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。

01.
medRxiv (Medicine) 2026-06-22

MinderCare: protocol for a mixed-methods evaluation of a digitally enabled dementia care service.

Introduction and aims Dementia is a growing public health challenge affecting millions of people worldwide. It is a progressive condition that increases the risk of infections, falls, hospital admissions, dependence in activities of daily living, safety issues such as wandering, care home transfers, and death. New ways of supporting people living with dementia (PLWD) at home are urgently needed. We describe the MinderCare study which evaluates a digitally enabled care model that integrates low-burden sensor-based remote monitoring within a nurse-led clinical service. Methods and analysis In this mixed-methods study, we will recruit 100 people with confirmed or suspected dementia living at home and deploy the Minder remote monitoring system for at least 12 months. A detailed characterisation of the cohort will be obtained, including cognition, frailty, participant and carer wellbeing, functioning, and quality of life. The feasibility, acceptability, sustainability, and resource requirements of the service will also be assessed. Low-cost sensors provide information about behaviour, environment and physiology from the home. Machine-learning algorithms have been used to develop digital biomarkers of infection, sleep, night-time behaviours, daily activities and routines, and the effects of clinical events and treatment. These will be assessed through clinical reports of sensor-derived data that include anomaly alerts provided to the clinical teams. Algorithms will be assessed for their clinical utility and acceptability. The comparative-effectiveness component will be designed as a target trial emulation using linked electronic health-record data to construct a time-indexed external usual-care control cohort. The primary comparative outcome will be Days Alive and Out of Hospital (DAOH) over 12 months from the activation-index date, with healthcare utilisation, costs, institutionalisation and mortality assessed as secondary outcomes. DAOH and estimated MinderCare effects will also be examined across prespecified strata of baseline inpatient utilisation. Ethics and dissemination Ethical approval has been granted by the North East Newcastle and North Tyneside 2 Research Ethics Committee, and the study has received confirmation of capacity and capability by the Imperial College Healthcare NHS Trust. Study findings will be disseminated to patients, health and social care professionals, and policymakers through peer-reviewed publications and conference presentations. Study registration number: ISRCTN14997677 and NIHR portfolio CPMSID 63023.

02.
arXiv (quant-ph) 2026-06-24

Quantum Correlations of Neutrinos in the Kerr-Newman Space-time

arXiv:2605.10424v2 Announce Type: replace-cross Abstract: Quantum phases provide a connection between gravitation and quantum information, which proposes a novel avenue to explore the properties of space-time. In this paper, we investigate the quantum correlations (QCs) of neutrinos in the Kerr–Newman space-time. Both radial and non-radial propagations are considered under the weak-field approximation. The results show that, for inward propagations, the oscillation probabilities and QCs differ significantly from those obtained in the Schwarzschild metric. In the case of radial outward propagation, the larger angular momentum $a$ increases the oscillation period of the survival probability $P_{ee}$, entanglement, and monogamy of nonlocality, whereas the larger charge $Q$ decreases the corresponding periods. For non-radial propagations, $M$ and $a$ can noticeably modulate the amplitudes of the considered QCs, which is not observed in the case of radial propagations. Furthermore, we find that, despite differences in their variation ranges, entanglement and coherence exhibit highly consistent oscillation behaviors in both radial and non-radial propagation cases. These findings provide a comprehensive understanding for the neutrinos-based relativistic quantum information.

03.
arXiv (CS.CV) 2026-06-16

MotionVLA: Vision-Language-Action Model for Humanoid Motion

Generating realistic humanoid motion from scene images and text involves both low-frequency pose semantics and high-frequency physical dynamics. However, many existing methods tokenize motion with a single shared codebook, forcing heterogeneous motion signals into the same quantization space. Our frequency-domain analysis of human motion data reveals a clear mismatch between single-codebook quantization and motion statistics: five DCT coefficients capture 93% of joint-position energy but only 37% of joint-velocity energy, which can bias quantization toward pose statistics and under-represent high-frequency velocity components. A second challenge lies in adapting a standard autoregressive model to effectively model high-frequency physical signals in motion sequences. Therefore, we propose DSFT, a dual-stream frequency tokenizer that separates motion into Base and physical streams and compresses them independently with DCT truncation and BPE. Furthermore, we present MotionVLA, a Qwen3.5-based model that arranges Base and physical tokens in a unified sequence, where Phys tokens are predicted after Base tokens. Experiments on HumanML3D and MBench show that, despite using a lightweight 2B backbone, MotionVLA reduces the Diversity gap to real data by over 50% on HumanML3D and improves Motion-Condition Consistency by 3.8% on MBench, supporting frequency-aware dual-stream decoupling as an effective formulation for autoregressive motion generation. Code: https://github.com/AIGeeksGroup/MotionVLA. Website: https://aigeeksgroup.github.io/MotionVLA.

04.
arXiv (CS.CV) 2026-06-16

Navigating Distribution Shifts in Medical Image Analysis: A Survey

Medical Image Analysis (MedIA) has become indispensable in modern healthcare, enhancing clinical diagnostics and personalized treatment. Despite the remarkable advancements supported by deep learning (DL) technologies, their practical deployment faces challenges posed by distribution shifts, where models trained on specific datasets underperform on others from varying hospitals, or patient populations. To address this issue, researchers have been actively developing strategies to increase the adaptability of DL models, enabling their effective use in unfamiliar environments. This paper systematically reviews approaches that apply DL techniques to MedIA systems affected by distribution shifts. Rather than organizing existing methods by technical characteristics, we explicitly bridge real-world clinical constraints – such as limited data accessibility, strict privacy requirements, and heterogeneous collaboration protocols – with the technical paradigms able to address them. By establishing this connection between operational constraints and methodological evolution, we categorize existing works into Joint Training, Federated Learning, Fine-tuning, and Domain Generalization, each aligned with specific healthcare scenarios. Beyond this taxonomy, our empirical analysis suggests that, as domain information becomes progressively less accessible across these paradigms, performance improvements become increasingly constrained, and further uncovers a gradual shift in methodological focus from explicit distribution alignment toward uncertainty-aware modeling, ultimately pointing to the need for more deployability-aware design in real-world MedIA.

05.
arXiv (CS.AI) 2026-06-19

Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts

arXiv:2402.14035v4 Announce Type: replace-cross Abstract: Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experiments, distilling from a 76M-parameter language model to a 2M-parameter recommender closes less than 40% of the performance gap between the undistilled student and the teacher. We show that introducing domain-specific experts – which share the student's architectural characteristics – alongside the foundation model as a diverse teacher committee significantly improves transfer. However, standard multi-teacher methods fail to exploit this diversity: naively combining heterogeneous teachers can degrade performance below single-teacher distillation. To address this, we propose DiverseDistill, an interactive distillation framework that employs a learnable Question-Answer mechanism to generate teacher-conditioned queries and align heterogeneous teacher outputs into the student's representation space. Unlike methods requiring gradient-based co-optimization or architectural modification of teachers, DiverseDistill operates with frozen teachers using only forward-pass inference through their intermediate layers: no parameter updates, no co-training, and no architectural surgery. A dynamic teacher importance mechanism further reduces training cost by filtering low-relevance teachers per sample (e.g., ~30% fewer forward passes with no quality loss for recommendation tasks), while the entire Distillation Module is discarded after training, adding zero inference overhead. Evaluations on recommendation (38x compression) and vision (3.6x compression) tasks demonstrate that DiverseDistill recovers 73-114% of the teacher-student performance gap, consistently outperforming all single- and multi-teacher baselines.

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

Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random

arXiv:2606.20206v1 Announce Type: cross Abstract: In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values. This issue arises in practical settings, including health care and marketing. We investigate off-policy evaluation (OPE) in finite-horizon Markov decision processes when rewards are missing not at random (MNAR), which breaks ignorability and induces selection bias even after conditioning on states and actions. To address this, we formalize a reward-dependent propensity model and use future states as shadow variables to identify the full-data conditional mean reward. We further introduce a bridge function that recovers the conditional mean reward without explicitly modeling the MNAR mechanism, and estimate it via a min-max procedure to avoid double sampling. Building upon these identification results, we propose an Fitted-Q-Evaluation-style estimator that propagates the recovered rewards while allowing target policies to depend on past missingness indicators. Finally, we establish consistency and finite-sample error bounds for our OPE estimator, and show through experiments the strong performance of our method compared to existing methods on simulated and MIMIC-III Sepsis data.

07.
arXiv (CS.CL) 2026-06-12

Detecting Functional Memorization in Code Language Models

Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be recoverable from model outputs, by auditing the textual overlap between training examples and model generations. Code, however, can be functionally equivalent while textually dissimilar. In this work, we study functional memorization: extraction of functional logic beyond what verbatim metrics detect. We construct a counterfactual setup for Olmo-3-32B, comparing a midtrained model (exposed to target code) against a pretrained reference (not exposed). We prompt both models with Python function signatures and measure both textual and functional similarity (i.e., LLM-as-a-judge, execution-based). Our results show clear evidence of functional memorization, highlighting the need for auditing metrics that go beyond textual overlap.

08.
arXiv (CS.CV) 2026-06-18

Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series

The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and operation at global scale. While Earth Observation based offshore wind infrastructure mapping has matured for spatial localization, existing open datasets lack temporally dense and semantically fine-grained information on construction and operational dynamics. We introduce a global Sentinel-1 synthetic aperture radar (SAR) time series data corpus that resolves deployment and operational phases of offshore wind infrastructure from 2016Q1 to 2025Q1. Building on an updated object detection workflow, we compile 15,606 time series at detected infrastructure locations, with overall 14,840,637 events as analysis-ready 1D SAR backscatter profiles, one profile per Sentinel-1 acquisition and location. To enable direct use and benchmarking, we release (i) the analysis ready 1D SAR profiles, (ii) event-level baseline semantic labels generated by a rule-based classifier, and (iii) an expert-annotated benchmark dataset of 553 time series with 328,657 event labels. The baseline classifier achieves a macro F1 score of 0.84 in event-wise evaluation and an area under the collapsed edit similarity-quality threshold curve (AUC) of 0.785, indicating temporal coherence. We demonstrate that the resulting corpus supports global-scale analyses of deployment dynamics, the identification of differences in regional deployment patterns, vessel interactions, and operational events, and provides a reference for developing and comparing time series classification methods for offshore wind infrastructure monitoring.

09.
arXiv (CS.CL) 2026-06-24

A Synthetic Reliability-Aware PINN Benchmark for Offshore Wind Turbine Support-Structure Monitoring with Bayesian Inverse Identification

Reliable structural health monitoring (SHM) of offshore wind turbine (OWT) support structures requires fast state estimation from sparse measurements. Repeated high fidelity finite element or aeroelastic analyses are difficult to use directly in online monitoring loops, while purely data-driven surrogates can require large training sets. This paper presents Digi Turbine, a synthetic reliability-aware Physics Informed Neural Network (PINN) benchmark for OWT monopile support structure monitoring. The workflow embeds a simplified Euler Bernoulli beam equation with Winkler soil foundation in the training objective, couples it with Bayesian-prior-informed inverse identification, and adds First Order Reliability Method (FORM) screening. All validation uses synthetic configurations with analytical or finite-difference ground truth motivated by the NREL 5MW reference turbine context.

10.
arXiv (math.PR) 2026-06-19

An alternative approach to well-posedness of McKean-Vlasov equations arising in Consensus-Based Optimization

arXiv:2512.19446v4 Announce Type: replace-cross Abstract: In this work we study the mean-field description of Consensus-Based Optimization (CBO), a derivative-free particle optimization method. Such a description is provided by a non-local SDE of McKean-Vlasov type, whose fields lack of global Lipschitz continuity. We propose a novel approach to prove the well-posedness of the mean-field CBO equation based on a truncation argument. The latter is performed through the introduction of a cut-off function, defined on the space of probability measures, acting on the fields. This procedure allows us to study the well-posedness problem in the classical framework of Sznitman. Through this argument, we recover the established result on the existence of strong solutions, and we extend the class of solutions for which pathwise uniqueness holds.

11.
medRxiv (Medicine) 2026-06-12

Crimean-Congo haemorrhagic fever virus transmission: exploring perceptions of human-animal-tick interactions across six districts in Uganda

Crimean-Congo haemorrhagic fever virus (CCHFV) causes a viral zoonotic disease transmitted through tick bites and direct contact with infected blood or tissue of infected animals. Socio-ecological and behavioural risk factors for CCHFV exposure in Uganda remain poorly understood, which can lead to the omission of key risk factors in quantitative survey design and limit our wider understanding. In this study, we explored human-animal-tick interaction transmission risks in Uganda. We conducted 24 focus group discussions (FGDs) and 31 key-informant interviews (KIIs) across six environmentally and socio-ecologically diverse districts, between October 2023 and March 2024. Study sites were selected using K-prototype analysis, which combined environmental and socio-ecological variables to identify distinct clusters within Uganda. FGDs were conducted separately with groups of community leaders, men, women and teenagers with stratified purposive sampling. Medical doctors, veterinarians, traditional healers, district surveillance officers, and herdsmen were individually interviewed as key informants and purposively sampled. Data were transcribed and translated into English, and analysed thematically using iterative categorisation in NVivo 14. Most participants reported tick bites, some as frequently as every day. Close contact with animals was common, including sleeping next to them in the same building, largely due to concerns about animal theft. Less frequent but notable practices included slaughtering animals for consumption or sacrifice and interactions with wild animals during hunting. Slaughtering and butchering an animal which was sick or had died was reportedly performed by participants in most districts. Plucking and roasting engorged ticks was a practice described in the Kaabong and Arua districts of Northern Uganda. These practices and behaviours highlight potential key risks of CCHFV transmission and underscore the need for future studies to address specific behaviours, to quantify if, and to what extent, they present an exposure risk. Further work should include underlying reasons for the behaviours, which would help ensure that culturally appropriate interventions are targeted.

12.
arXiv (CS.AI) 2026-06-16

Discovering Lattice Reduction Strategies via Self-Play

arXiv:2606.15301v1 Announce Type: cross Abstract: The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen moduli and higher dimensions up to $n=32$ without retraining.

13.
arXiv (CS.LG) 2026-06-19

Phase Transition for Stochastic Block Model with more than $\sqrt{n}$ Communities

arXiv:2509.15822v3 Announce Type: replace-cross Abstract: Predictions from statistical physics postulate that recovery of the communities in the Stochastic Block Model (SBM) with a fixed number $K$ of communities is possible in polynomial time above, and only above, the Kesten-Stigum (KS) threshold. This conjecture has given rise to a rich literature, proving that non-trivial community recovery is indeed possible in SBM above the KS threshold. Failure of low-degree polynomials (LDP) below the KS threshold was also proven, as long as $K\ll \sqrt{n}$, where $n$ is the number of nodes in the observed graph. When $K\geq \sqrt{n}$, Chin et al.(2025) recently proved that, in a sparse regime, community recovery in polynomial time is possible below the KS threshold by counting non-backtracking paths. This breakthrough led them to postulate a new threshold for the many-communities regime $K\geq \sqrt{n}$. In this work, we provide evidence supporting their conjecture:\\ 1- We prove that, for any graph density, LDP fail to recover communities below the threshold postulated by Chin et al.(2025) ;\\ 2- We prove that community recovery is possible in polynomial time above the postulated threshold, not only in the sparse regime considered in Chin et al.~(2025), but also in moderately sparse regimes, by counting occurrences of some specific motifs inspired by the LDP analysis.\\ In particular, counting self-avoiding paths of length $\log(n)$, which is closely related to spectral algorithms based on the Non-Backtracking operator, is optimal only in the sparse regime. More complex motifs based on the blow-up of a cycle must be considered in denser regimes.

15.
arXiv (CS.CV) 2026-06-24

MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving

Recovering realistic 3D vehicle models from autonomous driving scenes is crucial for synthesizing training data and building simulation environment. However, most existing vehicle generation methods fail to fully exploit multimodal sensors i.e. multi-view images and LiDAR point clouds) and rely on neural rendering based reconstruction, leading to low-quality mesh. Recently, native 3D generative models have made significant progress, yet they are not built for arbitrary multi-view inputs and often struggle with in-the-wild driving images. In this work, we present MM-TRELLIS, a multi-modal version of TRELLIS for in-the-wild 3D vehicle generation that integrates LiDAR and image sensors from autonomous driving datasets into native 3D generative models. Specifically, multi-view images are cycled as conditioning inputs, while LiDAR point clouds provide test-time guidance to ensure geometric accuracy and cross-view consistency. During denoising, we first align the guidance point cloud with the model priors, then enforce consistency between the generated geometry and the guidance point cloud. Finally, we introduce a voxel filtering strategy based on the opacity of 3D Gaussian Splatting to suppress floaters and produce clean meshes. Comprehensive experiments on Waymo dataset demonstrate our method outperforms existing methods in high-fidelity 3D vehicle generation. Code is available at https://github.com/HongliXiao/MM-TRELLIS.

16.
Nature (Science) 2026-06-24

Ductile alloys offering 100 MPa tensile strength at 2,400 °C

作者:

Extreme applications call for materials that are not only strong to withstand thermomechanical loads at temperatures in excess of 2,000 °C (refs. 1–3), but also highly formable at room temperature to allow for processing into complex-shaped parts. The latter excludes brittle ceramics4 and intermetallic compounds5, limiting the selection to highly ductile metals and their alloys, but for them, an adequate strength at ultrahigh temperatures seems unreachable. Here we show a breakthrough in casting alloys that achieve both simultaneously. A boron-stabilized HfO2-strengthened Ta-based alloy was carefully crafted using a new boron-intervened in situ oxidation reaction, producing about 50-nm diameter oxide particles dispersed densely and uniformly in the grain interior. The new alloy fills the blank at ultrahigh temperatures in terms of tensile yield strength, around 200 MPa at 2,000 °C and 100 MPa at 2,400 °C, while simultaneously possessing an excellent strength–ductility balance at room temperature (ultimate tensile strength >800 MPa, elongation-to-failure of about 35%), a property combination surpassing all previous refractory (including multi-principal-element) alloys. Moreover, the boron segregation around the oxide nanoparticles imparts excellent thermal stability against coarsening at 2,000–2,400 °C. Our strategy thus goes beyond traditional oxide-dispersion strengthening to enable highly ductile refractory alloys that are capable of load-bearing applications at extreme temperatures. A boron-stabilized oxide-strengthened tantalum alloy combines exceptional room-temperature ductility with record ultrahigh-temperature strength, enabling load-bearing applications above 2,000 °C.

17.
arXiv (CS.CL) 2026-06-25

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining

Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.94 by step 925). By step 3,500 the same model scores near zero on the same probes, although the rule's evidence is still in the training data. We call this within-run reversal natural ungrokking: the corpus decides, with no trace in the loss curve, which learned rules a model keeps. Which rules survive is predictable from one corpus statistic: how often the training stream shows the rule winning. Across un-intervened runs (two corpora, three budgets, three seeds), support frequency decides a rule's fate; the data-to-parameter ratio only modulates how deeply a doomed rule falls. The same emerge-then-collapse dynamics appear in public Pythia checkpoints, collapse depth ordered by model scale as predicted. The forgetting is a displacement: a competing surface pattern out-competes the rule, and the log-probability margin between them crosses zero within 100 training steps of the behavioral collapse. Control over this fate is asymmetric: the same edit that destroys a rule on demand cannot restore it. Flipping support to counter-evidence in place kills the rule with monotone dose-response in two unrelated rules; but injecting support back, even to 450 times the level that naturally sustains it, buys no recovery. Every confirmatory threshold and prediction was pre-registered before the data it governed was read.

18.
arXiv (CS.AI) 2026-06-16

MemPO: Self-Memory Policy Optimization for Long-Horizon Agents

arXiv:2603.00680v4 Announce Type: replace Abstract: Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model itself from proactively managing its memory content and aligning with the agent's overarching task objectives. To address these limitations, we propose the self-memory policy optimization algorithm (MemPO), which enables the agent (policy model) to autonomously summarize and manage their memory during interaction with environment. By improving the credit assignment mechanism based on memory effectiveness, the policy model can selectively retain crucial information, significantly reducing token consumption while preserving task performance. Extensive experiments and analyses confirm that MemPO achieves absolute F1 score gains of 25.98 over the base model and 7.1 over the previous SOTA baseline, while reducing token usage by 67.58% and 73.12%. The code is released at https://github.com/TheNewBeeKing/MemPO.

19.
arXiv (CS.CV) 2026-06-17

Effective Gaussian Management for High-fidelity Object Reconstruction

This paper proposes an effective Gaussian management framework for high-fidelity scene reconstruction of both appearance and geometry. Unlike recent Gaussian Splatting (GS) pipelines that treat all primitives uniformly during optimization, our framework explicitly manages the attribute activation, representation and pruning of Gaussian. Specifically, our framework first introduces GauSep, a novel densification strategy that selectively activates Gaussian color or normal attributes to alleviate destructive gradient conflicts arising from dual supervision. We further propose GauRep, an adaptive Gaussian representation that dynamically adjusts spherical harmonics (SHs) orders and performs task-decoupled pruning to reduce redundancy at both the individual and global levels. To provide reliable geometric supervision for above mangement process, we additionally introduce CoRe, an regularized surface reconstruction module that distills robust normal fields from an SDF branch to the Gaussian representation through a confidence mechanism. Notably, the proposed Gaussian management is compatible with various reconstruction architectures and can be seamlessly integrated to improve performance while reducing size of the model. Extensive experiments demonstrate that our approach achieves superior or comparable performance in appearance and geometry reconstruction compared with state-of-the-art methods, while using significantly fewer parameters.

20.
arXiv (CS.LG) 2026-06-11

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

21.
arXiv (math.PR) 2026-06-11

On the spatio-temporal increments of nonlinear parabolic SPDEs and the open KPZ equation

arXiv:2508.05032v3 Announce Type: replace Abstract: We study spatio-temporal increments of the solutions to nonlinear parabolic SPDEs on a bounded interval with Dirichlet, Neumann, or Robin boundary conditions. We identify the exact local and uniform spatio-temporal moduli of continuity for the sample functions of the solutions. These moduli of continuity results imply the existence of random points in space-time at which spatio-temporal oscillations are exceptionally large. We also establish small-ball probability estimates and Chung-type laws of the iterated logarithm for spatio-temporal increments. Our method yields extension of some of these results to the open KPZ equation on the unit interval with inhomogeneous Neumann boundary conditions. Our key ingredients include new strong local non-determinism results for linear stochastic heat equation under various types of boundary conditions, and detailed estimates for the errors in linearization of spatio-temporal increments of the solution to the nonlinear equation.

22.
arXiv (CS.CV) 2026-06-16

ReportQA: QA-Based Radiology Report Evaluation

Radiology report evaluation is essential for advancing automated report generation. Natural language generation metrics have limited clinical relevance. Clinical efficacy (CE) metrics evaluate important medical findings, but focus mainly on presence and cover only a limited set of entities. Due to heavy reliance on manual annotations, it is difficult for CE metrics to extend clinical entities or attributes. In clinical practice, radiology reports serve as a medium for information transfer. Clinicians use them to perform downstream diagnostic tasks without directly inspecting images. Based on this insight, we propose ReportQA, a clinical-related and flexible radiology report evaluation framework, supporting detailed quantitative analysis of radiology report generation systems. We first collect datasets covering multiple imaging modalities and anatomical regions. We then construct knowledge trees of clinical entities and attributes with radiologist guidance, and use large language models (LLMs) to extract structured information from raw reports. Next, we generate QA pairs from predefined templates and apply quality control through self-filtering and report-based filtering. During evaluation, the report is treated as context, and an LLM acts as a judge model to answer the QA pairs. Based on the resulting QA accuracy, we introduce QAScore metric. Compared with existing metrics, QAScore shows better alignment with radiologist judgments. Experiments on multiple state-of-the-art vision-language models reveal that current report-based inference paradigms struggle to learn fine-grained clinical representations and exhibit strong negative prior biases. In contrast, question-driven inference provides a more effective alternative. For reproducibility and extensibility, we release the knowledge trees, structured reports, and QA pairs, along with the pipeline code for QA construction and evaluation.

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

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

arXiv:2606.13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer reject a malicious contribution when the attacker controls both the code change and the accompanying PR text? We introduce SEVRA-BENCH (Social Engineering of Vulnerabilities in Review Agents), a benchmark that measures how often an automated reviewer approves such adversarial pull requests. Each malicious PR in SEVRA-BENCH is built from a real project commit that previously fixed a vulnerability listed in the Common Vulnerabilities and Exposures (CVE) database. We automatically invert that fix to restore the original vulnerable code and submit it as a pull request wrapped in one of 15 social-engineering framings, which vary the claims made, the supporting evidence, the urgency conveyed, signals of prior approval, and appeals to authority. SEVRA-BENCH contains 1,062 malicious PRs drawn from Common Vulnerabilities and Exposures (CVE)-linked fixes across the top 10 entries of the 2025 Common Weakness Enumeration (CWE) Top 25. In a realistic setting, we evaluate 8 current LLMs as code review agents on PRs that introduce vulnerabilities previously reported in public disclosures. Our results reveal a sharp gap in security capabilities between closed- and open-source models. We hope SEVRA-BENCH will serve as a valuable resource for advancing open-source models and narrowing this gap.

24.
arXiv (CS.AI) 2026-06-19

Learner-based Concept Drift Detection: Analysis and Evaluation

arXiv:2606.20216v1 Announce Type: cross Abstract: Machine learning algorithms deployed for evolving streaming environments must handle the non-stationary data distributions, commonly referred to as concept drift. The presence of concept drift poses a major challenge for many real-world applications because it can severely degrade their predictive performance, hindering their ability to support robust decision-making. Consequently, the timely and efficient detection of drift events is critical for sustaining high accuracy over time. This study examines theoretically the concept drift characteristics and numerous drift detection algorithms across several categories. Furthermore, we evaluate their performance on both synthetic and real-world datasets exhibiting diverse streaming scenarios and drift characteristics, such as abrupt and gradual changes. This study aims to enhance understanding of the complex notion of concept drift characteristics and behavior of drift detectors, along with their applicability to diverse contexts.

25.
arXiv (CS.CV) 2026-06-25

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

Despite recent successes, test-time scaling – i.e., dynamically expanding the token budget during inference as needed – remains brittle for vision-language models (VLMs). Unstructured visual reasoning chains entangle perception and reasoning, leading to long, disorganized contexts where small perceptual mistakes may cascade into completely wrong answers. Reasoning also requires expensive reinforcement learning with hand-crafted rewards. Here, we introduce SPARC (Separating Perception And Reasoning Circuits), a modular framework that explicitly decouples visual perception from reasoning. Inspired by sequential sensory-to-cognitive processing in the brain, SPARC implements a two-stage pipeline where the model first performs explicit visual search to localize question-relevant regions, then conditions its reasoning on those regions to produce the final answer. This separation enables independent test-time scaling with asymmetric compute allocation (e.g., prioritizing perceptual processing under distribution shift), and supports selective optimization (e.g., improving the perceptual stage alone when it is the bottleneck for end-to-end performance). It also accommodates compressed contexts by running global search at lower image resolutions and allocating high-resolution processing only to selected regions, thereby reducing visual token count and compute. SPARC outperforms monolithic baselines and strong visual-grounding approaches across challenging visual reasoning tasks, such as improving Qwen3VL 4B on the $V^*$ VQA benchmark by 6.7 points and surpassing "thinking with images" by 4.6 points in an OOD setting with a $200\times$ lower token budget.