Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.AI) 2026-06-24

Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

arXiv:2606.22314v2 Announce Type: replace-cross Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a conditional generative modeling problem. DiffIG first trains a diffusion model to learn a distribution over paths generated from a Stick-Breaking Process, then employs guided sampling to embed user guidance during the sampling procedure. We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations. This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.

02.
arXiv (quant-ph) 2026-06-25

Modelling the Impact of Device Imperfections on Electron Shuttling in SiMOS devices

arXiv:2512.03853v3 Announce Type: replace Abstract: Extensive theoretical and experimental work has established high-fidelity electron shuttling in Si/SiGe systems, whereas demonstrations in Si/SiO2 (SiMOS) remain at an early stage. To help address this, we perform full 3D simulations of conveyor-belt charge shuttling in a realistic SiMOS device, building on earlier 2D modelling. We solve the Poisson and time-dependent Schrodinger equations for varying shuttling speeds and gate voltages, focusing on potential pitfalls of typical SiMOS devices such as oxide-interface roughness, gate fabrication imperfections, and charge defects along the transport path. The simulations reveal that for low clavier-gate voltages, the additional oxide screening in multi-layer gate architectures causes conveyor-belt shuttling to collapse to the bucket-brigade mode, inducing considerable orbital excitation in the process. Increasing the confinement restores conveyor-belt operation, which we find to be robust against interface roughness, gate misalignment, and charge defects buried in the oxide. However, our results indicate that defects located at the Si/SiO2-interface can induce considerable orbital excitation. For lower conveyor gate biases, positive defects in the transport channel can even capture passing electrons. Hence we identify key challenges and find operating regimes for reliable charge transport in SiMOS architectures.

03.
arXiv (quant-ph) 2026-06-19

Subsystem Quantum Error Correction for Noisy Quantum Metrology

arXiv:2606.19628v1 Announce Type: new Abstract: Quantum error correction has been successfully applied to enhance the precision of parameter estimation in the presence of noise. Nonetheless, existing methods require a number of noiseless, controllable ancillae and lack efficient encoding and decoding procedures. In this Letter, we demonstrate that subsystem error correction provides a new direction that can substantially simplify the metrological protocol. We derive general conditions under which subsystem stabilizer codes achieve the Heisenberg limit and show that, for broad classes of noise, this can be realized by syndrome-free protocols using at most a single ancilla qubit. Furthermore, we extend this framework to dynamical error correction and show that Floquet codes can protect time-dependent metrological signals in reaching the Heisenberg limit.

04.
arXiv (math.PR) 2026-06-18

Formation of clusters and coarsening in weakly interacting diffusions

arXiv:2510.17629v3 Announce Type: replace-cross Abstract: This paper studies the clustering behavior of weakly interacting diffusions under the influence of sufficiently localized attractive interaction potentials on the one-dimensional torus. We describe how this clustering behavior is closely related to the presence of discontinuous phase transitions in the mean-field PDE. For local attractive interactions, we employ a new variant of the strict Riesz rearrangement inequality to prove that all global minimizers of the free energy are either uniform or single-cluster states, in the sense that they are symmetrically decreasing. We analyze different timescales for the particle system and the mean-field (McKean-Vlasov) PDE, arguing that while the particle system can exhibit coarsening by both coalescence and diffusive mass exchange between clusters, the clusters in the mean-field PDE are unable to move and coarsening occurs via the mass exchange of clusters. By introducing a new model for this mass exchange, we argue that the PDE exhibits dynamical metastability. We conclude by presenting careful numerical experiments that demonstrate the validity of our model.

05.
arXiv (CS.CL) 2026-06-11

Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation

Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning. While qualitative evidence supports the existence of this effect, its magnitude has not been systematically characterized. This study quantifies subliminal behavioral transfer ratios by steering two teacher models (Llama-2-7B-Chat and Qwen2.5-7B-Instruct) at varying steering strengths and distilling student models using only benign data. Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors. Llama-2 demonstrates a sharp threshold ($\tau = {0.25,0.32} \ beyond \ \alpha = -0.15$), whereas Qwen2.5 displays continuous and higher levels of transfer ($\tau$ up to $0.61$).

06.
arXiv (quant-ph) 2026-06-25

Neural network decoder confidence as a learned proxy for the logical gap

arXiv:2606.08758v2 Announce Type: replace Abstract: To utilize quantum error-correcting codes, a decoder must infer the logical sector from the measured syndrome. Beyond producing a hard logical decision, some decoders provide soft information that estimates the reliability of that decision. For minimum-weight perfect matching (MWPM), a common confidence measure is the complementary, or logical, gap. Here we test whether the logit of a graph neural network (GNN) decoder can act as a learned proxy for the logical gap. Using a pretrained GNN for the rotated surface code under uniform circuit-level noise [Physical Review Research, 7(2):023181, 2025], we compare its soft output with the MWPM complementary gap on the same sampled syndromes. We find that post-selection based on the GNN logit yields a lower logical error rate than one based on the MWPM gap. Shot-by-shot, the signed GNN confidence distribution resembles the signed MWPM gap at low and intermediate values, but assigns higher confidence to many correctly decoded shots. While both scores approximate the posterior log-likelihood ratio, the GNN confidence magnitude is closer to its ideal value. These results show that a neural-network decoder trained only on syndromes and logical labels learns both gap-like discrimination and a quantitative confidence scale, enabling confidence-based post-selection when MWPM gap estimates are unavailable, costly, or poorly matched to the noise model.

07.
arXiv (CS.AI) 2026-06-17

Volterra Generative Models

arXiv:2606.18071v1 Announce Type: cross Abstract: Score-based diffusion models typically use Brownian perturbations, which provide tractable reverse-time dynamics but impose memoryless noising. We introduce Volterra generative models, a continuous-time score-based framework whose forward process injects path-dependent noise through fractional kernels. To handle the non-Markovian and non-semimartingale dynamics, we construct finite-dimensional Markovian lifts using Gaussian quadrature in both regimes and a hybrid finite-difference exponential approximation in the smooth regime. We prove squared error bounds, derive an augmented linear-Gaussian forward process, and show that the learning can remain data-dimensional by considering residual states and analytic auxiliary Gaussian scores. We also identify covariance and reverse-time degeneracies caused by shared Brownian factors and signed smooth-regime weights. The degeneracy motivates stabilized conditioning and, for stiff larger lifts, a Gaussian-bridge reconstruction sampler. Experiments on MNIST and CIFAR-10 show that persistent fractional perturbations with small Markovian lifts can improve score-based generation on MNIST and provide a promising extension to natural images, while the bridge sampler provides a stability mechanism for larger lifts.

08.
arXiv (CS.AI) 2026-06-19

Hybrid ANN-SNN Pipeline with Local Plasticity

arXiv:2606.20151v1 Announce Type: cross Abstract: This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable high-performance spiking neural networks (SNNs). The architecture couples a pretrained EfficientNet encoder with a CoLaNET spiking classifier. We convert the encoder's activations into spike trains via rate-coding and train the subsequent SNN classifier using local, biologically inspired learning rules, bypassing end-to-end gradient propagation. This approach achieves 99.09% accuracy on a 64-class ImageNet benchmark, demonstrating performance on par with conventional deep networks. The work presents a biologically plausible and efficient framework for adapting powerful pretrained encoders to downstream spiking neural network tasks.

09.
arXiv (CS.LG) 2026-06-12

LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning

arXiv:2606.12895v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are well-regarded for their biological plausibility and energy efficiency in processing sequential data. However, dominant SNN architectures typically rely on first-order Ordinary Differential Equations (ODEs) to govern neuronal state transitions. This first-order assumption imposes a "memoryless" bottleneck, limiting the model's capacity to capture the complex, long-range dependencies inherent in long-sequence tasks. In this work, we propose LongSpike, a novel SNN framework that integrates fractional-order State-Space Modeling, or f-SSM, from control theory into the spiking domain. By extending traditional integer-order SSMs to the fractional-calculus regime, LongSpike enables the hierarchical integration of neuronal dynamics with long-memory kernels. To mitigate the computational overhead and parallelization challenges typically associated with fractional operators, we leverage a state-space formulation that supports efficient, parallel training. Empirical evaluations on challenging benchmarks, including Long Range Arena (LRA), large-scale WikiText-103, and Speech Commands, demonstrate that LongSpike outperforms state-of-the-art SNNs in accuracy while preserving sparse synaptic computation. The code is available at https://github.com/xinruihe389-commits/LongSpike.

10.
arXiv (CS.CV) 2026-06-18

When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift

Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, with recent methods increasingly focusing on improving generalization to unseen manipulations. This is typically evaluated using the Area Under the ROC Curve (AUC) measured separately across multiple datasets. However, such an evaluation fails to reflect real-world scenarios where detectors face a mixture of data sources and varying artifact types. To address this limitation, we introduce a novel metric, Cross-dataset AUC (Cross-AUC) that averages per-domain AUCs with a measure of prediction polarization for taking into account the robustness to domain shift. The polarization extent is quantified by the Wasserstein Distance between class score distributions. Cross-AUC not only assesses the generalization capabilities of deepfake detectors under domain shifts more realistically, but it is also interpretable as it better explains the reason behind a drop in performance. Experiments performed on seven benchmark datasets demonstrate its practical relevance.

11.
PLOS Medicine 2026-06-23

Comparisons of core component delivery in cardiac rehabilitation programs by country income classification and decade based on the 2025 Global Audit Update: A survey study

by Gabriela Lima de Melo Ghisi, Rachael P. Carson, Karam Turk Adawi, Rongjing Ding, Warner M. Mampuya, Mariya P. Jiandani, Jimena Martinez, Monserrat Cruz Rivero, Claudia V. Anchique, Dinah L. van Schalkwijk, Jonathan Gallagher, Buket Akinci, Dion Candelaria, Jirapa Champaiboon, Daniel F. Quesada-Chaves, Tone M. Norekvål, Iwona Szadkowska, Borut Jug, Evangelia Kouidi, Marta Supervia, Won-Seok Kim, Chamila Mettananda, Lilian Mbau, Gulsim T. Aimakova, Sherry L. Grace, on behalf of the ICCPR Global Cardiac Rehabilitation Audit Update Investigators Background Cardiovascular disease (CVD) remains a leading global health burden. Cardiac rehabilitation (CR) is essential to reducing morbidity and improving patient outcomes. Since the COVID-19 pandemic, CR delivery worldwide has evolved, yet these changes have not been systematically charactemkjrized. The objective of this study was to characterize globally: (1) the delivery of core CR components, including risk factors assessed, patient education practices, and program resources; (2) differences in these elements by country income classification and relative to the initial 2016 Global CR Audit. Methods and findings A cross-sectional Audit update was conducted. Program-level data were collected from May 1st to September 1st 2025 using a REDCap survey adapted from previous Audits. Eligible respondents were leads of phase II/post-discharge CR programs providing at least an initial assessment, structured aerobic exercise, and ≥1 additional core component. ICCPR associations and local leaders supported program identification. Main outcomes were core components delivered (10 assessed), risk factors assessed (14 assessed), patient education dose (hours/patient/program), and program resources (17 assessed). Generalized linear mixed models (GLMM) tested differences by income classification and (when applicable) changes since 2016. Of 7,025 programs identified globally, 1,505 (62% median country response rate) initiated a survey from 90/113 (80%) countries with CR. The median number of core components offered was 8/program (p25, p75 = 6, 10), with upper-middle income countries offering significantly more components overall (median = 9), and also high-income countries offering more than low-income countries (8 versus 6, p 

12.
arXiv (CS.LG) 2026-06-24

PROTECT-90: A Fault Dataset for Power System Protection

arXiv:2606.24298v1 Announce Type: cross Abstract: The increasing interest in data-driven methods for power system protection is accompanied by a lack of standardized, publicly available high-voltage waveform datasets that enable transparent and reproducible evaluation. To address this gap, this paper introduces the PROTECT-90 dataset, an open electromagnetic transient (EMT)-simulated reference benchmark for high-voltage fault studies with consistent digital-fault-recorder-like measurements, publicly released with this work. The dataset comprises 9,022 physically consistent short-circuit simulation episodes generated on a standardized 90 kV double-line topology with systematically documented domain randomization of grid operating points, line parameters, and fault conditions. For each episode, synchronized three-phase voltage and current waveforms are recorded at eight measurement locations and released together with structured, machine-readable metadata describing fault type, fault location, inception time, and operating conditions. All modeling assumptions, parameter ranges, and data-generation procedures are explicitly documented to ensure transparency and cross-study comparability. By combining physically grounded EMT simulation, balanced scenario coverage, and open accessibility, PROTECT-90 establishes a standardized foundation for reproducible benchmarking of protection-oriented signal processing and learning-based methods.

14.
arXiv (CS.AI) 2026-06-16

The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products

arXiv:2606.15485v1 Announce Type: cross Abstract: Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characteristics can create or exacerbate product risks. We studied how industry developers (n=35) perceive, prioritize, and address the risks in their agentic AI products. We found that developers' perceptions of risk were closely tied to the qualities that made the product agentic, such as autonomy, tool use, and usage in a real-world context. Developers prioritized product and business risks before considering downstream societal risks like job displacement and end-user privacy. This prioritization also impacted developers' ability and motivation to mitigate agentic risks. Finally, developers lacked mature controls for containing agentic risks, often relying on constraining the same characteristics that make agents useful: e.g., autonomy and goal complexity. These findings reveal a capability vs. risk control tension in agentic AI development: developers need to address risks that emerge from agentic capabilities, yet they currently have limited support for doing so without constraining agentic functionality.

15.
arXiv (CS.CV) 2026-06-25

C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation

Histopathological tissue segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels generated by Class Activation Mapping (CAM). Existing CAM approaches tend to focus on staining-driven appearance cues rather than true causal tissue morphology, resulting in spurious localization and poor structural consistency. To address this issue, we propose C$^2$RM-Seg, a two-stage framework that integrates causal pseudo-label refinement with structure-aware semantic enhancement. For classification, we introduce a Causal Counterfactual Reasoning Module (C$^2$RM) that decomposes features into latent factors and performs counterfactual intervention via a learned causal structure matrix, suppressing confounding context and producing morphology-aligned CAMs. For segmentation, we design a Dual-Path Structural-Semantic Architecture that combines fine-grained structural features from ResNeSt with global semantic priors from a frozen DINOV3 foundation model. A cross-path gating mechanism adaptively regulates semantic injection using local structural cues to preserve boundary fidelity. To further mitigate residual pseudo-label noise, we propose an Uncertainty-Gated Margin (UGM) loss, which dynamically balances margin enforcement and confidence learning based on prediction uncertainty. Extensive experiments on two public histopathological tissue datasets show that C$^2$RM-Seg achieves state-of-the-art performance.

16.
arXiv (CS.CL) 2026-06-16

PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino

Large language models (LLMs) process text as sequences of subword tokens, which can obscure the character-level and morphological structure that underlies word formation. This limitation is most acute for languages with non-concatenative morphology, where standard tokenizers systematically misalign token boundaries with morpheme boundaries. We introduce PACUTE, a diagnostic benchmark of 4,600 tasks designed to evaluate morphological understanding in Filipino, a language characterized by productive infixation, reduplication, and diacritic-driven lexical distinctions that are typically absent from written text. PACUTE includes a hierarchical diagnostic framework of six compositional levels that localizes where morphological understanding breaks down. Evaluating open-weight LLMs and frontier commercial models, we find that open-weight models perform near chance on morpheme decomposition regardless of scale. Frontier models perform much better, often recovering individual affixes under contains-match scoring, but remain far below their character-level ceilings on compositional tasks of morpheme transformations and syllabification. These results identify productive morphological composition, rather than character access alone, as the persistent bottleneck for Filipino word-structure understanding.

17.
arXiv (CS.AI) 2026-06-18

PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization

arXiv:2606.18518v1 Announce Type: cross Abstract: The development of medical AI is constrained by limited access to high-quality clinical data due to institutional silos and strict privacy regulations such as HIPAA and GDPR. Synthetic data generation offers a potential solution, but existing methods lack principled mechanisms to explicitly manage the privacy-utility trade-off, often degrading clinically meaningful patterns or risking patient re-identification. We present PSyGenTAB, a privacy-preserving generative framework that formulates synthetic healthcare data generation as a constrained optimization problem solved using the Augmented Lagrangian Method. By embedding configurable privacy constraints directly into model training, PSyGenTAB enforces minimum privacy thresholds while maximizing clinical data utility. Across multiple clinically motivated benchmarks, PSyGenTAB preserves inter-feature clinical relationships and minority-class diagnostic patterns essential for reliable health AI. Downstream evaluation using Train-on-Synthetic, Test-on-Real and Train-on-Real, Test-on-Synthetic protocols shows that models trained on synthetic data achieve performance comparable to those trained on real patient records. Privacy auditing further demonstrates reduced exact record reproduction and strong resilience to membership inference attacks. These results establish PSyGenTAB as a principled framework for balancing privacy protection and clinical utility in synthetic healthcare data, supporting secure cross-institutional AI development.

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

A Technical Taxonomy of LLM Agent Communication Protocols

arXiv:2606.19135v1 Announce Type: cross Abstract: As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructure for distributed agent networks. Nonetheless, the fragmented protocol landscape presents a significant interoperability challenge. This study develops a technical taxonomy to classify and analyze LLM agent communication protocols. Following an established iterative method, we defined the taxonomy's purpose, meta-characteristic, and ending conditions, then performed five iterations, three empirical-to-conceptual and two conceptual-to-empirical, on nine actively maintained open-source protocols with demonstrable adoption. The taxonomy comprises five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Classification reveals recurring architectural patterns: all sampled agent-to-agent protocols combine hybrid payloads with session-state persistence; most protocols support multiple predefined schemas, and two negotiate schemas at runtime, indicating a trend toward schema flexibility; decentralized discovery remains rare. Analysis suggests short-term convergence pressure toward protocols unifying agent-to-agent and agent-to-context (tool and data) communication. Long-term, however, no single protocol is likely to maximize versatility, efficiency, and portability simultaneously. The field will more likely evolve toward a federated, layered protocol stack. The framework guides protocol selection and highlights open research gaps such as privacy and policy enforcement.}

19.
arXiv (CS.CV) 2026-06-16

BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data

Insect classification is important for agricultural management and ecological research, as it directly affects crop health and production. However, this task remains challenging due to the complex characteristics of insects, class imbalance, and large-scale datasets. To address these issues, we propose BioAutoML-NAS, the first BioAutoML model using multimodal data, including images, and metadata, which applies neural architecture search (NAS) for images to automatically learn the best operations for each connection within each cell. Multiple cells are stacked to form the full network, each extracting detailed image feature representations. A multimodal fusion module combines image embeddings with metadata, allowing the model to use both visual and categorical biological information to classify insects. An alternating bi-level optimization training strategy jointly updates network weights and architecture parameters, while zero operations remove less important connections, producing sparse, efficient, and high-performing architectures. Extensive evaluation on the BIOSCAN-5M dataset demonstrates that BioAutoML-NAS achieves 96.81% accuracy, 97.46% precision, 96.81% recall, and a 97.05% F1 score, outperforming state-of-the-art transfer learning, transformer, AutoML, and NAS methods by approximately 16%, 10%, and 8% respectively. Further validation on the Insects-1M dataset obtains 93.25% accuracy, 93.71% precision, 92.74% recall, and a 93.22% F1 score. These results demonstrate that BioAutoML-NAS provides accurate, confident insect classification that supports modern sustainable farming.

20.
arXiv (quant-ph) 2026-06-19

Quantum Batteries as Work Sources for Phase-Locked Parametric Amplification

Authors:

arXiv:2606.20306v1 Announce Type: new Abstract: Quantum batteries have been proposed as locally precharged work sources for superconducting quantum technologies, suggesting a route to reduce continuously supplied microwave drives. Here we ask whether the pump tone of a quantum-limited parametric amplifier can be replaced, or strongly duty-cycled, by a finite bosonic quantum battery. Quantizing the pump of a nondegenerate parametric amplifier exposes a resource distinction hidden in the classical description: stored pump energy can generate signal-idler photons, but pump phase coherence is required to generate a phase-locked amplifier field. In a closed trilinear model, coherent and phase-randomized coherent pumps with the same photon-number distribution produce comparable pair numbers, yet only the coherent pump produces anomalous two-mode coherence and an EPR-squeezed interference dip. Including leakage, we collect the emitted fields into cascaded temporal modes. At matched collector bandwidth, the coherent pump gives \(I_{\min}^{(f)}=0.553\), whereas the phase-randomized pump gives \(I_{\min}^{(f)}=1.94\) at nearly identical collected energy. Weak amplitude squeezing slightly improves the dip by reducing finite-pump number fluctuations while preserving the coherent displacement. Thus battery-powered parametric amplification requires phase-coherent stored energy, possibly assisted by number-noise reduction, rather than stored energy alone.

21.
arXiv (CS.CL) 2026-06-17

Structural Role Injection in Handlebars-Templated LLM Prompts: Triple-Brace Interpolation, Delimiter Family, and the Limits of HTML Auto-Escaping

Large language model applications build prompts from templates, and Handlebars is a widely used templating engine and the default prompt-template format in Microsoft Semantic Kernel. Its double-brace {{x}} expression HTML-escapes the interpolated value and is documented as the safe default; its triple-brace {{{x}}} expression inserts the value raw. We show that this choice silently governs an application's exposure to structural role injection, where attacker-controlled data carries chat role delimiters that forge a higher-privilege turn. A model-free analysis establishes the mechanism: Handlebars escaping rewrites angle brackets but not square brackets, colons, or Markdown hashes, so it neutralises ChatML, Llama-3, and XML role delimiters (survival rate 0.00) while leaving Llama-2 [INST], legacy Human:/Assistant:, and Markdown ### delimiters intact (survival rate 1.00 for the last two). We then run 5760 trials across seven delimiter families, two attack objectives, and four models (GPT-3.5 Turbo, GPT-4o mini, GPT-4.1 mini, Claude Haiku 4.5) at a combined API cost of 1.63 USD. GPT-3.5 Turbo follows the task-hijack instruction in 97% of raw and 91% of escaped trials, with the escaping protection concentrated in the angle-bracket families and absent for the colon- and Markdown-based families; the harder secret-exfiltration objective, which does not saturate, exposes the same family interaction more cleanly. Claude Haiku 4.5 resists both objectives almost entirely. The escaped default protects only the delimiter schemes whose characters HTML escaping happens to cover, gives no protection for the rest, and cannot substitute for a structural separation of instruction and data.

22.
arXiv (quant-ph) 2026-06-16

Instrument-based quantum resources: quantification, hierarchies and towards constructing resource theories

arXiv:2508.09134v3 Announce Type: replace Abstract: Quantum resources are certain features of the quantum world that provide advantages in certain information-theoretic, thermodynamic, or other useful operational tasks that are outside the realm of what classical theories can achieve. Quantum resource theories provide us with an elegant framework for studying these resources quantitatively and rigorously. While numerous state-based quantum resource theories have already been investigated, and to some extent, measurement-based resource theories have also been explored, instrument-based resource theories remain largely unexplored, with only a few notable exceptions. As quantum instruments are devices that provide both the classical outcomes of induced measurements and the post-measurement quantum states, they are quite important, especially for scenarios where multiple parties sequentially act on a quantum system. In this work, we study several instrument-based resource theories, namely (1) the resource theory of information preservability, (2) the resource theory of (strong) entanglement preservability, (3) the resource theory of (strong) incompatibility preservability, (4) the resource theory of traditional incompatibility, and (5) the resource theory of parallel incompatibility. Furthermore, we outline the hierarchies of these instrument-based resources and provide measures to quantify them. We then also established a relationship between our resource measure and the advantage in an information-theoretic task. In short, we provide a detailed framework for a wide variety of instrument-based quantum resource theories.

23.
arXiv (CS.CV) 2026-06-16

Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

Fundus fluorescein angiography (FFA) is critical for assessing retinal vascular abnormalities, but its acquisition is invasive and not always feasible. In contrast, color fundus photography (CFP) is non-invasive and widely accessible, which has motivated studies on CFP-to-FFA synthesis. However, prior works rely solely on CFP surface texture, fundamentally limiting the ability to reconstruct functional vascular information and subtle pathological changes. To address this, we propose a novel framework that synthesizes FFA from CFP with structural guidance provided by optical coherence tomography (OCT). We construct a multi-modal retinal imaging dataset with paired CFP, FFA, and OCT from 3,676 patient eyes–the first tri-modally aligned dataset in retinal imaging. To bridge the spatial gap between OCT and fundus modalities, we propose a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects depth-resolved OCT features onto the fundus plane and injects them into the CFP encoder via adaptive layer normalization. Beyond feature fusion, we further introduce Token-wise Cross-Modality Alignment (TCMA), a token-level contrastive learning strategy that explicitly aligns CFP and FFA representations at corresponding spatial positions. Our method achieves superior synthesis performance compared to state-of-the-art methods. Moreover, extensive experiments demonstrate that the FFA images synthesized by our approach bring greater improvements in downstream disease diagnosis performance than existing methods, highlighting the clinical potential of our approach as a non-invasive decision-support tool in routine workflows. The code is available at https://github.com/while-plus/OCT-guide-FFA-Syn.

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

Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval

Composed image retrieval retrieves a target image using a composed query of a reference image and a modified text description. In the fashion domain, this task requires understanding subtle attribute variations such as color, pattern, and texture. However, existing approaches face limitations due to scarce annotated data and simplistic negative sampling. We propose a novel framework that integrates a multi-modal large language model (LLaVA) to generate attribute-aware triplets and introduces a two-stage fine-tuning strategy to enhance contrastive learning. We leverage pretrained vision-language models, such as CLIP-ViT/B32, to generate and concatenate sentence-level prompts with the relative caption and to scale the number of negatives using static representations. Experimental results demonstrate enhanced compositional reasoning and improved fine-grained retrieval behavior, underscoring the feasibility and potential of the proposed framework for fashion retrieval.

25.
medRxiv (Medicine) 2026-06-23

Unscreenable: The Burden, Structure, and Analytic Consequences of "Unable to Assess" Delirium Documentation in the Intensive Care Unit

Objective: To quantify the burden, structure, and downstream analytic consequences of "Unable to Assess" (UTA) delirium documentation in the intensive care unit (ICU). Design: Retrospective cross-sectional and repeated-measures study. Setting: A single US academic medical center (Medical Information Mart for Intensive Care IV [MIMIC-IV], 2008-2019). Patients: 72,944 adult ICU stays with at least 1 delirium screen. Interventions: None. Measurements and Main Results: Among 610,632 screens, 130,455 (21.4%; 95% CI, 21.0%-21.8%) were recorded as UTA, exceeding the 119,052 (19.5%) scored positive. The UTA fraction rose from 2.0% at a Richmond Agitation-Sedation Scale (RASS) score of 0 to 97.8% at RASS -4; 22.0% of UTA screens occurred in arousable patients, where UTA was associated with mechanical ventilation (odds ratio [OR], 3.43; 95% CI, 3.17-3.71) and non-English primary language (OR, 3.74; 95% CI, 3.43-4.08). Building the delirium label three ways from the same patients shifted prevalence modestly (32.1% to 30.8%) and prediction (area under the curve, 0.737 to 0.719) but most affected the delirium-mortality association: in a baseline-adjusted model the OR was 4.12 (95% CI, 3.88-4.36) under complete-case handling and fell to 2.16 (95% CI, 2.06-2.27) when UTA was recoded as negative. UTA was recoverable from the observed clinical state (area under the curve, 0.95). Conclusions: In this ICU cohort, Unable to Assess was the most common recorded delirium result other than Negative, exceeding positive screens; recoding it as negative roughly halved the apparent delirium-mortality association by relabeling deeply sedated, high-mortality patients. Delirium datasets should preserve and report UTA, whose concentration among arousable non-English-speaking patients is a measurable equity target.