探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18663

RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories

作者:

Kaiyan Zhao↗Zhongtao Miao↗Akiko Aizawa↗Yoshimasa Tsuruoka↗

Data mixture selection is critical for Large Language Model pretraining. Existing methods such as RegMix select a single static mixture by fitting a regression model on small-scale proxy runs. We propose RegMix-D, a simple extension of RegMix to dynamic mixing. Our key observation is that proxy runs produce not only endpoint losses, but also full loss trajectories, which can be used to further improve data mixture. By training regression model on these trajectories, we can predict optimal mixtures at multiple training stages. RegMix-D supports two deployment modes: an offline variant that generates a complete mixture schedule before target training, and an online variant that adapts the mixture during training using observed loss. Experiments on 25B tokens of the Pile dataset with a 1B parameter target model show that RegMix-D consistently improves over RegMix and DoReMi across 13 downstream tasks while remaining proxy-efficient: it surpasses RegMix even with only 128 proxy models (25% of RegMix's proxy compute budget).

阅读与讨论 → 访问原文 →

02.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2404.13730

Cluster sizes in subcritical soft Boolean models

作者:

Benedikt Jahnel↗Lukas L\"uchtrath↗Marcel Ortgiese↗

arXiv:2404.13730v2 Announce Type: replace Abstract: We consider the soft Boolean model, a model that interpolates between the Boolean model and long-range percolation, where vertices are given via a stationary Poisson point process. Each vertex carries an independent Pareto-distributed radius and each pair of vertices is assigned another independent Pareto weight with a potentially different tail exponent. Two vertices are now connected if they are within distance of the larger radius multiplied by the edge weight. We determine the tail behaviour of the Euclidean diameter and the number of points of a typical maximally connected component in a subcritical percolation phase. For this, we present a sharp criterion in terms of the tail exponents of the edge-weight and radius distributions that distinguish a regime where the tail behaviour is controlled only by the edge exponent from a regime in which both exponents are relevant. Our proofs rely on fine path-counting arguments identifying the precise order of decay of the probability that far-away vertices are connected.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24173

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

作者:

Disha Patel↗

arXiv:2606.24173v1 Announce Type: cross Abstract: On-device fault detection enables real-time diagnostics without cloud dependency, but deploying machine learning models on resource-constrained hardware demands careful tradeoffs between accuracy, latency, and model size. We present a benchmark comparing traditional ML methods (Random Forest, XGBoost, SVM, Logistic Regression) against lightweight transformer architectures (DistilBERT, TinyBERT-6L, TinyBERT-4L, MobileBERT) for binary fault detection across three public datasets: NASA C-MAPSS turbofan degradation, SECOM semiconductor manufacturing, and UCI AI4I 2020 predictive maintenance. We evaluate classification performance (F1-score, AUC), model size, and CPU inference latency, and further assess INT8 dynamic quantization and a two-stage adaptive inference pipeline. Our results reveal that on well-separated sensor data (C-MAPSS), lightweight transformers match traditional ML at 87.8% F1 but at 100x the model size and 9000x the latency. TinyBERT-4L emerges as the most deployment-friendly transformer at 55 MB and 18 ms CPU latency. INT8 quantization reduces size by 25% while preserving 86.9% F1. Our adaptive pipeline, routing 97.9% of predictions through a quantized triage model and only 2.1% to a larger expert, achieves 87.6% F1 at 19.5 ms average latency. On severely imbalanced datasets (SECOM, UCI-PM), both traditional and transformer methods struggle significantly, highlighting fundamental limitations of current approaches for extreme class imbalance in fault detection. All code is publicly available.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13067

Limits of spectral learning under noise

作者:

Sabin Roman↗Ljupco Todorovski↗Saso Dzeroski↗Marta Sales-Pardo↗Roger Guimera↗

arXiv:2606.13067v1 Announce Type: new Abstract: Learning functional relationships from noisy data is a central problem in scientific inference. Spectral methods approximate unknown functions by expanding them in a basis and estimating the corresponding coefficients from data, but the stability of these coefficients under noise remains poorly understood. Here we study supervised regression with additive label noise using sparse spectral representations across multiple bases and dimensions. We show that noise induces a predictable drift in the learned coefficient vector whose magnitude depends on the effective number of active spectral modes. After whitening the empirical feature geometry, we derive a closed-form expression for the overlap between noisy and noiseless coefficient vectors, revealing a universal degradation curve governed by a single intrinsic noise scale. Numerical experiments across Fourier, Legendre, Bessel, and Haar bases confirm the theoretical prediction. The results demonstrate that spectral learning exhibits a fundamental noise threshold beyond which coefficient estimates become unstable, placing intrinsic limits on recovering functional structure from noisy data.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2602.22159

CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness

作者:

Wenhao Guo↗Zhaoran Zhao↗Peng Lu↗Sheng Li↗Qian Qiao↗DeRui Li↗

Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and artifacts accumulate sharply. We revisit this challenge from a cross-scale distribution transition perspective and propose CASR, a simple yet highly efficient cyclic SR framework that reformulates ultra-magnification as a sequence of in-distribution scale transitions. This design ensures stable inference at arbitrary scales while requiring only a single model. CASR tackles two major bottlenecks: distribution drift across iterations and patch-wise diffusion inconsistencies. The proposed SSAM module aligns structural distributions via superpixel aggregation, preventing error accumulation, while SARM module restores high-frequency textures by enforcing correlation-guided consistency and preserving self-similarity structure through correlation alignment. Despite using only a single model, our approach significantly reduces distribution drift, preserves long-range texture consistency, and achieves superior generalization even at extreme magnification.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24605

ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling

作者:

Tianbao Ma↗Chang Xi↗Yichuan Zou↗Chengen Li↗Linxun Chen↗Zilong Lu↗Yanan Niu↗Zhaojie Liu↗Han Li↗Kun Gai↗

arXiv:2606.24605v1 Announce Type: new Abstract: Accurate user modeling often depends on rich interaction histories, which are unavailable for billions of low-activity users. Large Language Models (LLMs) can infer latent user states from static profiles, but this reasoning becomes unreliable when profiles are sparse, and applying an LLM to billions of users is prohibitively expensive. We present ScaleToT, which learns structured reasoning from a small LLM-processed subset and extends it to the broader low-activity user population. To improve reasoning reliability, ScaleToT constructs typed user-state chains with a bounded entropy-guided Tree-of-Thought (ToT) refinement procedure. To make this structured reasoning usable from sparse profiles, the teacher-curated chains are used to train a student model on static profiles through supervised fine-tuning (SFT) and Outcome-Driven Segment-Aware Implicit Reward Policy Optimization (OSIPO). ScaleToT then transfers the student's reasoning representations to a lightweight profile encoder, providing shared reasoning signals for the remaining users without LLM inference. We evaluate ScaleToT on lifetime value (LTV) prediction in a billion-scale advertising deployment. A randomized online A/B test increased LT30 by 6.738\%, while offline reasoning covered only 7.32\% of the potential population, greatly reducing compute cost compared with full-population reasoning.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13385

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

作者:

Zihao Wang↗Yiming Li↗Yutong Wu↗Zheyu Liu↗Kangjie Chen↗Fok Kar Wai↗Pin-Yu Chen↗Vrizlynn L. L. Thing↗Bo Li↗Dacheng Tao↗Tianwei Zhang↗

arXiv:2606.13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences. This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour. Existing security benchmarks adopt an attack-centric perspective, focusing on the technical feasibility of injections while overlooking the nuanced distribution of resulting harms. In practice, however, prompt-injection risk is victim-dependent: a single exploit can produce asymmetric consequences for different stakeholders, and the same attack pattern may exhibit substantially different effectiveness depending on whom it targets. To capture these properties, we introduce \sysname, a stakeholder-centric benchmark to systematically categorize and attribute harm in real-world web agent systems. It distinguishes between affected entities (e.g., user, seller, platform), decomposes the attacks into concrete objectives, and evaluates each case with complementary outcome- and process-level metrics. Our results reveal substantial and heterogeneous vulnerabilities: not a single attack objective is reliably resisted by current agents, and failures distribute across qualitatively distinct modes ranging from stealthy parasitism (attack succeeds without disrupting the user's delegated task) to misaligned disruption (task disrupted without attack success) and compounded failure (both adversarial objective and task integrity simultaneously violated). These patterns are missed by conventional evaluation, highlighting the need for stakeholder-aware assessment of LLM-based agents in real-world deployments. Benchmark is available at https://github.com/StakeBench/SBC.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2603.08999

Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning

作者:

Juming Xiong↗Kevin Guo↗Congning Ni↗Wexin Liu↗Chao Yan↗Katherine Brown↗Avinash Baidya↗Xiang Gao↗Bradley Malin↗Zhijun Yin↗

Large language models (LLMs) can achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet they often generate unnecessarily long reasoning paths that incur high inference cost. Self-consistency-based approaches push accuracy higher still, but they require sampling and aggregating multiple reasoning trajectories, leading to substantial computational overhead. In this paper, we introduce a confidence-aware selective sampling framework that, at inference time, analyzes a single reasoning trajectory to adaptively determine whether to rely on that trajectory alone or trigger multi-path sampling. The framework uses trajectory-level numeric features and sentence-level linguistic features extracted from reasoning states to guide selective multi-path reasoning. We train it on MedQA and evaluate it in-domain on MedQA and under calibration-only transfer on MathQA, MedMCQA, and MMLU, without further fine-tuning. Experimental results show that the proposed framework maintains comparable performance to full and efficient multi-path reasoning baselines, with accuracy changes of $-0.41 \pm 0.58$ and $-0.31 \pm 0.58$ percentage points, respectively, while reducing token usage by $71.7 \pm 5.0%$ and $36.6 \pm 9.1%$. These findings demonstrate that reasoning trajectories contain rich signals for uncertainty estimation, enabling a simple, transferable mechanism to balance accuracy and efficiency in LLM reasoning.

阅读与讨论 → 访问原文 →

09.

PLOS Computational Biology 2026-06-16 DOI: HASH:90aea8d024db29360f119f4a0bd368de

Evolution and the ultimatum game: An agent-based model with interbirth intervals and population structure

作者:

Jeffrey C. Schank↗

by Jeffrey C. Schank, Matt L. Miller The ultimatum game (UG) is widely used to study mutually beneficial exchanges, fairness, and prosocial behavior across different societies. However, human behavior in UG experiments does not align with the game-theoretical prediction that proposers should offer the least positive amount and responders should accept such offers. Instead, proposers make generous offers that are greater than the minimum responders are willing to accept, resulting in generous offers with wide offer-acceptance gaps. Numerous evolutionary models of the UG have been created and studied to explain human behavior, particularly generous offers made in UG experiments. These models have recently faced criticism for lacking biological realism and not adequately explaining the data. Here, we present an agent-based model inspired by our hunter-gatherer ancestors and with a biologically more realistic selection process. We assume that (1) agents exist in group-structured and group-clustered populations, where reproduction (2) depends on resource accumulation, but (3) is limited by interbirth intervals. We ran simulations to assess whether this biologically more realistic model evolves patterns of behavior consistent with patterns in the data from meta-analyses of human behavior in the UG. For the proposed model, we show that generous offers robustly evolve, as well as the difficult-to-explain offer-acceptance gaps, only in group-structured populations with interbirth intervals. We demonstrate that these results are robust and may help explain variation in data across societies. We discuss how interbirth intervals interact with group structure to modulate offer and rejection costs, favoring the evolution of generous offers, offer-acceptance gaps, and other patterns in the data on human behavior in the UG. We also discuss why weak selection and/or high mutation rate models cannot explain all the patterns in UG experimental data. We discuss biological realism and conclude that group structure and interbirth intervals may be essential for explaining prosocial behavior across societies.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2509.26633

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

作者:

Lujie Yang↗Xiaoyu Huang↗Zhen Wu↗Angjoo Kanazawa↗Pieter Abbeel↗Carmelo Sferrazza↗C. Karen Liu↗Rocky Duan↗Guanya Shi↗

arXiv:2509.26633v3 Announce Type: replace-cross Abstract: A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive locomotion and loco-manipulation. To address this, we introduce OmniRetarget, an interaction-preserving data generation engine based on an interaction mesh that explicitly models and preserves the crucial spatial and contact relationships between an agent, the terrain, and manipulated objects. By minimizing the Laplacian deformation between the human and robot meshes while enforcing kinematic constraints, OmniRetarget generates kinematically feasible trajectories. Moreover, preserving task-relevant interactions enables efficient data augmentation, from a single demonstration to different robot embodiments, terrains, and object configurations. We comprehensively evaluate OmniRetarget by retargeting motions from OMOMO, LAFAN1, and our in-house MoCap datasets, generating over 8-hour trajectories that achieve better kinematic constraint satisfaction and contact preservation than widely used baselines. Such high-quality data enables proprioceptive RL policies to successfully execute long-horizon (up to 30 seconds) parkour and loco-manipulation skills on a Unitree G1 humanoid, trained with only 5 reward terms and simple domain randomization shared by all tasks, without any learning curriculum.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17803

Continual Self-Improvement with Lightweight Experiential Latent Memories

作者:

Vaggelis Dorovatas↗Nancy Kalaj↗Rahaf Aljundi↗

arXiv:2606.17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process. We investigate whether models can instead learn online from this experience, converting transient computation (reasoning traces) into persistent reusable knowledge, and without external supervision or access to future data. We show that In-Context Learning (ICL) over raw reasoning traces fails to generalize, reflecting a fundamental limitation of token-level reuse: individual traces lack the abstraction needed for transfer, even after refinement (e.g. self-reflection). In contrast, drawing inspiration from recent works on unsupervised reinforcement learning, we find that lightweight per-instance training with self-generated test-time signals (majority voting) as rewards yields substantial gains, often surpassing full-dataset offline training, motivating a shift from raw traces to learned latent representations. Building on this insight, we propose an online method that distills inference-time compute spent on encountered problems into compact modular latent memories capturing the underlying reasoning structure. These memories are stored and retrieved for future inputs, enabling continual improvement while avoiding catastrophic forgetting through modular design. Importantly, our method is highly efficient, parametrized as extremely lightweight soft prompt memories (~0.001% of model parameters) and trained with only a few gradient steps, yet achieving performance competitive with full parametric updates and offline training. Across challenging mathematical reasoning benchmarks, our approach significantly outperforms zero-shot and raw data ICL baselines, while transferring effectively across datasets.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-24 DOI: arXiv:2606.22546

Venice-H1: Failure-Aware Query Re-Ranking with Multi-Scale Grid Signatures for Referring Image Segmentation

作者:

Nicol\`o Savioli↗

Modern Referring Image Segmentation (RIS) systems generate multiple candidate masks per expression but rely on a simple heuristic–typically the argmax detection score–to select the final output. We identify query selection as a failure-case bottleneck: although heuristic selection succeeds on 82-93% of samples, the residual 7-18% of failures dominate the error budget, leaving a best-query selection gap of 3-11% mIoU. We introduce Venice-H1, a lightweight, backbone-decoupled post-hoc re-ranking module that encodes each candidate through multi-scale grid signatures–compact spatial descriptors pooled onto 4x4, 8x8, and 16x16 grids–and feeds them to a Transformer-based re-ranker with a Failure Gate (ROCAUC 0.78-0.82) that intervenes only when the default choice is likely suboptimal. Instantiated on DeRIS-L and DeRIS-B, Venice-H1 achieves delta_fail of +1.40 and +0.89 mIoU with strictly positive 95% CIs on all 16/16 (split, backbone) pairs and harmful-switch rates below 0.53%. Zero-shot transfer to medical referring segmentation (MS-CXR, M3D-RefSeg-2D) yields +1.16 and +0.51 mIoU without RIS-backbone fine-tuning. The module adds approximately 11.3M parameters and under 1 ms latency.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2512.22671

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

作者:

Pere Martra↗

Structured width pruning of GLU-MLP layers in Llama-3.2 models, guided by the Peak-to-Peak Magnitude (PPM) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance on tasks relying on parametric knowledge (e.g., MMLU, GSM8K) and perplexity metrics degrades predictably with decreasing expansion ratios, instruction-following capabilities improve at the 2.4x equilibrium ratio (IFEval: +4.8 points / +46% in Llama-3.2-1B and +3.7 points / +39% in Llama-3.2-3B), and multi-step reasoning remains robust (MUSR). This pattern, observed consistently across both evaluated model sizes, challenges the prevailing assumption in compression research that pruning induces uniform degradation. To investigate this, we evaluated seven expansion ratio configurations using comprehensive benchmark suites that assess factual knowledge, mathematical reasoning, language comprehension, instruction-following, and truthfulness. Our analysis identifies the expansion ratio as a critical architectural parameter that selectively reshapes the model's task performance profile, rather than merely serving as a compression metric.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12160

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

作者:

Ao Sun↗

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token. Our method extracts a compact set of features such as maximum, minimum, mean, standard deviation, and slope-from the token logits across all layers, enabling effective hallucination detection without overfitting. Experiments on TruthfulQA and MMLU datasets demonstrate that CHAIR significantly improves detection accuracy, particularly in zero-shot scenarios, showcasing its robustness and generalizability. Beyond hallucination detection, CHAIR highlights the potential of using internal representations for designing advanced decoding strategies. By leveraging patterns in logits, we suggest that more sophisticated models and adaptive decoding methods could further reduce hallucinations and enhance text completion quality. CHAIR not only offers a practical solution for detecting hallucinations but also lays the groundwork for exploring richer representations in LLMs to improve their factuality and coherence.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24679

FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

作者:

Kunyu Ni↗Lei Cao↗Jie He↗Xiaotong Zhang↗Jianfeng Jin↗Junyu Dong↗Yanwei Yu↗

arXiv:2606.24679v1 Announce Type: cross Abstract: Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation operators. However, automatically constructing such pipelines is computationally difficult because operator sequences are combinatorial and end-to-end evaluation is expensive. Existing state-of-the-art (SOTA) Multi-DQN methods still face three key limitations: decoupled value estimators weaken long-horizon credit assignment, dataset context is only weakly injected into the policy, and exploration is inefficient in a sparse search space with many invalid states. To address these issues, we propose FlowPipe, a unified framework that formulates pipeline synthesis as conditional probabilistic flow generation over a directed acyclic graph. FlowPipe uses Conditional Generative Flow Networks (C-GFlowNets) with a Trajectory Balance objective to connect terminal validation rewards with early pipeline decisions. It further introduces Deep Semantic Modulation through Feature-wise Linear Modulation (FiLM), allowing LLM-derived logical priors to condition the policy's internal activations according to dataset semantics. In addition, FlowPipe incorporates failure awareness into the flow objective to avoid invalid states and concentrate search on high-potential regions. Experiments on two benchmark suites with 74 real-world datasets show that FlowPipe outperforms SOTA baselines, improving accuracy by 11.96% on average and achieving 12.5x faster training convergence. Source code is available at https://github.com/KunyuNi/FlowPipe.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16362

Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers

作者:

Sourya Sengupta. Mark A. Anastasio↗

arXiv:2606.16362v1 Announce Type: cross Abstract: Deep neural networks have achieved strong performance in medical image classification, but often work like black-box. Commonly used post-hoc interpretation methods often provide heuristic visualizations whose relationship to the classifier's predictive distribution is indirect. This work introduces a local sensitivity analysis framework based on the input-dependent Fisher Information Matrix (iFIM) of a trained classifier. The iFIM characterizes how the classifier's predictive distribution changes under infinitesimal perturbations of the input image. By using a Gram-matrix formulation, the nonzero eigenspectrum of the iFIM can be recovered without explicitly forming the full image-dimensional Fisher matrix. The leading iFIM eigenspace is then used to project an input image into a high local-sensitivity component and its orthogonal component. These components provide a model-intrinsic description of local predictive sensitivity, rather than a conventional pixel-wise attribution heatmap or a causal segmentation of task-relevant anatomy. The framework is evaluated on controlled and clinical medical image classification tasks using multiple classifier architectures. Perturbation-based experiments show that high-sensitivity iFIM components are more strongly coupled to changes in predictive confidence and classification performance than lower-sensitivity complementary components. The results support the iFIM framework as a principled tool for analyzing local decision sensitivity and for complementing existing attribution-based interpretability methods in medical imaging.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19183

Language Models as Interfaces, Not Oracles: A Hybrid LLM-ML System for Pediatric Appendicitis

作者:

Soheyl Bateni↗Maryam Abdolali↗

Large language models (LLMs) can make clinical decision support more accessible by interpreting free-text documentation, but their direct use as diagnostic engines is limited by sensitivity to prompts, information order, and plausible but incorrect outputs. Structured machine-learning models offer more stable risk prediction, yet they require tabular inputs that are difficult to integrate with narrative clinical workflows. We present ClaMPAPP (Clinical Language-assisted Machine-learning Pipeline for Appendicitis), a hybrid system that uses an LLM as an interface rather than as the final decision-maker. ClaMPAPP extracts schema-constrained clinical features from note-like narratives, applies deterministic plausibility checks, and passes validated features to an XGBoost classifier trained on clinical, laboratory, and ultrasound variables. We evaluated ClaMPAPP on two independent pediatric appendicitis cohorts from German hospitals and compared it with end-to-end LLM baselines, including open-source and proprietary models. To preserve ground truth while testing free-text input, narratives were generated from structured electronic health records through template rendering and constrained LLM rewriting, with additional sentence-order permutation to assess positional robustness. ClaMPAPP achieved the strongest overall diagnostic performance in both internal and external validation while minimizing missed appendicitis cases, the key safety concern in acute triage. End-to-end LLMs showed unstable sensitivity-specificity trade-offs and greater degradation under narrative reordering. These results support an LLM-as-interface, ML-as-predictor design that separates natural-language usability from predictive inference and provides a more auditable pathway for clinical decision support.

阅读与讨论 → 访问原文 →

18.

medRxiv (Medicine) 2026-06-22 DOI: HASH:763a9e8b1ac419f857e7be3be64047ca

Leishmaniasis on YouTube: a critical appraisal of the quality, reliability, and transparency of educational content

作者:

NANTALAGA↗K. C↗Nantege↗

Background: Leishmaniasis is a neglected tropical disease of significant global public health importance, for which accurate information is essential to support prevention and early care-seeking, particularly in endemic, resource-limited settings. YouTube is a widely used source of health information, but the quality and reliability of leishmaniasis-related content have not been evaluated. We aimed to assess the quality, reliability, and transparency of English-language YouTube videos on leishmaniasis. Methods: We conducted a cross-sectional analysis of YouTube videos retrieved via the YouTube Data API on 15 June 2026 using the terms "leishmaniasis," "cutaneous leishmaniasis," and "visceral leishmaniasis." After applying eligibility criteria and screening the 150 most-viewed eligible videos, 48 videos were included. Two reviewers independently assessed each video using the modified DISCERN (mDISCERN) tool, the Global Quality Score (GQS), and the JAMA benchmark criteria, with disagreements resolved by consensus. Inter-rater agreement was assessed using the intraclass correlation coefficient (ICC), and associations were examined using Spearman's rank correlation. Results: Of 402 videos retrieved, 48 met the inclusion criteria. The median GQS was 3.00 (IQR 2.00-4.00) and median mDISCERN was 3.00 (IQR 2.38-4.50), indicating moderate quality and reliability, while the median JAMA score was 2.00 (IQR 1.00-2.00), reflecting limited transparency; no video met all four JAMA criteria. The overwhelming majority of videos (47/48, 97.9%) were of professional or institutional origin. Inter-rater agreement was good to excellent (ICC 0.883 for GQS, 0.896 for mDISCERN, 1.000 for JAMA). The instruments were strongly inter-correlated (mDISCERN-GQS rho = 0.841, p < 0.001). Quality scores did not correlate positively with views, likes, or video duration; comments correlated weakly and negatively with mDISCERN (rho = -0.337, p = 0.031) and JAMA (rho = -0.381, p = 0.014). Conclusions: YouTube videos on leishmaniasis are of moderate quality and reliability but limited transparency, and are produced almost exclusively by professional sources. Video popularity, length, and age were not indicators of quality. There is a need for experts and institutions to produce clearly authored, well-sourced, and transparent educational content on this neglected tropical disease.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2605.20726

Everywhere Valid Bounds on False Discovery Proportions in Conformal Inference

作者:

Ziang Song↗Ying Jin↗Emmanuel J. Cand\`es↗

arXiv:2605.20726v2 Announce Type: replace-cross Abstract: Modern applications of conformal inference to multiple testing problems, such as outlier detection and candidate selection, often involve selecting test samples whose conformal p-values fall below a threshold. The quality of such methods is often measured by the false discovery proportion (FDP), defined as the fraction of incorrect selections. Existing approaches typically control the expected value of the FDP, using methods such as the Benjamini-Hochberg procedure. This approach fails to provide high-probability bounds on the realized false discovery proportion and invalidates statistical guarantees if the rejection threshold is selected after inspecting the data. This paper establishes finite-sample, distribution-free upper bounds on the FDP that hold simultaneously over all possible rejection thresholds, enabling arbitrary post hoc selection of the threshold. Simultaneous validity is achieved by constructing a high-probability envelope for the empirical distribution function of null conformal p-values by sampling from their joint distribution. Furthermore, our framework allows practitioners to modulate the envelope's shape, thereby producing tight bounds in rejection regions of primary interest. We use this flexible approach to derive simultaneous FDP upper bounds for both outlier detection and conformal selection. We demonstrate through synthetic and real-data experiments that the resulting bounds are both valid and substantially less conservative than those derived from existing approaches.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19494

Hidden Anchors in Multi-Agent LLM Deliberation

作者:

Apurba Pokharel↗Ram Dantu↗

arXiv:2606.19494v1 Announce Type: new Abstract: Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it works is rarely modelled. Such deliberation mirrors how humans reach decisions. As social animals we are pulled both by the group, the herd effect that classical opinion-dynamics models such as DeGroot and Friedkin–Johnsen capture, and by our own internal belief, which they do not. We model multi-agent deliberation as a closed-loop dynamical system in which each agent carries a hidden internal belief, its anchor, that continually pulls its opinion regardless of its neighbours. We show this anchor can be recovered from the deliberation alone, and that it explains a behaviour classical consensus rules forbid: an agent's confidence in the correct answer can climb past where any agent started, escaping the space (convexhull) formed by the initial beliefs. Checking whether the recovered anchor also predicts held-out runs (generalizes) gives a simple test for when a model is truly driven bysuch an anchor. Across three open-weight model families this is a spectrum, not all-or-nothing. All anchors' influence are about equally strongly, but they differ in where the anchor sits, and only when it sits far from the initial opinions does deliberation escape the hull and need the full closed-loop model.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14690

A Complexity Measure for Active Learning in Multi-group Mean Estimation

作者:

Abdellah Aznag↗Rachel Cummings↗Adam N. Elmachtoub↗

arXiv:2606.14690v1 Announce Type: new Abstract: We study a max-risk objective for active learning in a multi-group mean estimation $d$-armed bandits: a learner adaptively allocates a budget of $T$ samples across $d$ groups to minimize the worst-case uncertainty index $\max_{k\in[d]}\sigma_k^2/n_k$, where $\sigma_k$ is the standard deviation of the distribution of arm $d$, and $n_k$ is the number of times arm $d$ is sampled. We develop a local minimax framework and prove the first general lower bound for this objective, valid for any finite-variance hypothesis class. The bound separates difficulty into three orthogonal factors: a budget term, a heteroscedasticity index measuring how unevenly the uncertainty is spread across arms, and a model-dependent complexity measure, the Variance Local Curvature ($\mathrm{VLC}$), which captures how much information a local change of variance creates inside the hypothesis class. For smooth classes, the $\mathrm{VLC}$ is a reparametrization of a variance–Fisher information, with closed-form values for common families. Benchmarking against the strongest available upper bound shows near-optimality up to logarithmic factors in broad regimes, and pinpoints a systematic gap in highly heterogeneous instances. Our proof introduces two key ingredients: a loss-induced $\ell_1$ geometry on the decision space, and a representation-based instance generator that reduces hard-instance construction to an explicit random matrix calculation.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24820

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

作者:

Hovhannes Tamoyan↗Sean Narenthiran↗Erik Arakelyan↗Mira Mezini↗Boris Ginsburg↗

LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have emerged, yet are still evaluated as file retrieval rather than actionable diagnosis, producing locations without the diagnostic context a repair agent needs. We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent orchestration. SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods. Injecting our locations and diagnostic findings into repair agents yields, on average, +5.95 pp resolve rate on SWE-Bench Verified while cutting localization and total tokens by 36.7% and 23.1%.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14106

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

作者:

Seoyoung Choi↗Minseok Ko↗Hyunseok Lee↗Kunwoong Kim↗Woomin Song↗Chanseok Jeon↗Jinwoo Shin↗

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16131

Shift-and-Sum Quantization for Visual Autoregressive Models

作者:

Jaehyeon Moon↗Bumsub Ham↗

Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key challenges for applying PTQ to VAR: (i) large reconstruction errors in attention-value products, especially at coarse scales where high attention scores occur more frequently; and (ii) a discrepancy between the sampling frequencies of codebook entries and their predicted probabilities due to limited calibration data. To address these challenges, we propose a PTQ framework tailored for VAR. First, we introduce a shift-and-sum quantization method that reduces reconstruction errors by aggregating quantized results from symmetrically shifted duplicates of value tokens. Second, we present a resampling strategy for calibration data that aligns sampling frequencies of codebook entries with their predicted probabilities. Experiments on class-conditional image generation, inpainting, outpainting, and class-conditional editing show consistent improvements across VAR architectures, establishing a new state of the art in PTQ for VAR.

阅读与讨论 → 访问原文 →

25.

medRxiv (Medicine) 2026-06-18 DOI: HASH:f5dd52ac6dd6f167bae6b329954ac000

Excess mortality in Germany during 2020-2023: A descriptive age-stratified analysis

作者:

Sauter↗

This study investigates excess mortality in Germany in the years from 2020 to 2023 and its temporal alignment with reported COVID-19 deaths. The analysis uses annual and weekly all-cause mortality data and linear baseline trends derived from pre-pandemic years. Possible effects of demographic and population changes on baseline trends were also examined. Excess mortality was analysed over time and across age groups. Excess mortality was observed in all investigated years, rising from 2020 to its highest value in 2022. In absolute terms, the age group [&ge;]80 years accounted for the largest proportion of excess deaths throughout the study period. After 2021, elevated mortality relative to baseline was also observed in younger age groups down to 15 years of age, although absolute numbers remained substantially lower than in older groups. No evidence of excess mortality was observed for individuals younger than 15 years. Periods of excess mortality were temporally aligned with waves of reported COVID-19 deaths. In 2020, cumulative excess mortality after calendar week 11 closely matched reported COVID-19 deaths (43 876 vs. 41 835 deaths). Weekly excess mortality, reported COVID-19 deaths and wastewater viral load, when available showed strong temporal synchrony, although excess mortality increasingly exceeded reported COVID-19 deaths during later pandemic waves. Temporal patterns differed from the typical seasonal mortality peaks commonly associated with influenza epidemics during the early months of the year. In 2023, excess mortality declined substantially, possibly indicating a return to mortality levels before the emergence of SARS-CoV-2.

阅读与讨论 → 访问原文 →