Background and objective: Micro-ultrasound (micro-US) is a novel imaging modality with diagnostic accuracy comparable to MRI for detecting clinically significant prostate cancer (csPCa). We investigated whether artificial intelligence (AI) interpretation of micro-US can outperform clinical screening methods using PSA and digital rectal examination (DRE). Methods: We retrospectively studied 145 men who underwent micro-US guided biopsy (79 with csPCa, 66 without). A self-supervised convolutional autoencoder was used to extract deep image features from 2D micro-US slices. Random forest classifiers were trained using five-fold cross-validation to predict csPCa at the slice level. Patients were classified as csPCa-positive if 88 or more consecutive slices were predicted positive. Model performance was compared with a classifier using PSA, DRE, prostate volume, and age. Key findings and limitations: The AI-based micro-US model and clinical screening model achieved AUROCs of 0.871 and 0.753, respectively. At a fixed threshold, the micro-US model achieved 92.5% sensitivity and 68.1% specificity, while the clinical model showed 96.2% sensitivity but only 27.3% specificity. Limitations include a retrospective single-center design and lack of external validation. Conclusions and clinical implications: AI-interpreted micro-US improves specificity while maintaining high sensitivity for csPCa detection. This method may reduce unnecessary biopsies and serve as a low-cost alternative to PSA-based screening. Patient summary: We developed an AI system to analyze prostate micro-ultrasound images. It outperformed PSA and DRE in detecting aggressive cancer and may help avoid unnecessary biopsies.
Retinal imaging has emerged as a powerful, non-invasive modality for detecting and quantifying biomarkers of systemic diseases-ranging from diabetes and hypertension to Alzheimer's disease and cardiovascular disorders but current insights remain dispersed across platforms and specialties. Recent technological advances in optical coherence tomography (OCT/OCTA) and adaptive optics (AO) now deliver ultra-high-resolution scans (down to 5 {\mu}m ) with superior contrast and spatial integration, allowing early identification of microvascular abnormalities and neurodegenerative changes. At the same time, AI-driven and machine learning (ML) algorithms have revolutionized the analysis of large-scale retinal datasets, increasing sensitivity and specificity; for example, deep learning models achieve > 90 \% sensitivity for diabetic retinopathy and AUC = 0.89 for the prediction of cardiovascular risk from fundus photographs. The proliferation of mobile health technologies and telemedicine platforms further extends access, reduces costs, and facilitates community-based screening and longitudinal monitoring. Despite these breakthroughs, translation into routine practice is hindered by heterogeneous imaging protocols, limited external validation of AI models, and integration challenges within clinical workflows. In this review, we systematically synthesize the latest OCT/OCT and AO developments, AI/ML approaches, and mHealth/Tele-ophthalmology initiatives and quantify their diagnostic performance across disease domains. Finally, we propose a roadmap for multicenter protocol standardization, prospective validation trials, and seamless incorporation of retinal screening into primary and specialty care pathways-paving the way for precision prevention, early intervention, and ongoing treatment of life-threatening systemic diseases.
Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior work has predominantly focused on acoustic-level perturbations, leaving the impact of linguistic variation largely unexplored. In this paper, we investigate the linguistic sensitivity of both open-source and commercial anti-spoofing detectors by introducing transcript-level adversarial attacks. Our extensive evaluation reveals that even minor linguistic perturbations can significantly degrade detection accuracy: attack success rates surpass 60% on several open-source detector-voice pairs, and notably one commercial detection accuracy drops from 100% on synthetic audio to just 32%. Through a comprehensive feature attribution analysis, we identify that both linguistic complexity and model-level audio embedding similarity contribute strongly to detector vulnerability. We further demonstrate the real-world risk via a case study replicating the Brad Pitt audio deepfake scam, using transcript adversarial attacks to completely bypass commercial detectors. These results highlight the need to move beyond purely acoustic defenses and account for linguistic variation in the design of robust anti-spoofing systems. All source code will be publicly available.
Synthesizing expressive Japanese character speech poses unique challenges due to pitch-accent sensitivity and stylistic variability. This paper benchmarks two open-source text-to-speech models--VITS and Style-BERT-VITS2 JP Extra (SBV2JE)--on in-domain, character-driven Japanese speech. Using three character-specific datasets, we evaluate models across naturalness (mean opinion and comparative mean opinion score), intelligibility (word error rate), and speaker consistency. SBV2JE matches human ground truth in naturalness (MOS 4.37 vs. 4.38), achieves lower WER, and shows slight preference in CMOS. Enhanced by pitch-accent controls and a WavLM-based discriminator, SBV2JE proves effective for applications like language learning and character dialogue generation, despite higher computational demands.
Reliable automatic seizure detection from long-term EEG remains a challenge, as current machine learning models often fail to generalize across patients or clinical settings. Manual EEG review remains the clinical standard, underscoring the need for robust models and standardized evaluation. To rigorously assess algorithm performance, we organized a challenge using a private dataset of continuous EEG recordings from 65 subjects (4,360 hours). Expert neurophysiologists annotated the data, providing ground truth for seizure events. Participants were required to detect seizure onset and duration, with evaluation based on event-based metrics, including sensitivity, precision, F1-score, and false positives per day. The SzCORE framework ensured standardized evaluation. The primary ranking criterion was the event-based F1-score, reflecting clinical relevance by balancing sensitivity and false positives. The challenge received 30 submissions from 19 teams, with 28 algorithms evaluated. Results revealed wide variability in performance, with a top F1-score of 43% (sensitivity 37%, precision 45%), highlighting the ongoing difficulty of seizure detection. The challenge also revealed a gap between reported performance and real-world evaluation, emphasizing the importance of rigorous benchmarking. Compared to previous challenges and commercial systems, the best-performing algorithm in this contest showed improved performance. Importantly, the challenge platform now supports continuous benchmarking, enabling reproducible research, integration of new datasets, and clinical evaluation of seizure detection algorithms using a standardized framework.
Cardiac digital twins (CDT) are emerging as a potentially transformative tool in cardiology. A critical yet understudied determinant of CDT accuracy is the His-Purkinje system (HPS), which influences ventricular depolarization and shapes the QRS complex of the electrocardiogram (ECG). Here, we quantify how structural variations in the HPS alter QRS morphology and identify which parameters drive this variability. We generated HPS structures using a fractal-tree, rule-based algorithm, systematically varying nine model parameters and assessing their effects on ten QRS-related metrics. We conducted a Sobol sensitivity analysis to quantify direct and interaction-driven contributions of each parameter to observed variability. Our results suggest that most minor changes in HPS structure exert minimal influence on individual QRS features; however, certain parameter combinations can produce abnormal QRS morphologies. Wave durations and peak amplitudes of the QRS complex exhibit low sensitivity to individual HPS parameter variations; however, we found that specific parameter combinations can result in interactions that significantly alter these aspects of QRS morphology. We found that certain HPS structures can cause premature QRS formation, obscuring P-wave formation. QRS timing variability was primarily driven by interactions among branch and fascicle angles and branch repulsivity, though other parameters also showed notable interaction effects. In addition to interactions, individual variations in the number of branches in the HPS also affected QRS timing. While future models should account for these potential sources of variability, this study indicates that minor anatomical differences between a healthy patient's HPS and that of a generic model are unlikely to significantly impact model fidelity or clinical interpretation when both systems are physiologically normal.
The given paper emphasizes the importance of the Railway Silk Road for promoting Georgia's economic growth and development. The article notes that economic integration in the region increases cargo turnover in Central Asia and the Caucasus, thus boosting the volume of goods transported through Georgia and contributing to the sustainability of Georgia's macroeconomic and economic growth. The financial economic models aim to identify causal links between the sensitivity of railway cargo and the country's economic growth. The main task of the research was to use the Railway EVA and the Georgian economy to create a cargo sensitivity relationship between CAGR models. The paper analyzes key scientific problems regarding railway freight transportation studies. Calculations are provided for the share of the Railway System in the country's GDP for 2006-2017, as well as the average annual geometric (CAGR) growth of cargo volumes over a 16-year cycle, allowing Georgian Railway JSC to generate additional value in the country's overall GDP. The research shows that the added value to GDP comes in direct and indirect forms through the development and growth of various sectors of Georgia's economy, as some of the cargo shipped by railway remains in Georgia and is used in production, thereby adding value to the country's economic growth. The use of this model by foreign research centers also provides further opportunities for the economic growth of their countries.
Video quality assessment (VQA) is a challenging research topic with broad applications. Effective VQA necessitates sensitivity to pixel-level distortions and a comprehensive understanding of video context to accurately determine the perceptual impact of distortions. Traditional hand-crafted and learning-based VQA models mainly focus on pixel-level distortions and lack contextual understanding, while recent LLM-based models struggle with sensitivity to small distortions or handle quality scoring and description as separate tasks. To address these shortcomings, we introduce CP-LLM: a Context and Pixel aware Large Language Model. CP-LLM is a novel multimodal LLM architecture featuring dual vision encoders designed to independently analyze perceptual quality at both high-level (video context) and low-level (pixel distortion) granularity, along with a language decoder subsequently reasons about the interplay between these aspects. This design enables CP-LLM to simultaneously produce robust quality scores and interpretable quality descriptions, with enhanced sensitivity to pixel distortions (e.g. compression artifacts). The model is trained via a multi-task pipeline optimizing for score prediction, description generation, and pairwise comparisons. Experiment results demonstrate that CP-LLM achieves state-of-the-art cross-dataset performance on established VQA benchmarks and superior robustness to pixel distortions, confirming its efficacy for comprehensive and practical video quality assessment in real-world scenarios.
While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This vulnerability manifests itself as the order bias observed when LLMs decide between possible options (for example, a preference for the first option) and the tendency of LLMs to provide different answers when options are reordered. The use cases for this scenario extend beyond the classical case of multiple-choice question answering to the use of LLMs as automated evaluators in AI pipelines, comparing output generated by different models. We introduce Set-LLM, a novel architectural adaptation for pretrained LLMs that enables the processing of mixed set-text inputs with permutation invariance guarantees. The adaptations involve a new attention mask and new positional encodings specifically designed for sets. We provide a theoretical proof of invariance and demonstrate through experiments that Set-LLM can be trained effectively, achieving comparable or improved performance and maintaining the runtime of the original model, while eliminating order sensitivity.
We present a neural framework for learning conditional optimal transport (OT) maps between probability distributions. Our approach introduces a conditioning mechanism capable of processing both categorical and continuous conditioning variables simultaneously. At the core of our method lies a hypernetwork that generates transport layer parameters based on these inputs, creating adaptive mappings that outperform simpler conditioning methods. Comprehensive ablation studies demonstrate the superior performance of our method over baseline configurations. Furthermore, we showcase an application to global sensitivity analysis, offering high performance in computing OT-based sensitivity indices. This work advances the state-of-the-art in conditional optimal transport, enabling broader application of optimal transport principles to complex, high-dimensional domains such as generative modeling and black-box model explainability.
Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We first introduce the CTF-Code benchmark, constructed using counterfactual perturbations, minimizing input changes while maximizing output changes. The evaluation shows that many LLMs have a more than 10\% performance drop compared to the original problems. To fully utilize sensitivity, CTF-Instruct, an incremental instruction fine-tuning framework, extends on existing data and uses a selection mechanism to meet the three dimensions of difficulty, diversity, and sensitivity. Experiments show that LLMs fine-tuned with CTF-Instruct data achieve over a 2\% improvement on CTF-Code, and more than a 10\% performance boost on LiveCodeBench, validating the feasibility of enhancing LLMs' sensitivity to improve performance.
We say that a classifier is \emph{adversarially robust} to perturbations of norm $r$ if, with high probability over a point $x$ drawn from the input distribution, there is no point within distance $\le r$ from $x$ that is classified differently. The \emph{boundary volume} is the probability that a point falls within distance $r$ of a point with a different label. This work studies the task of computationally efficient learning of hypotheses with small boundary volume, where the input is distributed as a subgaussian isotropic log-concave distribution over $\mathbb{R}^d$. Linear threshold functions are adversarially robust; they have boundary volume proportional to $r$. Such concept classes are efficiently learnable by polynomial regression, which produces a polynomial threshold function (PTF), but PTFs in general may have boundary volume $\Omega(1)$, even for $r \ll 1$. We give an algorithm that agnostically learns linear threshold functions and returns a classifier with boundary volume $O(r+\varepsilon)$ at radius of perturbation $r$. The time and sample complexity of $d^{\tilde{O}(1/\varepsilon^2)}$ matches the complexity of polynomial regression. Our algorithm augments the classic approach of polynomial regression with three additional steps: a) performing the $\ell_1$-error regression under noise sensitivity constraints, b) a structured partitioning and rounding step that returns a Boolean classifier with error $\textsf{opt} + O(\varepsilon)$ and noise sensitivity $O(r+\varepsilon)$ simultaneously, and c) a local corrector that ``smooths'' a function with low noise sensitivity into a function that is adversarially robust.
We introduce a novel framework for differentially private (DP) statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveraging techniques from truncated statistics, we develop computationally efficient DP estimators for exponential family distributions, including Gaussian mean and covariance estimation, achieving near-optimal sample complexity. Previous works on exponential families only consider bounded or one-dimensional families. Our approach mitigates sensitivity through truncation while carefully correcting for the introduced bias using maximum likelihood estimation and DP stochastic gradient descent. Along the way, we establish improved uniform convergence guarantees for the log-likelihood function of exponential families, which may be of independent interest. Our results provide a general blueprint for DP algorithm design via truncated statistics.
Although modern Large Language Models (LLMs) support extremely large contexts, their effectiveness in utilizing long context for code reasoning remains unclear. This paper investigates LLM reasoning ability over code snippets within large repositories and how it relates to their recall ability. Specifically, we differentiate between lexical code recall (verbatim retrieval) and semantic code recall (remembering what the code does). To measure semantic recall, we propose SemTrace, a code reasoning technique where the impact of specific statements on output is attributable and unpredictable. We also present a method to quantify semantic recall sensitivity in existing benchmarks. Our evaluation of state-of-the-art LLMs reveals a significant drop in code reasoning accuracy as a code snippet approaches the middle of the input context, particularly with techniques requiring high semantic recall like SemTrace. Moreover, we find that lexical recall varies by granularity, with models excelling at function retrieval but struggling with line-by-line recall. Notably, a disconnect exists between lexical and semantic recall, suggesting different underlying mechanisms. Finally, our findings indicate that current code reasoning benchmarks may exhibit low semantic recall sensitivity, potentially underestimating LLM challenges in leveraging in-context information.
Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this tradeoff by varying the numerical precision across network layers. This study focuses on automatically selecting an optimal MP configuration within Post-Training Quantization (PTQ) for inference. The first key contribution is a novel sensitivity metric derived from a first-order Taylor series expansion of the loss function as a function of quantization errors in weights and activations. This metric, based on the Mean Square Error (MSE) of the loss, is efficiently calculated per layer using high-precision forward and backward passes over a small calibration dataset. The metric is additive across layers, with low calibration memory overhead as weight optimization is unnecessary. The second contribution is an accurate hardware-aware method for predicting MP time gain by modeling it as additive for sequential sub-graphs. An algorithm partitions the model graph into sequential subgraphs, measuring time gain for each configuration using a few samples. After calibrating per-layer sensitivity and time gain, an Integer Programming (IP) problem is formulated to maximize time gain while keeping loss MSE below a set threshold. Memory gain and theoretical time gain based on Multiply and Accumulate (MAC) operations are also considered. Rigorous experiments on the Intel Gaudi 2 accelerator validate the approach on several Large Language Models (LLMs).
With the rapid improvement of machine learning (ML) models, cognitive scientists are increasingly asking about their alignment with how humans think. Here, we ask this question for computer vision models and human sensitivity to geometric and topological (GT) concepts. Under the core knowledge account, these concepts are innate and supported by dedicated neural circuitry. In this work, we investigate an alternative explanation, that GT concepts are learned ``for free'' through everyday interaction with the environment. We do so using computer visions models, which are trained on large image datasets. We build on prior studies to investigate the overall performance and human alignment of three classes of models -- convolutional neural networks (CNNs), transformer-based models, and vision-language models -- on an odd-one-out task testing 43 GT concepts spanning seven classes. Transformer-based models achieve the highest overall accuracy, surpassing that of young children. They also show strong alignment with children's performance, finding the same classes of concepts easy vs. difficult. By contrast, vision-language models underperform their vision-only counterparts and deviate further from human profiles, indicating that na\"ive multimodality might compromise abstract geometric sensitivity. These findings support the use of computer vision models to evaluate the sufficiency of the learning account for explaining human sensitivity to GT concepts, while also suggesting that integrating linguistic and visual representations might have unpredicted deleterious consequences.
Ensuring the safety of large language models (LLMs) is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical dimensions: hallucination and reliability, social biases, and harmful content generation. Our evaluation of 17 state-of-the-art LLMs reveals patterns of systematic vulnerabilities across all safety dimensions, including sycophancy, prompt sensitivity, and stereotype reproduction. By highlighting these specific failure modes rather than simply ranking models, Phare provides researchers and practitioners with actionable insights to build more robust, aligned, and trustworthy language systems.
Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW) content, such as pornography, violence, political content, and discrimination. To mitigate the risk of generating NSFW content, refusal mechanisms, i.e., safety checkers, have been developed to check potential NSFW content. Adversarial prompting techniques have been developed to evaluate the robustness of the refusal mechanisms. The key challenge remains to subtly modify the prompt in a way that preserves its sensitive nature while bypassing the refusal mechanisms. In this paper, we introduce TokenProber, a method designed for sensitivity-aware differential testing, aimed at evaluating the robustness of the refusal mechanisms in T2I models by generating adversarial prompts. Our approach is based on the key observation that adversarial prompts often succeed by exploiting discrepancies in how T2I models and safety checkers interpret sensitive content. Thus, we conduct a fine-grained analysis of the impact of specific words within prompts, distinguishing between dirty words that are essential for NSFW content generation and discrepant words that highlight the different sensitivity assessments between T2I models and safety checkers. Through the sensitivity-aware mutation, TokenProber generates adversarial prompts, striking a balance between maintaining NSFW content generation and evading detection. Our evaluation of TokenProber against 5 safety checkers on 3 popular T2I models, using 324 NSFW prompts, demonstrates its superior effectiveness in bypassing safety filters compared to existing methods (e.g., 54%+ increase on average), highlighting TokenProber's ability to uncover robustness issues in the existing refusal mechanisms.
There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ideal "ground-truth" explanations, or by verifying model sensitivity to important inputs. We outline the limitations of these approaches, and propose three desirable principles to ground the future development of explanation evaluation strategies for local feature importance explanations. We propose a ground-truth Agnostic eXplanation Evaluation framework (AXE) for evaluating and comparing model explanations that satisfies these principles. Unlike prior approaches, AXE does not require access to ideal ground-truth explanations for comparison, or rely on model sensitivity - providing an independent measure of explanation quality. We verify AXE by comparing with baselines, and show how it can be used to detect explanation fairwashing. Our code is available at https://github.com/KaiRawal/Evaluating-Model-Explanations-without-Ground-Truth.
This paper presents a novel framework for prioritizing urban green space development in Tehran using diverse socio-economic, environmental, and sensitivity indices. The indices were derived from various sources including Google Earth Engine, air pollution measurements, municipal reports and the Weather Research & Forecasting (WRF) model. The WRF model was used to estimate the air temperature at a 1 km resolution due to insufficient meteorological stations, yielding RMSE and MAE values of 0.96{\deg}C and 0.92{\deg}C, respectively. After data preparation, several machine learning models were used for binary vegetation cover classification including XGBoost, LightGBM, Random Forest (RF) and Extra Trees. RF achieved the highest performance, exceeding 94% in Overall Accuracy, Recall, and F1-score. Then, the probability of areas lacking vegetation cover was assessed using socio-economic, environmental and sensitivity indices. This resulted in the RF generating an urban green space development prioritization map. Feature Importance Analysis revealed that the most significant indices were nightly land surface temperature (LST) and sensitive population. Finally, the framework performance was validated through microclimate simulation to assess the critical areas after and before the green space development by green roofs. The simulation demonstrated reducing air temperature by up to 0.67{\deg}C after utilizing the green roof technology in critical areas. As a result, this framework provides a valuable tool for urban planners to develop green spaces.