探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-15 DOI: HASH:c7a2eec04b04b62c6da4391414adc1f8

Unveiling the Awareness of Private Health Insurance Coverage among Healthcare Professionals in Freetown, Sierra Leone: Insights Extracted from Their Perspectives.

作者:

Gary↗L. P↗Kamara↗A. N↗Jimmy↗A. I↗Lebbie↗A. P↗

Our study is an assessment of the knowledge, personal coverage, and related determinants of private health insurance as revealed by healthcare professionals in Freetown, the urban capital of Sierra Leone. This study stands as a precursor for Low- and Middle-Income Countries (LMICs), like Sierra Leone, seeking to establish Universal Health Coverage (UHC) to provide healthcare access and coverage through publicly arranged risk pooling, designed to help protect against unmanageable medical costs. In parallel, such countries face significant challenges with achieving sustainable universal coverage due to limited public resources, inefficient allocation systems, uneasy reliance on out-of-pocket payments, and large struggling populations. Our research sheds particular light on how healthcare professionals view their own participation with private healthcare options. A cross-sectional, analytical study was conducted, openly recruiting individuals from various facilities in Freetown. Using the Yamane Formula, a sample size of 109 participants was calculated. STATA 14.0 was used for data analysis. Our findings revealed that 96 (88.9%) participants did not have private health insurance, while 12 (11.1%) did have private coverage. However, 105 (97.2%) reported other modes of health insurance, with only 3 (2.8%) uninsured. Notably, 97.2% expressed willingness to join a private health insurance scheme. Our study found no statistically significant associations between selected indicators (demographic or socioeconomic fac tors) and current insurance coverage among study participants. These results highlight a low prevalence and understanding of private health insurance among healthcare professionals in a representative urban center in Sub-Saharan Africa (SSA), while acknowledging high willingness to enroll. The lack of any significant determinants suggests other unexamined factors, such as cost, accessibility, or awareness, capable of influencing the adoption and implementation of a universal health program.

阅读与讨论 → 访问原文 →

02.

medRxiv (Medicine) 2026-06-18 DOI: HASH:8933fa4012539c43beb1b860359102a3

Device assessed 24-hour movement behaviour and cardiovascular disease mortality amongst cancer survivors.

作者:

Mitchell↗J. J↗Biswas↗R. K↗Blodgett↗J. M↗Koemel↗N. A↗Ahmadi↗M. N↗Fisher↗Friedenreich↗…

Background: Cancer survivors face elevated risks of mortality from cardiovascular disease (CVD). The potential importance of physical activity (PA) and other behaviours across the 24-hour day (e.g. sedentary behaviour (SB) and sleep) for CVD-mortality risk is not well understood in this at-risk population. Objectives: To assess the importance of 24-hour movement behaviour, using a compositional approach, for mitigating CVD-mortality amongst cancer survivors. Methods: Participants with a prior cancer diagnosis were drawn from the UK Biobank accelerometry sub-study (n=6,158). Accelerometer-derived movement (moderate-to-vigorous PA (MVPA), vigorous PA (VPA), moderate PA (MPA), light PA (LPA), SB, sleep) was examined in relation to CVD-mortality, identified from health record linkage data (using Fine-Gray Cox proportional-hazards models adjusted for demographic, health, lifestyle covariates). Results: Median follow-up was 8.0 years (Q1-Q3: 7.4-8.5), with n=500 (8.2%) deaths (CVD-deaths: n=118). Greater MVPA, in place of any other behaviour, was inversely associated with CVD-mortality with e.g. 10% lower hazard if MVPA theoretically replaced 7 minutes (mins)/day SB (Hazard ratio (HR): 0.91, (95% Confidence Interval: 0.86-0.95)), 9 mins/day LPA (HR: 0.90, 0.83-0.97), or 11 mins/day sleep (HR: 0.90, 0.83-0.97). The VPA component of MVPA proved critical, requiring only ~1-2 additional mins/day for equivalent hazard reduction. Sleep duration, was also inversely associated with CVD-mortality. A 10% lower hazard required replacing 29 mins/day of SB with sleep (HR: 0.90, 0.84-0.96); no other behavioural replacement amongst SB, sleep or LPA could provide an equivalent risk reduction. Conclusions: Among cancer survivors, the most potent reduction in CVD-mortality followed theoretically reallocating time to higher intensity movement.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11430

Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge

作者:

A. Mayeux↗

arXiv:2606.11430v1 Announce Type: cross Abstract: Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean mathlib), preventing unified access between published results and their formalizations. We propose a relational bridge-database that aligns publication metadata with formal artifacts, providing an interoperability layer between mathematical literature and machine-verifiable proofs. We introduce a paper-level formalization score that measures how much of a publication is covered in formal systems. As a feasibility study, we show how such scores can be estimated via cross-document alignment between informal texts and Lean formalizations, enabling large-scale analysis of formalization coverage. This framework is a first step toward integrating bibliographic and formal mathematical ecosystems into scalable, machine-actionable knowledge graphs linking publications to formal proof objects.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2510.04902

DP-Hype: Federated Differentially Private Hyperparameter Search

作者:

Johannes Liebenow↗Thorsten Peinemann↗Esfandiar Mohammadi↗

arXiv:2510.04902v3 Announce Type: replace Abstract: Tuning hyperparameters in federated machine learning can substantially impact model performance. When hyperparameters are tuned on sensitive data, privacy becomes an important challenge and to this end, differential privacy has emerged as the de facto standard for provable privacy. A standard setting in federated learning is that clients agree on a shared setup, i.e., find a compromise from a set of hyperparameters, like a model's learning rate. Yet, prior work on privacy-preserving hyperparameter tuning is tailored to specific learning tasks, does not account for the privacy leakage of aggregated results, or offers a sub-optimal privacy-utility trade-off. In this work, we present our algorithm DP-Hype, which performs a federated and privacy-preserving hyperparameter search by conducting a federated voting based on local hyperparameter evaluations of clients. In this way, DP-Hype selects hyperparameters that lead to a compromise supported by a majority of clients, while maintaining scalability and independence from specific learning tasks. We prove that DP-Hype preserves the strong notion of differential privacy called client-level differential privacy and, importantly, show that its privacy guarantees do not depend on the number of hyperparameters. We also provide bounds on its utility guarantees, that is, the probability of finding good hyperparameters, and implement DP-Hype as a submodule in the popular Flower framework for federated machine learning. In addition, we evaluate performance on multiple benchmark data sets in iid as well as multiple non-iid settings and demonstrate high utility of DP-Hype even under small privacy budgets.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2605.10840

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

作者:

Yixuan Yang↗Mehak Arora↗Ryan Zhang↗Baraa Abed↗Junseob Kim↗Tilendra Choudhary↗Md Hassanuzzaman↗Kevin Zhu↗Ayman Ali↗Chengkun Yang↗Alasdair Edward Gent↗Victor Moas↗…

arXiv:2605.10840v3 Announce Type: replace-cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data – to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning – remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum – predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization – addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13695

Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling

作者:

Boris Kriuk↗

arXiv:2606.13695v1 Announce Type: cross Abstract: Mineral prospectivity modelling (MPM) underpins exploration economics, yet most operational pipelines reduce to data-driven classifiers trained on shallow surface proxies. Such models are blind to the subsurface physics that actually localises ore: heat advection, fluid flow, and lithology-dependent precipitation. We present Korzhinskii-Net, a 2-D radial physics-informed neural network (PINN) that couples Darcy flow, advective-diffusive heat transport, and a softplus-saturated reaction rate into a single differentiable forward model, weakly supervised by surface and remote-sensing proxies. The network is named after Dmitri S. Korzhinskii (1899-1985), whose theory of infiltration metasomatism provides the physical scaffold. We evaluate Korzhinskii-Net on five ore provinces spanning four commodity classes – Norilsk (Ni-Cu-PGE), Pechenga (Ni-Cu sulphide), Udokan (sandstone-hosted Cu), Sukhoi Log (orogenic Au), and Mirny (kimberlitic diamond) – under a fair, leakage-controlled 5-fold cross-validation protocol with hard ring-shaped negatives. Korzhinskii-Net attains a mean PR-AUC of 0.885 versus 0.281 for the strongest classical baseline (gradient boosting), and a mean fractional rank of 0.019 versus 0.413. The improvement is consistent across all five provinces and four commodity systems, suggesting that physics-informed differentiable simulators, even when constrained only by global open-data proxies, can recover localisation patterns that pure feature-based learners systematically miss. We release the full pipeline and evaluation harness as open source.

阅读与讨论 → 访问原文 →

07.

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 →

08.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18465

What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy

作者:

Truong Xuan Khanh↗

arXiv:2606.18465v1 Announce Type: cross Abstract: Grokking, the delayed jump from memorization to generalization, is usually tied to the weight norm: a smaller norm generalizes sooner. We ask what the norm actually controls. Holding the weight norm fixed by clamping and varying only an output temperature, we slide the grokking delay across its entire norm-induced range under cross-entropy; matching the effective logit scale back to baseline recovers about 85% of the delay at two moduli. Across a grid of norms and temperatures the delay collapses onto the logit scale alone (R2 = 0.97), with the norm adding 1-2% beyond it. The effect is loss-dependent: under mean-squared error the logit scale is pinned and the norm acts through a different route. A memorization control, a float64 softmax-collapse audit, and a no-LayerNorm transformer point to the same channel. Forking arms from one identical state, the delay follows the held norm value and not the clamp operation, which closes a rescaling-artifact concern. The proximal variable is the logit scale and the softmax saturation it drives; the weight norm is only an upstream handle. All numbers, tables, and figures reproduce from released code and data.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12744

GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models

作者:

Garvita Allabadi↗Matteo Sodano↗Roberto Estev\~ao↗Yuxiong Wang↗Vikram Adve↗Emre Kiciman↗Ranveer Chandra↗

In-Context Learning (ICL) has become a powerful mechanism for adapting Large Language Models (LLMs) to new tasks without fine-tuning. Extending this concept to Large Multimodal Models (LMMs), Multimodal In-Context Learning (M-ICL) relies on retrieving relevant examples, such as images, captions, or question-answer pairs, to guide predictions across tasks like classification, captioning, and visual question answering (VQA). Most existing approaches select in-context examples based on feature-space similarity, assuming that semantically similar samples provide the most useful context. However, our systematic analysis reveals that this assumption does not always hold: visually similar examples are not necessarily those that most effectively enhance in-context learning performance. To address this, we propose the Guided Retrieval of In-context Prompts (GRIP), a learnable vision-only retrieval framework that leverages feedback from LMMs to identify examples that truly improve model predictions. GRIP learns to distinguish beneficial from detrimental in-context examples through contrastive training, refining retrieval beyond pure similarity. Across three multimodal tasks, namely classification, captioning, and VQA, GRIP improves consistently over similarity-based retrieval on Qwen2.5-VL-7B, with its strongest gains in classification on Idefics2-8B. Moreover, we demonstrate that retrievers trained with feedback from one open LMM can be transferred to other models without retraining, including closed-source GPT-4o and Gemini, enabling scalable and cost-efficient deployment of M-ICL. Code will be published upon acceptance.

阅读与讨论 → 访问原文 →

10.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:64b97f7ec539a0badbb55a8f77c9ff95

Machine Learning-Guided Discovery of Bacterial-Selective Membrane-Active Compounds Reveals Mechanistic Bias in Antibiotic Training Datasets

作者:

Chain↗Ghaffari↗Belakaria↗Sheehan↗J. P↗Irani↗Wu↗C.-Y↗Kim↗Engelhardt↗B. E↗Gitai↗…

The rise of antibiotic resistance necessitates the discovery of antibacterial compounds with novel mechanisms of action (MoAs). Recent machine learning approaches have shown promise in antibacterial compound discovery, but often identify derivatives of known antibiotic classes rather than mechanistically novel compounds. Previous approaches applied Tanimoto similarity filters at the end of screening pipelines, but this method has substantial drawbacks: Tanimoto similarity can be misleading in chemical space, and post-hoc filtering does not influence what activity models learn to prioritize. Here, we present a machine learning pipeline that addresses chemical novelty upfront by employing an XGBoost-based MoA classifier to explicitly prioritize compounds predicted to have mechanisms distinct from known antibiotic classes, combined with graph neural networks for antibacterial activity and toxicity prediction. Applied to the Zinc20 database, our approach successfully identified non-toxic antibacterial compounds structurally distinct from known antibiotics. Notably, the majority of these hits exhibited membrane-targeting activity with selectivity for bacterial cells over mammalian cells, suggesting potential for next-generation membrane-active antibiotics. However, we did not identify compounds with novel protein targets. Systematic analysis revealed that this limitation stems from mechanistic bias in training data rather than model architecture. Specifically, our activity model learned to preferentially score compounds similar to specific groups in the training data, thus overrepresenting certain MoA classes including membrane-active compounds. Even substantial model architecture and training data enhancements did not overcome this constraint. Our findings demonstrate that the primary bottleneck for discovering mechanistically novel antibiotics is the scarcity of diverse, mechanistically-annotated training data. This work provides both a methodological framework for mechanism-aware screening and critical insights into data requirements for genuinely novel antibiotic discovery.

阅读与讨论 → 访问原文 →

11.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.12856

Quantum walk-based optimisation for capacitated vehicle routing with homogeneous and heterogeneous fleets

作者:

Edric Matwiejew↗Aidan Smith↗Callum Neill↗Paulo Santos↗Ugo Varetto↗Jingbo Wang↗

arXiv:2606.12856v1 Announce Type: new Abstract: The capacitated vehicle routing problem (CVRP) is an appealing candidate for quantum optimisation due to its combinatorial complexity and practical importance. However, the problem's constrained search space poses a challenge for such quantum algorithms. We introduce a quantum walk-based optimisation algorithm (QWOA) for the CVRP with homogeneous or heterogeneous vehicle fleets, addressing this challenge through a continuous-time quantum walk over a product space that coincides with combinatorial structures intrinsic to the CVRP solution space. Relative to the prior QWOA-based formulation, this approach reduces the per-layer gate complexity from $\mathcal{O}(n^{3}\log n)$ to $\mathcal{O}(n^{2}\log n)$ and supports a circuit parameterisation schedule generated by a fixed number of classical parameters. Exact state-vector simulation on instances with up to $n=8$ customers and $K=3$ vehicles demonstrates improved convergence to low-cost solutions using markedly fewer objective function evaluations, with the advantage broadening as problem size increases. These results identify structured product-space walks as a promising tool for optimisation over constrained combinatorial spaces.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13211

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

作者:

Omar Alshahrani↗Muzammil Behzad↗

arXiv:2606.13211v1 Announce Type: new Abstract: AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucination: clinically plausible but factually incorrect outputs, including fabricated anatomical structures, missed findings, incorrect laterality, and invented measurements in generated reports, with direct consequences, for example, for biopsy decisions, staging, and treatment planning. This structured narrative synthesizes peer-reviewed studies, benchmark datasets, and FDA regulatory guidance across five imaging modalities to produce a cross-modality analysis of hallucination taxonomy, etiology, detection, and mitigation. Specifically, we address three questions in this study: (1) how can existing taxonomies be unified across modalities?, (2) how do medical-specialized foundation models hallucinate less than general-purpose ones?, and (3) which mitigation strategies are effective and compatible with FDA lifecycle oversight? We note that three taxonomic frameworks together cover the imaging pipeline in a way no single framework does alone. We also highlight that general-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks, indicating that narrow domain fine-tuning can introduce overfitting-induced confabulation. At the same time, the oversight of radiologists remains essential; for instance, a very high percentage of of AI-generated flags required expert correction before clinical use. Physics-informed architectural constraints, Chain-of-Thought prompting, and human-in-the-loop safeguards each address different failure modes and is effective when combined. All findings are mapped to the FDA's Total Product Lifecycle and Predetermined Change Control Plan frameworks, which treat hallucination management as a lifecycle obligation rather than a pre-deployment checklist.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2510.11709

Adversarial Attacks Leverage Interference Between Features in Superposition

作者:

Edward Stevinson↗Lucas Prieto↗Melih Barsbey↗Tolga Birdal↗

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decision boundary structure, but none provides a representation-level mechanism that explains why specific perturbations succeed and why attacks transfer between models. In this paper, we show that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, vulnerability can arise from superposition - the phenomenon where networks represent more concepts than they have dimensions, forcing non-orthogonal representation and thus interference. This interference causes perturbations targeting one representation to affect others, creating vulnerabilities determined by interference patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. The resulting attacks are predictable: PGD-discovered perturbations align with theoretically optimal perturbations derived from the interference geometry. Models trained on similar data develop similar interference patterns, explaining attack transferability. We then show that successful attacks on image classifiers exhibit the structure predicted by our proposed mechanism. These findings reveal that adversarial vulnerability can be a byproduct of networks' representational compression, complementing existing explanations based on data properties or architectural factors.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2603.18374

Black Hole–Entropy Container or Creator

作者:

William G Unruh↗

arXiv:2603.18374v3 Announce Type: replace-cross Abstract: Do black holes possess entropy or do they create it? The dominant assumption is that they possess entropy, and a they evaporate that entropy is emitted and decreases. In this paper I use a model of a linear amplifier, in which I argue that the amplifier has not entropy and yet it emits entropy in the process of it operation. This model is closely related to behaviour of black holes, resulting in answer the question of that title that black holes do not have entropy, but nevertheless them create and emit entropy with the total entropy emitted being the same as the usual expression proportional to the square of the mass of the black hole.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.10466

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

作者:

Du Yin↗Hao Xue↗Jinliang Deng↗Yang Yang↗Shuang Ao↗Arian Prabowo↗Flora Salim↗

arXiv:2606.10466v2 Announce Type: replace-cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmentation, we propose UPLOTS, a Unified, Prompt-guided Language model framework fOr constrained Time-Series Generation across diverse domains. Instead of building task-specific models, UPLOTS leverages a single pre-trained transformer backbone guided by learned constraint prompts, enabling on-demand generation with precise pattern control. One key innovation is our dynamic multi-dataset loss re-weighting and prompt-to-pattern mapping, which allows UPLOTS to internalize diverse temporal structures during training and conditionally generate them at inference. We evaluate UPLOTS on four real-world benchmarks and multiple constraint settings, including peak-period, calendar, load-level, and volatility patterns. Additional held-out constraint-combination and downstream forecasting experiments further demonstrate that UPLOTS generalizes beyond the original peak-pattern setting and improves data augmentation under scarce real-data regimes. Our code and baselines are available at anonymous github repo: https://anonymous.4open.science/r/UPLOTS-6C36.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19613

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

作者:

Vlad Sobal↗Shuo Yang↗Yuting Zhang↗Wei Xia↗Stefano Soatto↗

arXiv:2606.19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.03090

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

作者:

Hang Li↗Fedor Filippov↗Yuping Lin↗Pengfei He↗Kaiqi Yang↗Yucheng Chu↗Yingqian Cui↗Hui Liu↗Jiliang Tang↗

arXiv:2606.03090v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubrics while achieving satisfactory grading performance. Despite these advantages, new security concerns may also arise. In particular, prompt injection (PI) attacks have recently become a major threat to LLM-based applications. In the context of AG, attackers can potentially exploit PI vulnerabilities to manipulate grading systems into assigning artificially high scores regardless of the actual answer quality. Such behavior poses serious risks to the fairness, reliability, and integrity of educational assessment. In this work, we study PI attacks in AG systems, and systematically investigate the effectiveness of such attacks in educational scenarios. We further evaluate the effectiveness of existing defensive strategies against these attacks. Through comprehensive experiments under rubric-based grading settings, we demonstrate that current LLM-based AG systems remain highly vulnerable to PI attacks. We hope that our findings raise awareness of this emerging threat and motivate future research toward secure, robust, and trustworthy LLM-based educational systems.

阅读与讨论 → 访问原文 →

18.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.06452

Energy-Modulated Time-Asymmetric Spontaneous Collapse: Forward-Backward Dynamics from Stochastic Ito Reversal and Bright Solitons

作者:

Ikechukwu C. Okoro↗Mike O. Osiele↗Godfrey E. Akpojotor↗

arXiv:2606.06452v3 Announce Type: replace Abstract: We present a rigorous theoretical framework for symmetry breaking and quantum irreversibility arising from stochastic Ito field reversal within a cubic-quintic nonlinear Schrodinger equation (CQ-NLSE) formalism. Starting from three physically motivated considerations, forward and backward nonlinear stochastic differential equations are derived via the Ito calculus. Kinematic time-reversal is shown to be fundamentally incompatible with the Ito stochastic structure, yielding the universal asymmetry-coupling parameter of 2/3. An energy-driven collapse operator proportional to the product of noise strength, local probability density, and excitation energy squared is introduced, amplifying the collapse in high-density, high-excitation regions. Exactly bright soliton solutions are obtained for a quasi-one-dimensional BEC of attractive Li-7 atoms, with forward and backward amplitude ratio of 1.870. Heat map analysis of the parameter planes reveals that the forward collapse operator grows monotonically in time while the backward counterpart decays, achieving a ratio approximately 1030, sharply distinguishing this framework from conventional symmetric collapse models.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2602.06257

On Randomized Algorithms in Online Strategic Classification

作者:

Chase Hutton↗Adam Melrod↗Han Shao↗

arXiv:2602.06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open or close credit cards and bank accounts to obtain a positive prediction. The learning goal is to achieve low mistake or regret bounds despite such behavior. While randomized algorithms have the potential to offer advantages to the learner in strategic settings, they have been largely underexplored. In the realizable setting, no lower bound is known for randomized algorithms, and existing lower bound constructions for deterministic learners can be circumvented by randomization. In the agnostic setting, the best known regret upper bound is $O(T^{3/4}\log^{1/4}T|\mathcal H|)$, which is far from the standard online learning rate of $O(\sqrt{T\log|\mathcal H|})$. In this work, we provide refined bounds for online strategic classification in both settings; our bounds depend on the Littlestone dimension $\mathrm{Ldim}(\mathcal H)$ of the hypothesis class $\mathcal H$ and the maximum degree $\Delta$ of the manipulation graph. In the realizable setting, we extend, for $T > \mathrm{Ldim}(\mathcal H) \Delta^2$, the existing lower bound $\Omega(\mathrm{Ldim}(\mathcal H) \Delta)$ for deterministic learners to all learners. This yields the first lower bound that applies to randomized learners. We then provide the first randomized learner that improves the known (deterministic) upper bound of $O(\mathrm{Ldim}(\mathcal H) \cdot \Delta \log \Delta)$. In the agnostic setting, we give an improper randomized learner that improves the regret upper bound to $O(\sqrt{T\log|\mathcal H|})$, matching the standard online learning rate. We also show a larger lower bound for all proper learning rules, demonstrating that improperness is necessary to achieve the optimal rate.

阅读与讨论 → 访问原文 →

20.

bioRxiv (Bioinfo) 2026-06-18 DOI: HASH:3fd1513f17e693a820d87068c3efe76b

Predicting optimal growth temperatures of bacteria using learned structural information from a single protein

作者:

Hoffert↗Myerscough↗Dragone↗N. B↗Gebert↗M. J↗Silberg↗J. J↗Fierer↗

Temperature is a fundamental determinant of bacterial physiology and ecology. Optimal growth temperature (OGT) is highly variable across species, contributing to differences in where and when species are most likely to thrive. Although the OGTs for most bacteria remain unknown, the increasing availability of genomes from uncultivated and cultivated taxa has made it advantageous to build genomic, cultivation-independent models to infer OGT. However, pre-existing genomic models often lack the generalizability and mechanistic grounding required for robust inferences of OGT. We propose a novel framework for predicting bacterial OGT which uses learned protein structural signatures of thermal adaptation. We hypothesize that biophysical tradeoffs which dictate enzymatic functions across variable temperatures provide a more robust empirical basis for OGT prediction than broad genomic features. Our OGT-predicting model, ROSEATE, is based on a single gene, adenylate kinase (ADK), that encodes for a ubiquitous enzyme essential for energy homeostasis. ROSEATE uses high-dimensional latent space encoding via MSA Transformer, a protein language model which embeds ADKs in a manner which preserves biophysical information about embedded proteins. We show that the accuracy of the ROSEATE model is on par with other genome-based models, has a high degree of phylogenetic generalizability, and the ESM embeddings effectively capture key temperature-adaptive enzyme characteristics derived from AlphaFold structures. Because ROSEATE is based on analyses of a single ubiquitous protein, it can be used with metagenomic data to infer the community-level variation in bacterial OGTs. We demonstrate this feature of ROSEATE by reconstructing ADK sequences from over 500 environmental and host-associated metagenomes, successfully distinguishing community-wide thermal preferences across diverse habitats, from polar oceans to mammalian guts. By transitioning from genomic proxies to informationally dense protein structural features, this work provides an efficient, interpretable tool for predicting bacterial OGTs across taxa and whole communities.

阅读与讨论 → 访问原文 →

21.

PLOS Computational Biology 2026-06-22 DOI: HASH:1e34ce535987e6ddaedc7011657d7e19

Heterogeneous suppressive effect of <i>Wolbachia</i> incompatible insect technique coupled with sterile insect technique across time and historical <i>Ae. aegypti</i> abundance - using distributional synthetic controls

作者:

Yichen Zhai↗

by Yichen Zhai, Chia-Chen Chang, Zhiyong Xi, Cheong Huat Tan, Lee Ching Ng, Jue Tao Lim Background Biological control tools such as Wolbachia incompatible-insect technique, are a promising class of interventions to modify and suppress Aedes aegypti mosquitoes to reduce risk of Aedes-borne diseases. Due to the spatial nature of the intervention, intervention effects can be spatio-temporally heterogeneous. Yet, most evaluations of field-based technologies rely on average treatment effects, which preclude characterization and understanding of treatment effect heterogeneities and the factors influencing it. Methods Here, we developed a causal inference framework using distributional synthetic controls to explicitly account for spatio-temporal trap-level mosquito abundance data to ascertain the entomological efficacy of Wolbachia in suppressing Ae. aegypti abundance. This method is able to construct counterfactual distributions of intervened areas, provide detailed comparisons to actual distributions and quantify treatment effects of the intervention on mosquito abundance over different quantiles. By employing our framework to trap-level mosquito abundance data from 57,990 unique mosquito traps routinely maintained and measured twice a week, and a large-scale field trial of Wolbachia incompatible-insect technique coupled with sterile insect technique (IIT-SIT) in Singapore, we (1) quantified heterogeneous treatment effects for IIT-SIT across the time-since-intervention, over the traps’ historical mosquito abundance, over calendar time, (2) quantified whether elimination of wild-type Aedes aegypti was possible in intervention locations and (3) addressed if suppressive effects in spillover locations adjacent to directly intervened locations were heterogeneous. Results IIT-SIT interventions led to a strong suppressive effect on adult Aedes aegypti abundance. From the onset of intervention in directly treated locations, sector-specific intervention effectiveness (IE) ranged from 24.04% in the earliest treatment period, and reached 86.08% in the latest treatment period. Raw reductions in aegypti abundance were also found to increase over time as sectors were intervened over longer time periods. In spillover sectors, IE was lower in magnitude and more variable, but average IE reached a maximum of 78.08% in 2-years post-treatment. Wolbachia interventions also led to an increase in the percentage of traps recording no mosquitoes from 6.8% at the start of intervention to 33.01% 124-weeks post-intervention. We found that IE was higher in sectors with lower historical mosquito abundance. However, IE converged across sectors with different historical mosquito abundance as intervention time increased. Conclusion This study revealed spatial heterogeneities in suppressing wild-type female Ae. aegypti by IIT-SIT and provided strong evidence that IIT-SIT can drastically suppress wild-type Ae. aegypti populations despite heterogeneous treatment effects over time.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16988

Agent trajectories as programs: fingerprinting and programming coding-agent behavior

作者:

Hamidah Oderinwale↗

arXiv:2606.16988v1 Announce Type: cross Abstract: Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.06113

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

作者:

Huaisong Zhang↗Hao Yu↗Yuxuan Zhang↗Jiahe Wang↗Xinrui Chen↗Haoxiang Cao↗Feng Lu↗Wendong Zhang↗Changqian Yu↗Chun Yuan↗

Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To address this representation bottleneck, we propose Structured Defect Grounding (SDG), which casts T2I diagnosis as structured set prediction by modeling each defect as a (location, type, reason, importance) tuple. To make this formulation trainable and measurable, we introduce SDG-30K, a 30K-image dataset with box-grounded annotations across four modern T2I generators, together with a dedicated evaluation protocol, SDG-Eval. Building on this structured representation, we further present a diagnosis-to-alignment framework in which a Vision-Language Model (VLM) serves as the SDG detector, and BoxFlow-GRPO converts predicted defect sets into box-derived, importance-weighted spatial rewards for diffusion model alignment. Extensive experiments show that our SDG detector outperforms leading proprietary VLMs on structured defect grounding, while SDG-guided rewards consistently improve T2I alignment and support localized image refinement. These results establish SDG as a unified, instance-level interface for diagnosing, evaluating, and enhancing modern generative models.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20457

Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation

作者:

Rostislav Makarov↗Timo Gerkmann↗

arXiv:2606.20457v1 Announce Type: cross Abstract: Classifier guidance is a way to control diffusion generation by using a noise-conditioned classifier to steer the sampling process toward a target class. One drawback of classifier guidance is that it requires two separately trained models: a classifier and a diffusion model. We therefore study a more compact alternative in which a conventionally trained speech classifier is repurposed as the backbone for diffusion generation. Starting from a frozen noise-conditioned classifier in log-Mel space, we attach a lightweight subnetwork that reuses intermediate classifier representations and train only this subnetwork under a Denoising Score Matching objective. Our work shows that a pretrained classifier can be repurposed for conditional generation, providing an appealing bridge between discriminative modeling and conditional speech synthesis resulting in high speech quality within a single-backbone model, with reduced memory footprint and computational cost.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16995

When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning

作者:

Nathan Gavenski↗Juarez Monteiro↗Francisco Galuppo↗Adriano Veloso↗Odinaldo Rodrigues↗

arXiv:2606.16995v1 Announce Type: new Abstract: Reinforcement Learning (RL) policies often degrade in unfamiliar environments because they lack explicit deliberation. We propose Plan, Align, Commit, Think (PACT), a hybrid architecture that combines a fast, reactive RL policy with a slow, deliberative Small Language Model (SLM) planner. PACT invokes the SLM asynchronously to generate and validate candidate action plans. Once a plan is verified through simulation as safe, feasible, and complete, it is executed directly, bypassing the RL policy without retraining or modifying it. Evaluated on three FrozenLake configurations of increasing difficulty, PACT outperforms all baselines while relying on a 2B-parameter SLM backbone, suggesting that deliberative planning and reactive execution are more powerful in concert than either is alone in these settings.

阅读与讨论 → 访问原文 →