remained independently associated with willingness to pursue specialty training in the final multivariable model. Conclusions: A majority of medical interns were interested in pursuing specialty training, with preferences concentrated in a limited number of specialties perceived as offering favorable financial prospects, prestige, and lifestyle. Economic concerns and educational fatigue were the dominant factors influencing willingness and unwillingness to continue specialty education. These findings highlight the need for structured career counseling, broader exposure to different specialties, and policy measures to address financial and structural barriers to residency training. Keywords: medical specialty choice; medical interns; residency training; medical education; Hormozgan university of medical sciences

13.
arXiv (quant-ph) 2026-06-11

Circulators Based on Coupled Quantum Anomalous Hall Insulators and Resonators

arXiv:2505.07770v2 Announce Type: replace Abstract: Integrated plasmonics is advancing rapidly, enabling a wide range of functionalities to be incorporated onto a single chip. Applications span information processing, computation, quantum sensing, and dark-matter detection. This progress has driven the development of integrated non-reciprocal devices, which are essential for preventing unwanted feedback that can degrade system performance. While non-reciprocal devices have been realized in edge magnetoplasmon materials via classical interference effects, their operation is often limited by the input power range. Here, we demonstrate that topological circulators utilizing asymmetric coupling offer improved input power range, isolation, and insertion loss. In this configuration, we demonstrate the coupling between a chiral edge magnetoplasmonic resonator and a pair of LC resonators is well described by an effective non-Hermitian two-site Hatano-Nelson model with asymmetric directional couplings, resulting in nonreciprocal behavior. The coherent photon-plasmon interaction enables a circulator with up to 50 dB of isolation across a broad range of excitation power. These results suggest that magnetic topological insulators provide a promising platform for realizing asymmetric non-Hermitian couplings at radio frequencies and for exploring regimes of strong directional suppression and possible exceptional-point physics. More broadly, they highlight the potential of topological-material-based microwave devices for future integration with superconducting quantum information platforms.

14.
arXiv (CS.LG) 2026-06-17

Informative Missingness to Generate Irregular Clinical Time Series

arXiv:2606.17106v1 Announce Type: new Abstract: Laboratory tests in electronic health records are collected irregularly, and the absence of a test order can be as informative as the measurement itself. Such missingness reflects clinicians' decisions and patient physiology, making it important to model it directly rather than treat it as a preprocessing artifact. Here we present a diffusion-based approach for generating clinical time series that jointly models laboratory values and their observation patterns using the public Data Analytics Challenge on Missing Data Imputation (DACMI) benchmark derived from MIMIC-III. To preserve realistic sampling, we align chart times into 4-hour intervals and segment admissions into 7-day windows, producing trajectories that pair each lab value with a corresponding observation indicator. Standard transformations and normalization are applied to stabilize training. Our method extends the TimeDiff framework to learn continuous lab values and discrete missingness patterns through complementary diffusion objectives. Experiments show that the generated data closely match real patient trajectories across individual lab distributions and joint value-missingness embeddings, demonstrating that diffusion models can capture clinically meaningful dependencies between patient physiology and clinicians' testing behavior under MNAR-like (missing-not-at-random) missingness. These preliminary results indicate that our model can serve as an initial component toward developing clinical foundation models. By producing synthetic priors that preserve key physiology-missingness relationships, this work motivates the subsequent training of Prior-Data Fitted Networks capable of leveraging informative missingness, which we will investigate in the extended work.

15.
arXiv (CS.AI) 2026-06-16

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

arXiv:2606.01365v2 Announce Type: replace Abstract: Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework for a three-agent architecture – orchestrator, search agent, and execution agent – that converts structured events into online signals for loops, budget pressure, low information gain, and tool instability, then adds offline semantic grounding metrics and selective LLM-as-judge evaluation. On 165 GAIA validation traces under identical caps, 98 runs produce usable final answers and 67 fail or stop without one. Among warned failed runs, 58.1% of tokens are spent after the first warning on average, indicating substantial opportunity for intervention. A 10-task Level-2 pilot uses warnings to diversify search or require evidence, reducing post-warning token fraction from 0.638 in the baseline to 0.304. The results support a layered design: cheap online signals help the orchestrator redirect or halt redundant behavior, while deeper semantic checks identify whether completed answers are grounded enough to trust.

16.
arXiv (quant-ph) 2026-06-25

Routing Codes: High-Rate Quantum LDPC Codes with Short, Parallel Non-Local Connectivity

arXiv:2606.25330v1 Announce Type: new Abstract: Quantum low-density parity-check (qLDPC) codes are promising candidates for realizing large-scale fault-tolerant quantum computing. Although many codes with favorable theoretical parameters have been developed, their practical adoption must take hardware implementability into account. For mainstream quantum platforms such as superconductors and neutral atoms, the connectivity, the length of non-local couplings, and the complexity of wiring or atom rearrangement are key factors that dictate the difficulty of hardware realization. Here, we propose a new family of qLDPC codes, termed routing codes. Within this family, we find explicit instances whose encoding rates are comparable to those of bivariate bicycle (BB) codes, while systematically reducing qubit connectivity, shortening the length of non-local couplings, and, crucially, making all non-local couplings mutually parallel. This parallelism fundamentally eliminates wiring crossings in superconducting multi-layer architectures and drastically simplifies the scheduling of atom movement in neutral-atom arrays. Under circuit-level simulation, the weight-7 routing codes reduce the physical qubit overhead by approximately a factor of 8, compared to surface codes achieving a same logical error rate. These results establish routing codes as a hardware-centric qLDPC family that bridges the gap between theoretical optimality and near-term physical feasibility.

18.
arXiv (CS.AI) 2026-06-24

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

arXiv:2606.24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.

19.
arXiv (CS.LG) 2026-06-11

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

arXiv:2606.11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution. Upon detection, a conformal abstention layer adapts decision thresholds to recover a target error rate epsilon=0.1. In a pre-registered factorial evaluation (4 classifiers x 5 shift conditions x 20 seeds x 2 window sizes, 800 cells), the system achieves 86.6% valid detection (693/800, 95% CI [84.1%, 88.8%]) with mean latency of 39.5 steps. Detection holds across three ground-truth regimes: synthetic onset (86.6%), real temporal jailbreaks (85%, 17/20), and GCG adversarial attacks. Weighted conformal prediction recovers up to 39 pp of lost coverage for DeBERTa (ESS=46/300) but collapses for all other classifiers (ESS~300): logistic density ratio estimation achieves perfect source/target separability in high-dimensional embedding spaces, clipping all importance weights to the floor. DeBERTa shows a gradient from effective correction (paraphrase, ESS=46) to near-total collapse (adversarial suffix, ESS=206). PCA to 32 dimensions breaks the collapse, recovering 33 pp for Llama Guard and 21 pp for ShieldGemma. Variance decomposition reveals classifier (eta^2=0.243), shift type (eta^2=0.237), and their interaction (eta^2=0.185) all contribute substantially to detection latency variance (all p

20.
arXiv (CS.AI) 2026-06-17

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning

arXiv:2605.05172v2 Announce Type: replace-cross Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been collected. Existing offline-to-online learning methods often cause policies to replace previously learned good actions due to a distribution mismatch between offline data and online learning. In this work, we propose Q2RL, Q-Estimation and Q-Gating from BC for Reinforcement Learning, an algorithm for efficient offline-to-online learning. Our method consists of two parts: (1) Q-Estimation extracts a Q-function from a BC policy using a few interaction steps with the environment, followed by online RL with (2) Q-Gating, which switches between BC and RL policy actions based on their respective Q-values to collect samples for RL policy training. Across manipulation tasks from D4RL and robomimic benchmarks, Q2RL outperforms SOTA offline-to-online learning baselines on success rate and time to convergence. Q2RL is efficient enough to be applied in an on-robot RL setting, learning robust policies for contact-rich and high precision manipulation tasks such as pipe assembly and kitting, in 1-2 hours of online interaction, achieving success rates of up to 100% and up to 3.75x improvement against the original BC policy. Code and video are available at https://pages.rai-inst.com/q2rl_website/

21.
arXiv (CS.AI) 2026-06-16

Deep Q-Learning on Hölder Spaces

作者:

arXiv:2606.16846v1 Announce Type: cross Abstract: We study the operator-theoretic core of Q-learning in continuous-time stochastic control with continuous states and actions. In value-based reinforcement learning, each Q-learning or DQN update is built from a Bellman optimality target; our analysis isolates this target in a diffusion setting and studies its regularity and approximation complexity. Under uniform ellipticity and Hölder-regular coefficients, we show that a Bellman update maps bounded inputs into an anisotropic regularity class, smoothing the state variable while leaving only Lipschitz dependence on the action variable. This yields a compact family of Bellman iterates and motivates a tensor-product DeepONet architecture adapted to the mixed regularity of the problem. We then derive explicit approximation and resource bounds, together with a stiffness–complexity trade-off as the time step $\delta \to 0$. The resulting theory makes a direct contribution to Q-learning theory at the level of Bellman target regularity and approximation in continuous stochastic control. At the same time, we do not claim a full convergence theorem for practical sampled Q-learning with exploration, replay, and stochastic gradient updates.

22.
arXiv (CS.AI) 2026-06-17

Enhanced Evolutionary Multi-Objective Deep Reinforcement Learning for Reliable and Efficient Wireless Rechargeable Sensor Networks

arXiv:2510.21127v2 Announce Type: replace-cross Abstract: Despite rapid advancements in sensor networks, conventional battery-powered sensor networks suffer from limited operational lifespans and frequent maintenance requirements that severely constrain their deployment in remote and inaccessible environments. As such, wireless rechargeable sensor networks (WRSNs) with mobile charging capabilities offer a promising solution to extend network lifetime. However, WRSNs face critical challenges from the inherent trade-off between maximizing the node survival rates and maximizing charging energy efficiency under dynamic operational conditions. In this paper, we investigate a typical scenario where mobile chargers move and charge the sensor, thereby maintaining the network connectivity while minimizing the energy waste. Specifically, we formulate a multi-objective optimization problem that simultaneously maximizes the network node survival rate and mobile charger energy usage efficiency across multiple time slots, which presents NP-hard computational complexity with long-term temporal dependencies that make traditional optimization approaches ineffective. To address these challenges, we propose an enhanced evolutionary multi-objective deep reinforcement learning algorithm, which integrates a long short-term memory (LSTM)-based policy network for temporal pattern recognition, a multilayer perceptron-based prospective increment model for future state prediction, and a time-varying Pareto policy evaluation method for dynamic preference adaptation. Extensive simulation results demonstrate that the proposed algorithm significantly outperforms existing approaches in balancing node survival rate and energy efficiency while generating diverse Pareto-optimal solutions. Moreover, the LSTM-enhanced policy network converges 25% faster than conventional networks, with the time-varying evaluation method effectively adapting to dynamic conditions.

23.
arXiv (CS.AI) 2026-06-15

A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health

arXiv:2606.14604v1 Announce Type: cross Abstract: Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60\%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

24.
arXiv (CS.AI) 2026-06-18

Hardware- and Vision-in-the-Loop Validation of Deep Monocular Pose Estimation for Autonomous Maritime UAV Flight

arXiv:2606.19176v1 Announce Type: cross Abstract: Autonomous UAV operations on ships require reliable vision-based relative pose estimation, yet at-sea validation is costly, weather-dependent, and risky. This paper presents a hardware-validated vision-in-the-loop framework that enables fully autonomous indoor flight while emulating photorealistic maritime environments. Rendered maritime views are processed onboard by a deep transformer-based monocular pose estimator. Delayed vision measurements are fused with high-rate IMU data using a delayed Kalman filter to provide consistent state estimates for geometric control. The system captures critical embedded effects, including perception latency, asynchronous updates, and computational constraints, that are absent in pure simulation. Autonomous takeoff, trajectory tracking, and landing experiments demonstrate stable closed-loop flight. The results establish a safe and hardware-realistic intermediate stage for developing maritime UAV autonomy prior to shipboard deployment.

25.
arXiv (CS.CL) 2026-06-15

Sub-Token Routing for KV Cache Compression

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached tokens, or by reducing the visual-token sequence before language-model inference. We introduce sub-token routing, a KV-compression method that adds a finer control axis inside retained tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after token-level reduction. First, a token-reduction method determines which tokens are retained. Then, sub-token routing compresses the value states inside those retained tokens. Experiments under matched KV budgets show that adding sub-token routing improves token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further token removal becomes costly. Overall, token-level reduction and sub-token routing provide complementary ways to reduce KV cost.