探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-10 DOI: HASH:b30c5359a1656e7879e15a1fbd9e3fdd

Global and local genetic overlap among ME/CFS, irritable bowel syndrome and psychiatric traits: a hypothesis-generating analysis

作者:

Lee↗

Background. Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) and irritable bowel syndrome (IBS) frequently co-occur following infection, yet shared genetic architecture at the locus level has not been systematically characterised. Aims. To estimate global and local genetic correlations between ME/CFS (including infection-onset subgroup), IBS, major depressive disorder (MDD) and loneliness/isolation, and characterise ME/CFS cell-type heritability enrichment. Method. GWAS summary statistics: DecodeME (15,579 ME/CFS; 9,738 infection-onset), FinnGen R9 (9,296 IBS), PGC MDD Wave 2 (45,396) and UK Biobank loneliness (N=455,364). LDSC for global correlations; LAVA for local correlations across 2,495 loci; MAGMA for cell-type enrichment (Descartes Human atlas); coloc.abf for colocalisation. Results. All pairwise global correlations were significant after Bonferroni correction, including ME/CFS-all-MDD (rg=0.598, 95% CI 0.46-0.74) and ME/CFS-all-IBS (rg=0.573, 0.39-0.75). Of 4,232 local tests, 16 reached FDR

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19808

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

作者:

Sajib Acharjee Dip↗Dawei Zhou↗Liqing Zhang↗

Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes. We study this as a deployment allocation problem rather than a new-verifier problem. We introduce \sevra, Selective Verification for Reasoning Allocation, a serving-layer controller that decides whether to preserve a frozen solver's initial answer or invoke active verification. Using a frozen Qwen3-4B solver, we log intervention outcomes and train recoverability-aware gates from serving-visible attempt state. On \mathfive, selective verification reaches 76.3\% accuracy, compared with 75.5\% for always verifying, while reducing post-generation tokens by 26.8\% and harmful flips from 2.2\% to 1.0\%. However, an 8,192-token initial solve reaches 76.0\% accuracy with 28\% fewer total model tokens, showing that selective recovery is useful but not the best tested cost frontier. In frozen transfer to \gsm, the selective policy verifies only 3.0\% of examples, improves accuracy from 93.4\% to 94.5\%, and reduces verification tokens by 91.2\% relative to always verifying; again, a longer initial solve matches its accuracy with fewer realized tokens. On CommonsenseQA, always-on verification hurts, while Self-Consistency@5 improves accuracy at about five times the realized token cost. The resulting deployment rule is: tune the initial budget first, then use selective recovery when explicit checks, bounded retries, auditability, or regression-risk control matter.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17628

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

作者:

Guibin Zhang↗Xun Xu↗Yanwei Yue↗Zikun Su↗Wangchunshu Zhou↗Xiaobin Hu↗Shuicheng Yan↗

Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accumulate skills, but often lack the holistic competence to select useful experience, act on it, write reusable knowledge, and maintain a growing repository. We introduce OPD-Evolver, a slow-fast co-evolution framework that cultivates such an agent evolver through on-policy self-distillation. In the fast loop, OPD-Evolver interacts with a four-level memory hierarchy to read, use, write, and maintain experience for rapid test-time evolution. In the slow loop, outcome-calibrated memory attribution and privileged hindsight distill these four abilities into the deployable policy. Across multi-domain benchmarks, OPD-Evolver surpasses memory systems such as ReasoningBank by up to 11.5%, and training-based methods such as Skill0 by ~5.8%. Further analysis shows that OPD-Evolver internalizes high-value experience and memory management, enabling OPD-Evolver-9B to challenge giant counterparts such as Qwen3.5-397B-A17B and Step-3.5-Flash, pointing beyond memory-augmented agents toward genuinely qualified agent evolvers.

阅读与讨论 → 访问原文 →

04.

PLOS Computational Biology 2026-05-29 DOI: HASH:50ba33afab4132a321c975b37f241668

A prototype-augmented graph representation learning framework for identifying brain disorder-associated genes and facilitating drug repurposing

作者:

Jiafang Li↗

by Jiafang Li, Yifei Li, Siying Lin, Jiahua Rao, Huiying Zhao Many genetic loci were identified as associated with neuropsychiatric disorders and neurodegenerative disorders by Genome-wide association studies (GWAS). How these loci impact these diseases is unclear. Advances in deep-learning approaches and multi-omics data have the potential to link GWAS findings with disease mechanisms. Here, we proposed the Multi-omics Graph Transformer Network (MOGT), a semi-supervised graph neural network that leverages graph representation learning to model biological networks derived from multi-omics data to predict disease-associated genes. MOGT outperforms the current approaches in disease gene prediction for two psychiatric disorders and three neurodegenerative/neurological diseases. High-risk genes (HRGs) for Parkinson’s disease (PD) predicted by MOGT were used to drug discovery by integrating with the CMAP database. Finally, 10 drugs were identified as potential candidates. Among them, the effect of drug UK-356618 was experimentally verified in a primary neuron model, showing that UK-356618 reversed the abnormal expression of PD-associated genes and improved the cell-level phenotypes of PD. Together, these results indicate that MOGT can be used to identify HRGs for brain disorders, and these predicted HRGs provide high-level insights into the mechanisms and treatments of brain disorders.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2602.07628

SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures

作者:

Keondo Park↗Younghoon Na↗Yourim Choi↗Hyunwoo Ryu↗Hyun-Woo Shin↗Hyung-Sin Kim↗

arXiv:2602.07628v2 Announce Type: replace Abstract: While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi , a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age, sex and BMI to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of $>$20,000 PSG recordings (158K hours),SleepMaMi outperforms or matches state-of-the-art existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2204.14224

Investigation of Neural Network Methods for Reconstruction and Classification of Texture Images Under Conditions of Incomplete Information

作者:

Galymzhan Abdimanap↗Kairat Bostanbekov↗Abdelrahman Abdallah↗Anel Alimova↗Darkhan Kurmangaliyev↗Daniyar Nurseitov↗Tatyana Dedova↗Larissa Balakay↗Serik Nurakynov↗

The automated analysis of heterogeneous natural textures is frequently hindered by physical damage and data loss, presenting a significant challenge to computer vision. While deep learning has shown success in controlled environments, its application to complex geological materials under conditions of incomplete information remains underexplored. This study presents an integrated framework for the inpainting and classification of high-resolution core sample images. We propose an end-to-end pipeline that utilizes object detection for sample segmentation, followed by image inpainting using Generative Adversarial Networks (GANs) with Contextual Residual Aggregation (CRA) to reconstruct missing high-frequency details. Subsequently, we evaluate the performance of modern Transformer-based (Swin, ViT) and CNN architectures on the reconstructed data. Our experiments revealed a critical divergence between reconstruction quality and downstream utility: despite high structural fidelity (PSNR 28.7~dB, FID 74.01), classification accuracy plateaued at 53\%. To improve minority-class detection, we propose a confidence-based hybrid ensemble that raises MCA from 48\% to 58\%. These results highlight the limitations of current state-of-the-art generative models, which may produce visually plausible but semantically ambiguous features ("hallucinations") that confound classifiers. This work provides insights into the dependencies between image reconstruction quality and classification performance, offering a reproducible baseline for future research in non-destructive testing and material science. Given that cross-well accuracy remains in the 49–53\% range, we position the resulting system as a decision-support and screening tool for lithofacies interpretation rather than as a fully autonomous classifier. The code is available at https://github.com/GalymzhanAbdimanap/Lithology_recognition

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16011

Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs

作者:

Nafiseh Nikeghbal↗Amir Hossein Kargaran↗Shaghayegh Kolli↗Jana Diesner↗

Standard accuracy benchmarks are designed to test how closely large language models (LLMs) approach correct answers, but are not suitable for testing whether LLMs stick with a correct answer when that answer is challenged by a plausible counter-argument. We introduce a controlled protocol for evaluating answer stability: after a model answers a multiple-choice question correctly, we challenge the model's answer with a coherent argument for an incorrect option and measure whether the model flips. The setup a) isolates argumentative content from overt social pressure and b) varies argument length, self-attribution, and cross-model source. Across seven frontier models and 57 MMLU subjects, flip rates range from 17.5% to 97.3%, revealing large differences in stability that are not captured by accuracy metrics alone. We find that self-attribution consistently increases flip rates (mean +7.1pp, up to +18.7pp). Also, pooling wrong-answer arguments across models and selecting the most effective one per question yields stronger adversarial challenges than relying on any single source model. We further construct MaxFlip, a curated challenge set that amplifies flips by up to +23.6pp over standard self-generated challenges. We release the protocol, challenge records, and MaxFlip to support stability evaluation alongside standard accuracy benchmarks. Materials are available at https://github.com/nafisenik/WhoFlips and https://hf.co/datasets/nafisehNik/WhoFlips.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15980

Do Safety Monitors Stay Reliable After an Update? Benchmarking and Predicting Activation-Monitor Staleness

作者:

Evan Duan↗

Activation monitors-lightweight probes trained on a language model's internal representations-are an increasingly common layer in deployment safety stacks. Deployed models however are rarely static: they are quantized, fine-tuned, adapted with LoRA, or served with merged adapters while the monitor remains frozen. We present the first systematic test of whether this implicit contract holds: whether activation monitors trained on a base model remain reliable after these routine model updates. Across multiple safety-relevant monitors, model depths, update families, and open-weight models, we find a sharp split: quantization-style updates largely preserve frozen probe performance, while fine-tuning-style updates frequently make probes stale. Fragility is highly monitor-dependent, with privacy/PII probes most affected and refusal-compliance probes comparatively stable, showing that retraining a behavior need not stale its corresponding monitor. QLoRA is especially damaging despite NF4 quantization alone being relatively benign, suggesting that quantization becomes riskier when combined with adaptation. We further show that degradation is predictable from pre-deployment features, enabling revalidation budgets to be triaged toward the monitors most likely to fail. These results suggest that fine-tuning should trigger activation-monitor revalidation by default, while prediction can help prioritize which monitors to check first.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2510.09468

Geodesic Calculus on Implicitly Defined Latent Manifolds

作者:

Florine Hartwig↗Josua Sassen↗Juliane Braunsmann↗Martin Rumpf↗Benedikt Wirth↗

arXiv:2510.09468v3 Announce Type: replace Abstract: Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus approximating classical geometric operators. These tools are robust against inaccuracies of the implicit representation often occurring in practical examples. To obtain a suitable implicit representation, we propose to learn an approximate projection onto the latent manifold by minimizing a denoising objective. This approach is independent of the underlying autoencoder and supports the use of different Riemannian geometries on the latent manifolds. The framework in particular enables the computation of geodesic paths connecting given end points and shooting geodesics via the Riemannian exponential maps on latent manifolds. We evaluate our approach on various autoencoders trained on synthetic and real data.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11643

Improving Cross-Format Robustness in Language Models with Multi-Format Training

作者:

June M. Liu↗Shaomian Zheng↗He Cao↗Dingnan Jin↗Qing Cui↗Jun Zhou↗

Large language models often remain sensitive to answer format: a question solved correctly in one form may fail in another semantically equivalent form. To study this gap, we define cross-format robustness as the extent to which a model answers the same underlying question consistently across formats. We then compare full-format training with FormatMix, which expands only a subset of training items into multiple equivalent formats using either random or targeted selection. Across GLM4 and Llama-3.1, multi-format supervision consistently improves both task performance and cross-format robustness, whereas Multiple-choice question (MCQ)-only supervision alone brings little benefit and can even reduce robustness. We further find that expanding only about 30% of the training set into multiple formats often recovers most of the gain from full-format training, and this effect appears across the model families and sizes we study. These results suggest that format diversity, rather than additional supervision alone, is the key driver of robustness. That lightweight multi-format augmentation is a practical way to make LLMs less sensitive to answer format without changing the base model.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2511.08639

The Journal of Prompt-Engineered (Moral) Philosophy Or: Why AI-Assisted Ethics Research Requires Process Transparency

作者:

Michele Loi↗

arXiv:2511.08639v4 Announce Type: replace-cross Abstract: Existing AI disclosure mandates in scholarship require that AI assistance be reported but leave transparency philosophically unspecified: they fix the duty without explaining what the duty serves. We argue that ethical inquiry is essentially contested at two independent levels – about what it is, and about what it demands of the inquirer – defeating output-only evaluation and welfare-economic dismissal of the transparency question, and, by extension, reproducibility framings imported from the empirical sciences. The transparency duty is grounded instead in agent-integrity: the legibility, before a community of inquiry, of the identity-constituting commitments that the author's mode of philosophising expresses. Because the standards for evaluating such work are not communally settled, the achievable goal for transparency is not evaluation against agreed criteria but tracking – accumulating the evidentiary record that lets each tradition assess the work on its own terms and makes future normative judgments possible. We develop a documentation-adequacy framework that operationalises Meaningful Human Control through five transparency elements – declaration, navigation, documentation account, process documentation, and development records – demonstrated by the paper itself, whose full documentation record is archived at a persistent identifier. The framework is a first iteration subject to revision, not a settled standard.

阅读与讨论 → 访问原文 →

12.

medRxiv (Medicine) 2026-06-11 DOI: HASH:542fadb543badbd4cfba6e04c59e27de

Foundation model-based tool for automated ulcerative colitis histology scoring demonstrates non-inferiority to pathologists across multiple scoring indices

作者:

Tahir↗Shamshoian↗Tauber↗Clinton↗L. K↗Griffin↗Shah↗Singh↗Fahy↗Sucipto↗Brosnan-Cashman↗Altepeter↗…

In clinical trials for ulcerative colitis (UC), pathologists assess disease severity through standardized histological indices, including the Geboes Score, Robarts Histopathology Index (RHI), and Nancy Histologic Index (NHI). Despite strong associations with clinical outcomes, histologic scoring suffers from inter- and intra-reader variability, and consensus criteria for histologic remission remain uncertain. Through a consortium approach, we developed an artificial intelligence-based measurement (AIM) tool for scoring histology in UC mucosal biopsies (AIM-HI UC). This model, trained on a large dataset of UC biopsies (N=10,230), utilizes additive multiple instance learning models leveraging PLUTO, a pathology foundation model, that predict each of the Geboes subgrades, from which the Geboes grade-level score, RHI, and NHI can be calculated. Evaluation of this model on a standalone verification set including clinical trial specimens established algorithm non-inferiority and/or superiority relative to standard qualified pathologists through comparison of algorithm-consensus and pathologist-consensus agreement metrics (non-inferior if difference >-0.1, superior if difference >0, inclusive of confidence intervals). AIM-HI UC was determined to be non-inferior to pathologists (N=3) for the prediction of all seven Geboes subgrades, grade-level Geboes, RHI, NHI, histologic improvement (GS

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11578

Contactless 3D Human Body Measurement Using Depth Cameras for Smart Health Monitoring

作者:

Martha Asare↗Xuan Wang↗Juan Lopez Alvarenga↗Lois Akosua Serwaa↗Jinghao Yang↗

Contactless body measurement technologies are becoming increasingly significant for smart health monitoring, digital health applications, and remote patient assessment. Traditional anthropometric measurements typically necessitate physical contact and trained personnel, which may constrain scalability in remote healthcare settings. In this study, we introduce a depth camera-based framework for estimating human body measurements utilizing 3D point cloud data. An Orbbec Astra 2 depth camera was employed to capture RGB images, depth maps, and 3D point clouds of participants. The captured point cloud was processed using Python-based tools, including Open3D, NumPy, and OpenCV, to segment the human body from the background. Key anthropometric measurements, such as height and arm span, were computed. The measurements were obtained through a combination of spatial filtering and landmark selection on the 3D point cloud, followed by the projection of the computed measurements onto the corresponding RGB image using camera intrinsic parameters. In addition to linear measurements, the approximate body volume and visible surface area were estimated using voxel-based occupancy analysis and mesh-based surface reconstruction methods. The experimental results from a single depth capture demonstrated that accurate body measurements and geometric estimates could be obtained from depth camera data without physical contact. This study provides a foundation for future real-time systems that integrate depth sensing with intelligent health monitoring and generative AI models for smart healthcare applications.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12997

Reliability of Probabilistic Emulation of Physical Systems

作者:

Sam F. Greenbury↗Radka Jersakova↗Paolo Conti↗Marjan Famili↗Christopher Iliffe Sprague↗Edwin Brown↗Jason D. McEwen↗

arXiv:2606.12997v1 Announce Type: new Abstract: Two dominant approaches have emerged for generating probabilistic forecasts of physical systems: generative models, such as diffusion or flow matching; and ensembles of deterministic models with stochasticity injected, trained using the continuous ranked probability score (CRPS) loss. While both approaches have demonstrated strong predictive accuracy, the reliability of their uncertainties has not been systematically assessed. We address this gap by developing a framework to evaluate both approaches across diverse 2D spatiotemporal physical systems, under matched model size and computational budget. We assess the reliability of probabilistic emulation by inspecting the empirical coverage of predictive intervals, while also considering accuracy and computational efficiency metrics. CRPS-trained ensembles typically achieve more reliable uncertainties on both single-step prediction and autoregressive rollouts, demonstrating better coverage than the standard alternative of training generative models in a latent space. Moreover, the CRPS approach offers significantly faster inference. When generative models are trained in ambient rather than a compressed latent space, which is often infeasible for high-dimensional problems, they exhibit comparable coverage to CRPS-trained ensembles, though with substantially larger inference latency. In contrast, when CRPS-trained ensembles are trained in latent space they do not show a marked degradation in coverage with respect to ambient space. Both generative models and CRPS-trained ensembles demonstrate good predictive accuracy. To facilitate future research and application, we release AutoCast, a modular framework implementing both generative models and CRPS-trained ensembles, alongside AutoSim, a flexible dataset generation package for rapid prototyping.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2601.14033

Private Prediction via PAC Privacy

作者:

Xiaochen Zhu↗Mayuri Sridhar↗Srinivas Devadas↗

arXiv:2601.14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs. This renders private prediction, i.e., privatizing a model's outputs rather than its parameters, a natural privacy target: model outputs are lower-dimensional and far more stable to training-data changes than weights. While differential privacy (DP) cannot effectively exploit this as it calibrates noise to worst-case sensitivity that is intractable to bound for non-convex models, we argue that PAC privacy is a natural fit for private prediction. It is instance-based, and calibrates noise to a black-box function's empirical stability to control mutual-information (MI) leakage. The missing ingredient is efficient, adaptive composition. Serving predictions means answering a long stream of adaptively chosen queries from untrusted users; existing composition either fails under adaptivity, grows quadratically, or reverts to input-independent, DP-like noise. We close this gap with a new adversarial composition result via adaptive noise calibration and prove that MI accumulates only linearly under adaptive and adversarial querying. Experiments across modalities show that prediction stability enables high utility even at a tiny per-query budget: on CIFAR-10, we achieve 87.79% accuracy with a per-query MI budget of $2^{-32}$. This enables serving one million queries while provably bounding membership-inference success to 51.08% – the same guarantee as $(0.04, 10^{-5})$-DP. Further, in the presence of auxiliary public data, the large volume of PAC-private predictions enables us to distill a publishable model that can be queried without limit. Concretely, 210,000 private labels on an ImageNet subset distill into a student reaching 91.86% accuracy on CIFAR-10 with membership inference success bounded by 50.49%, comparable to $(0.02, 10^{-5})$-DP.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2604.22119

Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework

作者:

Tharindu Kumarage↗Lisa Bauer↗Yao Ma↗Dan Rosen↗Yashasvi Raghavendra Guduri↗Anna Rumshisky↗Kai-Wei Chang↗Aram Galstyan↗Rahul Gupta↗Charith Peris↗

arXiv:2604.22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecified objectives). Systematically understanding and benchmarking these risks remains an open challenge. To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation. We construct an extensible risk taxonomy of 7 categories, which is decomposed into 20 subcategories. ESRRSim generates evaluation scenarios designed to elicit faithful reasoning, paired with dual rubrics assessing both model responses and reasoning traces, in a judge-agnostic and scalable architecture. Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation contexts.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16034

Inference-Time Decision Calibration for Temporal Classification

作者:

Arthur Chagas↗Arthur Buzelin↗Yan Aquino↗Pedro Bento↗Gisele L. Pappa↗Wagner Meira Jr↗Cristiano Arbex Valle↗

arXiv:2606.16034v1 Announce Type: new Abstract: Temporal classification errors are often treated as representation failures, but they can also arise from how available evidence is converted into decisions. This paper proposes a representation–calibration decomposition for temporal classification. We keep a trained native classifier frozen and separate two inference-time interventions: a conservative residual multi-scale branch that adds auxiliary logits to the native prediction, and a post-hoc branch-aware calibrator that recombines native and residual evidence at decision time. This design distinguishes missing temporal evidence from underused decision-level evidence without retraining the backbone. Across FI-2010, PTB-XL, UCI-HAR, MHEALTH, and HARTH, we find that gains are strongly regime-dependent. Residual multi-scale evidence is most useful in noisy or representation-limited settings, especially short-horizon FI-2010 and weaker recurrent backbones, while branch-aware calibration helps when native and auxiliary logits contain complementary evidence not fully exploited by the raw decision rule. Near-saturated settings show limited gains from either intervention. These results suggest that temporal classification should be understood not only as representation learning, but also as the problem of trusting, combining, and calibrating evidence from multiple views.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13740

Efficient On-Device Diffusion LLM Inference with Mobile NPU

作者:

Tuowei Wang↗Yanfan Sun↗Ju Ren↗

arXiv:2606.13740v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference. However, repeated denoising introduces substantial computation on smartphones. Mobile neural processing units (NPUs) offer high-throughput dense matrix computation, but efficiently exploiting them remains challenging: token commitment shrinks per-block effective workloads, token revision complicates KV cache reuse, and limited NPU-visible address space incurs costly remapping and data transfer overheads. In this paper, we propose llada.cpp, the first NPU-aware inference framework for accelerating dLLMs on smartphones. llada.cpp aligns block-wise dLLM inference with the execution characteristics of mobile NPUs through three techniques. (1) Multi-Block Speculative Decoding fills the shrinking workload in late-stage current-block decoding with speculative future-block tokens. (2) Dual-Path Progressive Revision keeps committed tokens revisable until stable and refreshes unstable tokens through a CPU-side path without stalling dense NPU execution. (3) Swap-Optimized Memory Runtime compacts NPU-visible address layouts and overlaps data staging with NPU computation to reduce remapping and transfer overheads. We implement llada.cpp as an end-to-end framework and evaluate it across diverse hardware platforms and dLLM workloads. llada.cpp reduces LLaDA-8B generation latency by 17x-42x over the CPU baseline with prefix KV cache reuse, while preserving generation quality.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18356

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

作者:

Yuchuan Tian↗Mengyu Zheng↗Haocheng Mei↗Ye Yuan↗Chao Xu↗Xinghao Chen↗Hanting Chen↗Yu Wang↗

arXiv:2606.18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injection, tool-return injection, memory poisoning, memory extraction, and ambiguity-driven unsafe inference. SafeClawBench reports three separate endpoints: semantic attack acceptance, audit-visible harm evidence, and sandbox-observed tool/state harm. Evaluating five agent endpoints under four prompt-level policies, we find that these endpoints capture different failure modes. Without additional prompt protection, semantic failure rates vary widely across models, from 9.0% to 44.2%. Audited harm evidence is narrower than semantic failure, and under a separate executable protocol some matched task identities produce sandbox harm despite passing the Semantic Core call: in a 12,000-row matched analysis, 291 of 347 observed sandbox harms occur in rows that pass the semantic check. Prompt policies change endpoint outcomes, but their effects depend on both model and protocol. SafeClawBench provides a reproducible framework for comparing agent models and prompt-policy conditions without conflating textual compliance, evidence-supported harm, and executable state changes. The open-source dataset is available at https://huggingface.co/datasets/sairights/safeclawbench.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2605.29588

Brain-IT-VQA: From Brain Signals to Answers

作者:

Roman Beliy↗Matias Cosarinsky↗Oliver Heinimann↗Navve Wasserman↗Michal Irani↗

Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-standing challenge. While significant progress has been made in recent years in visual question answering (VQA) from fMRI, performance remains limited. Moreover, although recent models can make increasingly accurate predictions, they have rarely been used as tools for understanding the structure of visual representations in the brain. We present Brain-IT-VQA, a framework for visual question answering from fMRI. Building on the Brain Interaction Transformer (Brain-IT), our method decodes language tokens from brain activity and integrates them with a language model to answer visual questions. Our model substantially outperforms previous fMRI-based captioning and VQA approaches. We further introduce NSD-VQA, a new dataset and benchmark for visual question answering from fMRI. Unlike existing image-fMRI VQA datasets, which typically provide only a few broad and weakly controlled questions per image, NSD-VQA provides on average 20 question-answer pairs per image across 20 controlled question categories that disentangle multiple levels of visual understanding. This enables more reliable and interpretable evaluation despite limited fMRI test data. Together, Brain-IT-VQA and NSD-VQA provide both a strong predictive framework and a tool for studying brain representations. Using this benchmark, we quantify which forms of visual and semantic information can be reliably decoded from fMRI responses to natural images. We further analyze the contributions of different brain regions across question types.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15307

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

作者:

Mohamed Bayan Kmainasi↗Mucahid Kutlu↗Ali Ezzat Shahroor↗Abul Hasnat↗Firoj Alam↗

Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based multimodal large language models (MLLMs) have advanced vision-language understanding, their application to meme content moderation remains underexplored. We propose a reinforcement learning-based post-training method that improves classification performance and reference-based explanation quality in thinking-based MLLMs via task-specific rewards and Group Relative Policy Optimization (GRPO). Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful and propagandistic meme understanding across English and Arabic benchmarks, (ii) extend existing meme datasets with weakly supervised chain-of-thought (CoT) rationales via distillation and multi-LLM fine-grained propaganda annotations, (iii) introduce a GRPO-based objective with thinking-length regularization that jointly optimizes classification accuracy and explanation quality, and (iv) investigate self-supervised GRPO on unlabeled memes using consensus-based pseudo-labels. Experiments on the Hateful Memes and ArMeme benchmarks show that our approach improves over previously reported results on FHM accuracy (up to +2.1%, from 79.9% to 82.0%) and on ArMeme macro-F1 (up to +7.6 points, from 0.536 to 0.612 with explanations; +6.1 compared to the original ArMeme benchmark), while also generating natural-language explanations. On ArMeme, sequence-classification baselines remain stronger in terms of raw accuracy, whereas our approach provides more balanced per-class performance along with explanations. We publicly release our code, data extensions, and evaluation resources.

阅读与讨论 → 访问原文 →

22.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2605.12191

Sure-almost-sure and Sure-limit-sure Window Mean Payoff in Markov Decision Processes

作者:

Pranshu Gaba↗Shibashis Guha↗

arXiv:2605.12191v2 Announce Type: replace-cross Abstract: Given rationals $\alpha$ and $\beta$, the sure-almost-sure problem for a threshold Boolean objective $\varphi$ in a Markov decision process (MDP) asks if one can simultaneously ensure that all outcomes of the MDP have $\varphi$-value at least $\alpha$ (i.e. sure $\alpha$ satisfaction) and with probability $1$ the outcome has $\varphi$-value at least $\beta$ (i.e. almost-sure $\beta$ satisfaction). The sure-limit-sure problem asks if for all $\varepsilon > 0$ one can simultaneously ensure that all outcomes have $\varphi$-value at least $\alpha$ and with probability at least $1 - \varepsilon$ the outcome has $\varphi$-value at least $\beta$. Moreover, if simultaneous satisfaction of objectives is possible, then one would also like to construct a strategy (for sure-almost-sure) or a family of strategies (for sure-limit-sure) that achieves this. In this paper, we solve the sure-almost-sure and sure-limit-sure problems for window mean-payoff objectives. The window mean-payoff objective strengthens the standard mean-payoff objective by requiring that eventually, from every point in the infinite run, the average payoff becomes greater than a given threshold within a finite window length. We study two variants of window mean payoff: in the fixed variant, the window length $\ell$ is given, while in the bounded variant, the length is not given but is required to be bounded throughout the run. We show that the sure-almost-sure problem and the sure-limit-sure problem are both in P for the fixed variant (if $\ell$ is given in unary) and are both in NP $\cap$ coNP for the bounded variant, matching the computational complexity of sure satisfaction and almost-sure satisfaction when considered separately for these objectives. We also give bounds for the memory requirement of winning strategies for all considered problems.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13249

Multi-Field Hybrid Retrieval-Augmented Generation for Maritime Accident Root Cause Analysis

作者:

Seongjin Kim↗Sungil Kim↗

arXiv:2606.13249v1 Announce Type: new Abstract: Maritime accident adjudication reports contain critical tribunal findings for root cause analysis (RCA), yet retrieving relevant precedents and drafting consistent reports from decades of records remains labor-intensive. This paper proposes a multi-field hybrid retrieval-augmented generation (RAG) framework for automated maritime RCA, utilizing a comprehensive dataset of 13,329 Korea Maritime Safety Tribunal (KMST) reports (1971-2025). We transform raw adjudications into a structured knowledge base of "incident cards", indexing three distinct fields-Summary, Causes, and Disposition-alongside a hierarchical L1/L2 cause taxonomy. Our retrieval strategy employs a field-aware hybrid approach, fusing sparse and dense rankings via Reciprocal Rank Fusion (RRF). Given the lack of large-scale expert relevance labels, we evaluate retrieval performance using ceiling-normalized recall and nDCG based on a metadata-derived proxy relevance score. Experimental results demonstrate that our proposed retrieval significantly outperforms baseline methods, improving NormRecall@100 from 0.18 to 0.55. Furthermore, grounding the generator on the retrieved precedents enhances RCA generation quality over an LLM-only baseline, increasing the LLM-as-a-judge score from 3.34 to 3.72. These findings suggest that field-aware RAG can substantially streamline maritime safety investigation workflows by enabling faster precedent search and more consistent, evidence-based RCA drafting.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2602.06276

Statistical Learning from Attribution Sets

作者:

Lorne Applebaum↗Robert Busa-Fekete↗August Y. Chen↗Claudio Gentile↗Tomer Koren↗Aryan Mokhtari↗

arXiv:2602.06276v2 Announce Type: replace Abstract: We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailable. Motivated by privacy-preserving browser APIs and the deprecation of third-party cookies, we study a setting where the learner observes a sequence of clicks and a sequence of conversions, but can only link a conversion to a set of candidate clicks (an attribution set) rather than a unique source. We formalize this as learning from attribution sets generated by an oblivious adversary equipped with a prior distribution over the candidates. Despite the lack of explicit labels, we construct an unbiased estimator of the population loss from these coarse signals via a novel approach. Leveraging this estimator, we show that Empirical Risk Minimization achieves generalization guarantees that scale with the informativeness of the prior and is also robust against estimation errors in the prior, despite complex dependencies among attribution sets. Simple empirical evaluations on standard datasets suggest our unbiased approach significantly outperforms common industry heuristics, particularly in regimes where attribution sets are large or overlapping.

阅读与讨论 → 访问原文 →

25.

Nature (Science) 2026-06-09 DOI: HASH:e965c6e96db8e206429b797bc244040f

Seven steps for critically analysing research papers

作者:

Jacques Cornwell↗

By sticking to a clear strategy when reading, I get much more out of the literature, says Jacques Cornwell. By sticking to a clear strategy when reading, I get much more out of the literature, says Jacques Cornwell.

阅读与讨论 → 访问原文 →