探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-17 DOI: HASH:9f7530fe420eaac6c118dd7d88d486a1

Determinants of non-utilization of insecticide-treated nets among children under five in Rwanda: analyses of the 2024 Rwanda malaria indicator survey

作者:

Eduah↗K. N↗A. O↗

Background Insecticide-treated nets (ITNs) are effective for preventing malaria among children under five years, who bear a disproportionate burden of malaria. This study assessed the prevalence and determinants of ITN non-utilization among children under five in Rwanda using data from the 2024 Rwanda Malaria Indicator Survey (RMIS).Methodology This cross-sectional study utilized nationally representative data from the 2024 RMIS. Analyses were restricted to children under five residing in households that owned at least one ITN. The outcome was non-utilization of ITN, defined as not sleeping under an ITN the night preceding the survey. Survey-weighted descriptive statistics were used to estimate the prevalence of ITN non-utilization. Factors associated with non-utilization were identified using a survey-weighted Poisson regression model. Adjusted prevalence ratios (aPRs), 95% confidence intervals and p-values were reported.Results A total of 1,979 children were included in the study. The weighted prevalence of ITN non-utilization among children under five years was 20.11% (95% CI: 17.81 - 22.63). After adjusting for other factors, children aged 2 - 3 years were associated with an 83% higher prevalence of ITN non-utilization compared with those aged [&le;]1 year (aPR = 1.83, 95% CI: 1.423 - 2.352, p < 0.001). Compared with households that owned only one ITN, children in households with three or more ITNs were associated with a 76% lower prevalence of ITN non-utilization (aPR = 0.24, 95% CI: 0.171 - 0.332, p < 0.001). Children living in households with 5 - 7 members were associated with an 87% higher prevalence of ITN non-utilization compared with those in households with 1 - 4 members (aPR = 1.87, 95% CI: 1.476 - 2.358, p < 0.001).Conclusion The findings suggest that ITN utilization among children is influenced not only by household access to nets but also by household composition and dynamics that shape the allocation and use of available preventive resources.

阅读与讨论 → 访问原文 →

02.

medRxiv (Medicine) 2026-06-18 DOI: HASH:b5cd118e839127ccdd43e011db7b98a9

Web-based education on Metabolism and Obesity is associated with improved lifestyle and health behaviours among Brazilian school teachers

作者:

Evangelista-Silva↗P. H↗Coutinho↗C. P↗Martins Correia↗C. C↗Moraes↗Fernandes Ferreira↗A. F↗Medeiros Komino↗A. C↗Neves Ramos↗…

Background: Obesity is a major global public health challenge, and teachers play a critical role in school-based health promotion. This study examined the perceived impact of a web-based educational program on metabolism and obesity delivered to Brazilian school teachers. Methods: This analytical cross-sectional study included 217 teachers who responded to the evaluation questionnaire after attending the course between 2017 and 2022. Statistical analyses included logistic regression and chi-square tests. Findings: Course completion rate was 81.98%, substantially exceeding the 5-15% typical of global MOOCs. However, ethnic disparities were observed: White respondents were 4.95 times more likely to complete the course than Black respondents (p=0.00097) and Brown respondents were 3.05 times more likely (p=0.0268) than Black respondents. Among non-completers, lack of time (64.7%) was the primary barrier. Participation was concentrated in Sao Paulo (77%), with no respondents from three northern states. Perceived difficulty showed a non-significant trend (p=0.0893) where by Black respondents had the lowest predicted difficulty; the most challenging course material was Scientific Content/Reading papers (50%). Completion was strongly associated with applying learned activities in teaching (p

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-25 DOI: arXiv:2606.25278

Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation

作者:

Xiaopei Wu↗Yuenan Hou↗Junkai Xu↗Wenxiao Wang↗Binbin Lin↗Yu Li↗Ping Li↗Haifeng Liu↗Deng Cai↗Wanli Ouyang↗

Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely on auxiliary input signals or suffer from costly computational expense. To efficaciously enhance the segmentation performance without introducing intolerable costs, we propose to transfer the rich knowledge from the multi-modal model (i.e., point clouds and images) and multiple model experts to the point-cloudbased network through knowledge distillation. Specifically, we present Information-oriented Heterogeneous Distillation (IHD) to help the uni-modal model absorb the complementary knowledge from the multi-modal teacher. We design the Information-Oriented Filtering (IOF) strategy to select informative images from the continuous image sequence for multi-modal fusion. This practice can boost the performance of the multi-modal teacher, thus benefiting the learning of the student. Besides, as opposed to vanilla model ensembling that requires the separate training of each expert, we propose Adept Snapshot Distillation (ASD). ASD treats the freely available model snapshots generated during the training phase as multiple experts, which significantly reduces the training cost for model ensembling. For each expert teacher, it only provides supervision to the student in the class where it is adept. The resulting Heterogeneous and Adept Snapshot Knowledge Distillation, dubbed HAS-KD, attains state-of-the-art results on ScanNetV2 and S3DIS datasets. HAS-KD can be seamlessly integrated into contemporary 3D segmentation algorithms and bring considerable gains without introducing extra inference burdens. The code will be made publicly available upon publication.

阅读与讨论 → 访问原文 →

04.

medRxiv (Medicine) 2026-06-24 DOI: HASH:ca74d7d1637a1537db60046f59ec3d84

Allostatic load modifies neuropsychiatric risk following traumatic brain injury

作者:

Wroblewski↗T. H↗Barr↗P. B↗Bigdeli↗T. B↗Barthelemy↗E. J↗

Importance: Outcomes following traumatic brain injury (TBI) vary substantially, with a subset of individuals experiencing neuropsychiatric morbidity and worse prognosis. Exposure to psychosocial and environmental stressors may be an important, yet understudied, modifier of TBI trajectory. Allostatic load (AL) represents the cumulative physiological burden of chronic stress and provides a useful framework for evaluating pre-injury vulnerability. Objective: To assess the relationship between pre-injury AL burden and risk of mortality and incident neuropsychiatric diagnosis following TBI. Design, Setting, and Participants: This cohort study leveraged electronic health record, survey, and laboratory data from the All of Us Research Program, version 8. Participants aged 18 years or older enrolled between May 6, 2018, and October 1, 2023, were queried for TBI diagnosis using clinical diagnostic codes. Data were analyzed between November 11, 2024, and January 7, 2026. Exposure: The physiological burden of pre-injury chronic stress exposure was estimated using an AL index (pALI) derived from anthropometric and laboratory biomarkers collected before index TBI. Main Outcomes and Measures: Post-TBI mortality and incident neuropsychiatric diagnosis clusters. Mortality risk was assessed using Cox proportional hazards models (hazard ratio [HR] with 95% CI), and risk of incident neuropsychiatric diagnosis was modeled using competing-risk regression with death as a competing event (sub-distribution HR with 95% CI). Results: The primary cohort included 4,552 individuals with an established TBI diagnosis and sufficient biomarker data to estimate pALI. The pALI measure differed across sociodemographic groups and was positively correlated with perceived stress (r=.08, p=.002). Higher pALI was associated with increased post-TBI mortality risk (adjusted HR=1.71; 95%CI, 1.36-2.14). Elevated pALI was also associated with greater risk of incident post-traumatic stress disorder (PTSD; adjusted HR=1.28; 95%CI, 1.10-1.50) and sleep disorder (adjusted HR=1.42 95%CI, 1.29-1.57) diagnoses. Conclusions and Relevance: Higher pre-injury ALI was associated with increased risk of mortality and select neuropsychiatric outcomes following TBI, suggesting that AL burden may shape post-injury trajectories. Pre-injury chronic stress exposure and underlying stress biology may represent underrecognized determinants of vulnerability and resilience in brain injury recovery.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-25 DOI: arXiv:2606.25449

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

作者:

Alex Kwon↗

A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains. Across seven models this direction never reverses, a clean kill condition that none breaks. We call this brittle memory: behavioral, not the near-immediate information bound beneath it; only its magnitude is disposition- and task-dependent, not its direction. We measure it with reclaim evaluation: compress a drifted interaction at a fixed budget, then test whether a correction recovers the known answer, scored against ground truth with no judge. Correctability is bottlenecked by whether the answer-determining source survives, not by capability. A one-line source-first policy (keep the recomputable source, drop the re-derivable conclusion) restores correctability at equal budget where that source is compact and identifiable; a length-matched control rules out added text as the cause. The hand-built oracle reaches 1.00; a one-prompt deployable version reclaims 0.49-0.88. The stake compounds: chained through a memory loop, a single dropped-source error corrupts a growing span of downstream steps and stays uncorrectable, while source-first holds to a bounded budget horizon. The wall and fix replicate across three deployed memory systems and on real dialogue (MultiWOZ), and past the budget where the source no longer fits, the fix fails silently unless the note records completeness. This is a controlled study of a mechanism, not a benchmark: judge-free exact scoring, matched-budget controls, and validators built to come out false. We release the harness, conditions, and validators.

阅读与讨论 → 访问原文 →

06.

medRxiv (Medicine) 2026-06-15 DOI: HASH:4274e116a257d77f4261c15c2b9e0edd

Non-Parametric Ancestry Adjustment for Polygenic Scores

作者:

Mas Montserrat↗Barrabes↗Bustamante↗C. D↗Ioannidis↗A. G↗

Modern polygenic risk scores (PRS) exhibit shifts correlated with ancestry, leading to erroneous predictions for non-European individuals when models are trained on predominantly European cohorts. Such shifts arise from, among other factors, (1) algorithmic limitations in the ability of PRS model training to detect causal variants, rather than nearby variants with ancestry-dependent correlations to the causal one, (2) under-representation of alleles with higher prevalence in non-European populations in the association study training, and (3) gene-by-environment interactions where the environment is correlated with genetic ancestry. Current ancestry-adjustment methodologies often discretize individuals into population categories and apply a simple affine mapping to reduce these genetic ancestry biases. However, such approaches provide suboptimal adjustments, particularly for admixed individuals. In this work, we introduce a detailed theoretical characterization of ancestry-dependent biases and propose novel methods based on non-parametric neighborhood techniques that provide more accurate empirical results and admit statistical consistency guarantees. Extensive experiments using the UK Biobank demonstrate the effectiveness of the proposed methods.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14327

I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts

作者:

Shaun Feakins↗Ibrahim Habli↗Kim Littler↗Robert Palin↗

arXiv:2606.14327v1 Announce Type: cross Abstract: This paper appraises recent frameworks within AI development to integrate LLMs into control tasks in automotive contexts from the perspective of safety assurance. This work has built upon the rapid integration of LLMs across automotive settings. However, we find that at present, these frameworks face significant challenges, limiting their efficacy in real-time safety-critical contexts. Firstly, we consider conceptual challenges, including the fact that deployers are faced with a dual challenge, wherein they must assure a model which has been developed upstream, i.e. as general-purpose tools by the large AI labs, in a downstream context, i.e. into specific vehicle architectures. Secondly, we consider concrete challenges from across existing standards. We show that there are currently both fundamental engineering constraints covered in ISO21448, such as latency, and novel LLM-specific issues, such as alignment-related issues covered in ISO/PAS8800. We ground both examples in a concrete introductory, experimental case study exploring an existing open-source repository, Talk2Drive. We present a safety argument in order to make explicit the limitations of existing solutions. Nonetheless, given that the use of LLMs in automotive contexts is being explored at a technical level and operationalised, we propose potential assurance mechanisms for LLM-related hazardous events going forward.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.09547

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

作者:

Apratim Bhattacharyya↗Shweta Mahajan↗Sanjay Haresh↗Rajeev Yasarla↗Reza Pourreza↗Litian Liu↗Risheek Garrepalli↗Roland Memisevic↗

arXiv:2606.09547v2 Announce Type: replace-cross Abstract: Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios. Extensive experiments show that Ego-MC-Bench is highly challenging for state-of-the-art video LLMs. We argue that a key reason is the limited availability of training data for fine-tuning models on this task. Although there exists a wide range of cooking video datasets, existing datasets lack examples of mistakes along with appropriately timed interventions. To help address this data limitation, we also introduce Ego-CoMist, a counterfactual synthetic dataset created by transforming non -interactive cooking videos into supervised training examples showing proactive interventions. We show that fine-tuning on Ego-CoMist yields performance gains especially for smaller and more efficient video LLMs that are well suited for delivering assistance on edge devices.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13994

Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH

作者:

Vikhyath Kothamasu↗Virginia Smith↗Chhavi Yadav↗

arXiv:2606.13994v1 Announce Type: cross Abstract: LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world. A key emerging threat is Decomposition Attacks [glukhov2024breach, jones2024adversaries] in which a harmful task is broken into simpler, benign subtasks that evade safety mechanisms when executed separately but cumulatively fulfill the malicious intent. Although recent benchmarks assess agent safety in multi-turn and multi-tool-use settings, they do not explicitly capture this form of decompositional misuse and may not represent realistic adversarial execution flows. To this end, we introduce DeCompBench, a benchmark designed specifically to evaluate agentic safety under decomposition attacks. DeCompBench is created with a decomposition-by-design principle using a graphical framework and enables harmful task decomposition into individually benign and executable subtasks with realistic workflows. Our experiments using a custom decomposer show that state-of-the-art agents exhibit high refusal rates on monolithic harmful tasks, but significantly lower refusal rates on their decomposed variants, while often inadvertently fulfilling the adversarial objectives. These findings underscore the need for safety evaluations against decomposition attacks and corresponding defenses. Our dataset is publicly available and can be found at https://huggingface.co/datasets/decompositionbench/DeCompBench.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17820

Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation

作者:

Reihaneh Amooie↗Yun Hao↗Wietse de Vries↗Jelske Dijkstra↗Matt Coler↗Martijn Wieling↗

This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20062

Optimal Coarse Correlated Equilibria in Mean Field Games: Linear Programming and No-Regret Learning

作者:

Luciano Campi↗Federico Cannerozzi↗Ioannis Tzouanas↗

arXiv:2606.20062v1 Announce Type: cross Abstract: We introduce optimal coarse correlated equilibria for continuous-time mean field games. A coarse correlated equilibrium is a randomized recommendation scheme from which no player can gain by ignoring the recommendation and switching to an alternative strategy. The problem is as follows: a moderator selects, among all mean-field coarse correlated equilibria, one that optimizes a prescribed performance criterion, which may differ from the representative player's objective. After formulating the problem, we develop a linear programming (LP) formulation, prove the existence of optimal LP coarse correlated equilibria, and relate the LP characterization to the original probabilistic setting. Building on this characterization, we design a no-regret primal-dual algorithm, based on an equivalent Lagrangian formulation of the external-regret constraint, for learning such equilibria. We provide explicit convergence rates for the learning algorithm, and numerical examples illustrate the method.

阅读与讨论 → 访问原文 →

12.

bioRxiv (Bioinfo) 2026-06-10 DOI: HASH:f4e6e5d24beb2fbbe4de01fcb9a8665f

Bias-mitigated microbiome inference refines coronary artery disease signature

作者:

Honeybrook↗

Roughly half the cells in the human body are microbial, and changes in these communities are increasingly implicated in cardiovascular, metabolic, and oncological diseases. Yet identifying which taxa truly differ in abundance, differential abundance (DA), is distorted by four major sources of bias: loss of total microbial load, taxa measurement efficiencies, arbitrary pseudocounts required to handle pervasive zeros, and contamination which has recently driven retractions. No existing DA method accounts for all four. Here we introduce BootDA, a non-parametric bootstrap-based method that explicitly models each bias source without data transformations, pseudocounts, parametric assumptions, or assuming that most taxa are non-DA. In semi-parametric simulations preserving the sparsity (>70% zeros) and correlation structure of real 16S amplicon data, BootDA achieved the highest sensitivity among tested methods, including ANCOM-BC2, LinDA, MaAsLin 3, and Wilcoxon tests, while controlling the false discovery rate. Performance was retained in low biomass settings when contamination contributed ~50% of counts, and without negative controls, indicating de novo decontamination capability. Applied to a coronary artery disease cohort, BootDA refined the original signature to two co-enriched genera, Klebsiella and Gemmiger, and excluded likely contaminants. BootDA is available as an R package and could generalise to other sparse, high dimensional biological data.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.14867

Evaluating the Robustness of Proof Autoformalization in Lean 4

作者:

Zhengtao Gui↗Sheng Yang↗Zhouxing Shi↗

Proof autoformalization aims to translate a mathematical informal proof written in natural language into a formal proof in a formal language such as Lean~4. Several works have developed LLM-based models for proof autoformalization. However, existing evaluations have typically focused on translating well-formed informal proofs from curated datasets. We argue that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and we present the first study on the robustness of proof autoformalization models. We formulate two categories of perturbations and evaluate robustness under each: a global perturbation paraphrases the informal proof in a different style, under which the formalization should remain consistent; a local perturbation alters a value, symbol, or proof step, possibly in a counterfactual way, and a robust formalization should faithfully reflect the perturbation rather than reverting to the original one or inferring a different one on its own. We build a benchmark with both perturbations on miniF2F and MATH-500, and automatically measure how stable a proof autoformalization's correctness is under global perturbations and how faithfully its output reflects local perturbations. We evaluate seven recent models, all of which are sensitive to global perturbations and mostly fail to remain faithful under local perturbations. Code and data are available via https://github.com/ucr-rai/robust-proof-autoformalization.

阅读与讨论 → 访问原文 →

14.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:d913354eca23c2730c762161634084e3

DynamicDemiLog: A Single Sketch for Ultrafast Similarity, Frequency, and Cardinality Estimation

作者:

Bushnell↗B. J↗

Probabilistic cardinality estimators (HyperLogLog), similarity sketches (MinHash), and frequency estimators (Count-Min Sketch) are fundamental approximate data structures that each target one primary problem. We present DynamicDemiLog (DDL), a sketch that unifies cardinality estimation, set similarity, containment, element frequency and composition in one tiny data structure built from a single pass over the input stream. Using an inverted index over 200,687 RefSeq sketches (159,567 organisms), DDL performs all-to-all sketch similarity comparison of the full database in 30 seconds (128 threads, indexed) - over 375x faster per query than Mash's brute-force all-to-all comparison of 91,282 sketches, or 31x faster without the index, at double the sketch resolution. DDL extends the LogLog register with a mantissa: each register stores a floating-point-encoded hash value consisting of an integer exponent (the leading-zero count) and a fractional mantissa (the sub-leading-zero bits), rather than the integer leading-zero count alone. This preserves enough hash information for meaningful register-by-register comparison - a property that standard 6-bit registers lack - while improving on LogLog's cardinality estimation machinery, including DynamicLogLog's early exit mask for high-throughput streaming. With a default 10 mantissa bits (16-bit registers, 2,048 buckets, 4 KB), DDL achieves a per-register false-match rate of 0.018% on unrelated random same-size sets (compared to 17.0% for LL6, a basic HyperLogLog implementation), enabling Weighted Kmer Identity (WKID), Average Nucleotide Identity (ANI), containment, and completeness estimation from register comparison alone. A 16-bit per-register observation counter provides element frequency information at trivial additional computation cost, and an additional byte tracks element composition (GC content, for biological data). Furthermore, DDL's high-specificity registers enable an inverted index structure (DDLIndex) that answers similarity queries against a database of N sketches in O(B + M) time, where M is the number of matching index entries, compared to O(NxB) for pairwise comparison.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.26080

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

作者:

Changdae Oh↗Wendi Li↗Seongheon Park↗Samuel Yeh↗Tanwi Mallick↗Sharon Li↗

arXiv:2606.26080v1 Announce Type: cross Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale. In this work, we show that reinforcement learning (RL) post-training already provides the ingredients for effective step-level scoring, eliminating the need for dedicated reward model training altogether. Concretely, we derive an implicit advantage under a general stochastic Markov decision process, which we term progress advantage – log-probability ratio between the RL-trained policy and its reference policy exactly recovers the optimal advantage function. This formulation makes the resulting signal annotation-free, domain-agnostic, and available as a byproduct of the standard RL post-training pipeline. We validate the effectiveness of the progress advantage across three different applications: test-time scaling, uncertainty quantification, and failure attribution on five benchmarks and four model families. Across all settings, it consistently outperforms confidence-based baselines and, despite requiring no task-specific training, surpasses dedicated trained reward models. We complement these results with deeper analyses on characteristics of progress advantage, offering practical guidance for adoption in real-world agentic systems.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16062

Auditing Reward Hackability in Code RL Training Environments

作者:

Shreshth Rajan↗

arXiv:2606.16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct. On a 49-task sample of SWE-bench Verified, 28.5% of tasks have test suites weak enough that a Docker-verified incorrect patch passes them. On 20 R2E-Gym tasks across 6 repositories, the same pipeline at single-shot exploit generation yields 25.0%. A random-effects meta-analysis over 134 frontier model submissions to SWE-bench Verified finds, within the same human-rated difficulty stratum, model Pass@1 is +14.14 percentage points higher on flagged-hackable tasks than on robust ones (95% CI [+11.80, +16.48]; one-sided p < 10^-6; I^2 = 0%; 123 of 134 models positive). We then describe a procedure for hardening the broken tasks. An inline LLM judge with a Docker gold-sanity gate runs each generated test against the gold solution before the judge is consulted. On the 11 broken tasks in the audit, the gate flags 65 of 105 decisive LLM-generated tests as failing on the gold patch itself, a 61.9% per-augmentation defect rate the LLM judge alone misses. With diversity-biased retry, the loop converges 9 of 11 tasks to a gated upgrade.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.13911

Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveys

作者:

Isai Daniel Chac\'on↗Zhongqi Miao↗Bruno Demuro↗Caleb Robinson↗Rahul Dodhia↗Lasha Otarashvili↗Jason Holmberg↗Kirk Larsen↗Howard Frederick↗Nathan J. Pamperin↗Pablo Arbel\'aez↗Juan M. Lavista Ferres↗…

Automated aerial wildlife surveys increasingly rely on deep learning, yet standard object detectors require bounding-box annotations, reported to be up to seven times slower and three times more expensive to produce than point-level labels. To address this bottleneck, we introduce the Overhead Wildlife Locator (OWL), a weakly supervised density-estimation framework with three variants: OWL-C, a fully convolutional model for high-throughput screening; OWL-T, a Swin-augmented hybrid for heterogeneous, cluttered scenes; and OWL-D, built on a frozen DINOv3 ViT-H+/16 encoder with a DPT-style fusion decoder. We benchmark all three against POLO, YOLOv11n, and YOLOv11l across five public aerial datasets, from sparse fixed-wing savanna surveys to dense UAV paddock imagery, and against the published HerdNet baseline on its native Delplanque split. OWL-D sets a new state of the art on Delplanque (0.934 AP vs. HerdNet's 0.840) and records the highest AP on four of the five datasets. Performance is regime-dependent: on the extreme-density SheepCounter UAV dataset the hybrid OWL-T leads (0.978 AP) and the convolutional variants attain the lowest counting error, whereas the foundation-based OWL-D degrades, indicating which variant suits which survey type. We further validate operational readiness on the Alaska Department of Fish and Game's 2022 Central Arctic Caribou census: under cross-herd and cross-temporal transfer, OWL-C fine-tuned on the 2017 Porcupine Caribou Herd split attains F1 = 0.965 on a held-out patch test set, with a signed count error of +3.1% aggregated across the released test patches. We release the OWL code, model weights, and the annotated Porcupine Caribou Herd 2017 (PCH) and Central Arctic Herd 2022 (CAH) patches, the first open patch-level datasets for large-scale caribou aerial surveys, at https://github.com/microsoft/MegaDetector-Overhead.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.01338

Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware

作者:

Sagar Bhetwal↗Rajan Bastakoti↗Nirajan Acharya↗Gaurav Kumar Gupta↗Ambika Baniya Bhandari↗

Biopharmaceutical manufacturing organizations operate under regulatory frameworks such as FDA guidance, EU Good Manufacturing Practice (GMP), and the EU AI Act, which can restrict the use of cloud-based artificial intelligence systems. Locally deployed large language models (LLMs) offer a privacy-preserving alternative, but their suitability for pharmaceutical manufacturing tasks remains underexplored. This study evaluates four open-source LLMs (Qwen 2.5 Coder 7B, Llama 3.1 8B, Mistral 7B, and Meditron 7B) deployed locally via Ollama for natural-language-to-SQL generation over a pharmaceutical manufacturing database. A FastAPI-based evaluation platform, PharmaBatchDB AI, was developed using a synthetic Microsoft SQL Server database containing approximately 63,000 records across Batch, Manufacturing Execution System (MES), and Clean-In-Place (CIP) modules. Models were benchmarked on 60 domain-specific natural-language questions using metrics including SQL extraction rate, SQL compliance, factual consistency, ROUGE-L, hallucination rate, throughput, and latency. Qwen 2.5 Coder 7B, Llama 3.1 8B, and Mistral 7B generated SQL for all evaluation tasks, while Meditron 7B failed on nearly all tasks due to context-window limitations and poor SQL generation capability. Llama 3.1 8B achieved the highest SQL compliance, whereas Qwen 2.5 Coder 7B achieved the strongest overall text similarity and factual consistency. Performance differences between the two leading models were not statistically significant. The results show that code-tuned general-purpose LLMs outperform a domain-specific biomedical model on structured query generation for pharmaceutical manufacturing data. Although fully local, GxP-aligned NLQ systems are feasible on consumer hardware, current performance levels still require human oversight and downstream validation for regulated use.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13753

The Weight Norm Sets the Grokking Timescale: A Causal Delay Law

作者:

Truong Xuan Khanh↗Doan Hoang Viet↗Luu Duc Trung↗Phan Thanh Duc↗

arXiv:2606.13753v1 Announce Type: cross Abstract: Grokking is the delayed onset of generalization in neural networks, arising long after they fit the training data. Whether the weight norm causes this delay is disputed: some studies report a critical norm at the transition, others observe grokking with no fixed norm at all. We settle this by intervening on the norm during training rather than only observing it. Under free training with weight decay, networks grok when the weight norm reaches a value Wc that varies little across seeds and learning rates (CV 1 to 2 percent) and grows with the modular base as a power law. When we instead clamp the norm to a fixed multiple rho of Wc and hold it there, the network still groks, but the delay follows T_grok proportional to exp(alpha rho). One exponent, alpha near 7.5, fits this delay across four moduli (R^2 = 0.996). Over the swept ranges the held norm moves the delay by about 19x and the learning rate by only about 2x, and holding the norm above Wc slows grokking rather than preventing it. A final LayerNorm removes the dependence by decoupling weight scale from the network function; without it the exponential law returns. This pinned-norm delay is the exponential counterpart to the logarithmic delay predicted for a freely contracting norm.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12930

Is Spurious Correlation Removal Always Learnable?

作者:

Yibo Zhou↗Bo Li↗Hai-Miao Hu↗Hanzi Wang↗Xiaokang Zhang↗Ruifan Zhang↗

arXiv:2606.12930v1 Announce Type: new Abstract: Invariant learning can fail even when the invariant structure is statistically identifiable. We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive motivated by average-case sparse-recovery reductions, there exist samplable multi-environment instances with a one-dimensional predictive invariant subspace ($k=1$) that are learnable with polynomial samples by exhaustive search, while any polynomial-time constant-accuracy recovery algorithm would contradict the primitive. We further quantify environment diversity by a separation parameter $\gamma$, which controls identifiability and the curvature of invariance objectives. Under sufficient diversity and local Gaussian regularity, the minimax risk is $\mathbb{E}[\dist(\hat{V},V_{\mathrm{inv}})^2]=\Theta(k(d-k)/(n|\mathcal{E}|))$, and under label-induced shifts a phase transition occurs at $n^*\propto k(d-k)/(|\mathcal{E}|\gamma^2)$ with refined estimation error scaling proportional to $1/\gamma^2$. Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.08270

An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response

作者:

Joseph Walusimbi↗Joshua Benjamin Ssentongo↗

arXiv:2606.08270v2 Announce Type: replace-cross Abstract: University Academic Management Information Systems (ACMIS) are high-value targets for a wide spectrum of security threats including brute-force login attacks, payment fraud, privilege escalation, insider data theft, and academic integrity violations. Traditional rule-based intrusion detection systems are inadequate because many malicious activities are structurally indistinguishable from normal operations. This paper presents an AI-based security agent for ACMIS that combines supervised anomaly detection, behavioural analytics, and a natural language processing chatbot for secure password recovery. The agent monitors five operational layers: authentication, authorisation, financial transactions, user behaviour, and system health, and responds through a four-tier risk escalation framework. A modular architecture allows the core engine to be extended to other institutional systems. Experiments on a simulated ACMIS event log dataset of 147,922 sessions demonstrate a threat detection macro-average F1 of 0.966, compared to 0.156 for a rule-based baseline and 0.836 for a sequence-only (LSTM) baseline, with end-to-end critical-tier automated response latency under 1 ms on a single-node prototype. The integrated recovery chatbot achieves 97.1 percent identity verification accuracy and an 87.3 percent mass-reset attack detection rate with zero false positives on legitimate high volume recovery periods.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15669

Z-Plane Neural Networks: Bounded Geometric Activation Replaces ReLU and LayerNorm

作者:

Sungwoo Goo↗Hwi-yeol Yun↗Sangkeun Jung↗

arXiv:2606.15669v1 Announce Type: cross Abstract: Modern deep neural networks rely on Euclidean scalar activations (e.g., ReLU) and global normalization techniques (e.g., LayerNorm) to prevent gradient instability in deep architectures. However, these mechanisms inherently cause dead neurons, discard critical directional information, and destroy the orthogonality of feature representations. Inspired by the frequency-modulation transmission of biological axons, we propose the Z-Plane Neural Network, which maps hidden states into 2D phasor bundles on a hypersphere. We introduce a novel geometric activation function, Radial Bounding($\mathbf{x} / \max(1, \|\mathbf{x}\|_2)$), which limits the energy magnitude while preserving the phase (direction). We demonstrate mathematically that this isotropic activation maintains 1-Lipschitz continuity and prevents gradient vanishing by preserving tangential gradients. Empirically, a 100-layer Z-Plane Multi-Layer Perceptron (MLP)-entirely devoid of ReLU and LayerNorm-successfully converges on the MNIST dataset with 98.34% accuracy and absolute numerical stability, proving that bounded geometric activation alone is sufficient for stable deep learning.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.24572

The Vector and Canonical Components of the Momentum Operator in 3D Euclidean Space Spanned by General Curvilinear Coordinates

作者:

M. S. Shikakhwa↗

arXiv:2606.24572v1 Announce Type: new Abstract: We construct the Hermitian vector and canonical components of the momentum operator in 3D Euclidean space spanned by general curvilinear coordinates (GCC's) using a simple, natural and unified approach based on identifying the momentum operator in any coordinate system as mass times the velocity operator. When this latter is calculated by applying the Heisenberg equation of motion, it returns ($-i\hbar$ times) the gradient operator plus an additional zero-valued sum, which when distributed among the components of the gradient, it makes each the Hermitian vector component of the momentum operator in GCC's. The canonical components follow immediately upon symmetrizing each of these vector components in the corresponding base vector. For accessability by wider audiences, we first develop the formalism for the simple polar coordinates and then we develop the case for GCC's.

阅读与讨论 → 访问原文 →

24.

medRxiv (Medicine) 2026-06-18 DOI: HASH:662edec7f3ddce59e18d86871a86c492

Looked but didn't see: inattentional blindness and yes-bias confabulation in vision-language models

作者:

Raymond↗J. D↗Hu↗Solomon↗B. D↗Duong↗

Previous work showed that many participants fail to notice a gorilla in a video of people playing basketball. Another study found that 83% of trained radiologists failed to report a gorilla figure inserted into a chest CT nodule-search task, even though eye-tracking revealed that most observers had foveated the figure. We ask whether a similar phenomenon exists in contemporary vision-language models (VLMs). We find that (i) VLMs are capable of spotting the gorilla in both still-frame images and videos of lung CT scans; (ii) models display inattentional blindness, which varies according to model generation and type of stimulus presented; (iii) Gemini-3.1-Pro outperforms most other flagship and open-weight VLMs at identifying the presence or absence of the gorilla. We additionally ran a segmentation experiment utilizing two different model classes: a generalist (SAM 3), which found the gorilla but produced little to no results for anatomy-based prompts; a medical specialist (BiomedParse), which produced more promising anatomy-based results but flagged "gorilla" on gorilla-free control videos on 82% of frames. The behavioral signature of inattentional blindness reproduces in VLMs, but a unique confabulation failure mode means that any "did the model see X" claim requires signal-detection analysis with a matched-control false-alarm baseline.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2603.09170

ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data

作者:

Haoran Yang↗Jiacheng Bao↗Yucheng Xin↗Haoming Song↗Yuyang Tian↗Bin Zhao↗Dong Wang↗Xuelong Li↗

arXiv:2603.09170v3 Announce Type: replace-cross Abstract: Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperation-free framework that learns humanoid whole-body interaction from human egocentric videos paired with synchronized whole-body motion and text annotations. ZeroWBC adopts a generation-then-tracking formulation to tackle the static scene whole-body interaction control problem. Given an initial egocentric image and a language instruction, a fine-tuned Vision-Language Model generates future human whole-body motion tokens, which are decoded into continuous motions and retargeted to the humanoid. The resulting reference motions, together with root and key body-part trajectories, are then executed by a general interactive motion tracking policy. To improve interaction performance, we introduce an interaction-oriented tracking reward that prioritizes global root and key body-part trajectory alignment while preserving natural whole-body motion. Experiments on the Unitree G1 humanoid robot show that ZeroWBC enables diverse scene-aware behaviors without robot teleoperation demonstrations. These results suggest a scalable paradigm for learning natural humanoid whole-body interaction from human egocentric data.

阅读与讨论 → 访问原文 →