In this paper, we propose Mix-QViT, an explainability-driven MPQ framework that systematically allocates bit-widths to each layer based on two criteria: layer importance, assessed via Layer-wise Relevance Propagation (LRP), which identifies how much each layer contributes to the final classification, and quantization sensitivity, determined by evaluating the performance impact of quantizing each layer at various precision levels while keeping others layers at a baseline. Additionally, for post-training quantization (PTQ), we introduce a clipped channel-wise quantization method designed to reduce the effects of extreme outliers in post-LayerNorm activations by removing severe inter-channel variations. We validate our approach by applying Mix-QViT to ViT, DeiT, and Swin Transformer models across multiple datasets. Our experimental results for PTQ demonstrate that both fixed-bit and mixed-bit methods outperform existing techniques, particularly at 3-bit, 4-bit, and 6-bit precision. Furthermore, in quantization-aware training, Mix-QViT achieves superior performance with 2-bit mixed-precision.
Purpose: Diabetic retinopathy (DR) is a major cause of vision loss, particularly in India, where access to retina specialists is limited in rural areas. This study aims to evaluate the Artificial Intelligence-based Diabetic Retinopathy Screening System (AIDRSS) for DR detection and prevalence assessment, addressing the growing need for scalable, automated screening solutions in resource-limited settings. Approach: A multicentric, cross-sectional study was conducted in Kolkata, India, involving 5,029 participants and 10,058 macula-centric retinal fundus images. The AIDRSS employed a deep learning algorithm with 50 million trainable parameters, integrated with Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing for enhanced image quality. DR was graded using the International Clinical Diabetic Retinopathy (ICDR) Scale, categorizing disease into five stages (DR0 to DR4). Statistical metrics including sensitivity, specificity, and prevalence rates were evaluated against expert retina specialist assessments. Results: The prevalence of DR in the general population was 13.7%, rising to 38.2% among individuals with elevated random blood glucose levels. The AIDRSS achieved an overall sensitivity of 92%, specificity of 88%, and 100% sensitivity for detecting referable DR (DR3 and DR4). These results demonstrate the system's robust performance in accurately identifying and grading DR in a diverse population. Conclusions: AIDRSS provides a reliable, scalable solution for early DR detection in resource-constrained environments. Its integration of advanced AI techniques ensures high diagnostic accuracy, with potential to significantly reduce the burden of diabetes-related vision loss in underserved regions.
Extremum-seeking control (ESC) is widely used to optimize performance when the system dynamics are uncertain. However, sensitivity to sensor noise is an important issue in ESC implementation due to the use of high-pass filters or gradient estimators. To reduce the sensitivity of ESC to noise, this paper investigates the use of adaptive input and state estimation (AISE) for numerical differentiation. In particular, this paper develops extremum-seeking control with adaptive input and state estimation (ESC/AISE), where the high-pass filter of ESC is replaced by AISE to improve performance under sensor noise. The effectiveness of ESC/AISE is illustrated via numerical examples.
Large language models (LLMs) are increasingly being deployed in high-stakes applications like hiring, yet their potential for unfair decision-making and outcomes remains understudied, particularly in generative settings. In this work, we examine the fairness of LLM-based hiring systems through two real-world tasks: resume summarization and retrieval. By constructing a synthetic resume dataset and curating job postings, we investigate whether model behavior differs across demographic groups and is sensitive to demographic perturbations. Our findings reveal that race-based differences appear in approximately 10% of generated summaries, while gender-based differences occur in only 1%. In the retrieval setting, all evaluated models display non-uniform selection patterns across demographic groups and exhibit high sensitivity to both gender and race-based perturbations. Surprisingly, retrieval models demonstrate comparable sensitivity to non-demographic changes, suggesting that fairness issues may stem, in part, from general brittleness issues. Overall, our results indicate that LLM-based hiring systems, especially at the retrieval stage, can exhibit notable biases that lead to discriminatory outcomes in real-world contexts.
With over 85 million CT scans performed annually in the United States, creating tumor-related reports is a challenging and time-consuming task for radiologists. To address this need, we present RadGPT, an Anatomy-Aware Vision-Language AI Agent for generating detailed reports from CT scans. RadGPT first segments tumors, including benign cysts and malignant tumors, and their surrounding anatomical structures, then transforms this information into both structured reports and narrative reports. These reports provide tumor size, shape, location, attenuation, volume, and interactions with surrounding blood vessels and organs. Extensive evaluation on unseen hospitals shows that RadGPT can produce accurate reports, with high sensitivity/specificity for small tumor (<2 cm) detection: 80/73% for liver tumors, 92/78% for kidney tumors, and 77/77% for pancreatic tumors. For large tumors, sensitivity ranges from 89% to 97%. The results significantly surpass the state-of-the-art in abdominal CT report generation. RadGPT generated reports for 17 public datasets. Through radiologist review and refinement, we have ensured the reports' accuracy, and created the first publicly available image-text 3D medical dataset, comprising over 1.8 million text tokens and 2.7 million images from 9,262 CT scans, including 2,947 tumor scans/reports of 8,562 tumor instances. Our reports can: (1) localize tumors in eight liver sub-segments and three pancreatic sub-segments annotated per-voxel; (2) determine pancreatic tumor stage (T1-T4) in 260 reports; and (3) present individual analyses of multiple tumors--rare in human-made reports. Importantly, 948 of the reports are for early-stage tumors.
Working from an observability characterization based on output energy sensitivity to changes in initial conditions, we derive both analytical and empirical observability Gramian tools for a class of continuum material systems. Using these results, optimal sensor placement is calculated for an Euler-Bernoulli cantilever beam for the following cases: analytical observability for the continuum system and analytical observability for a finite number of modes. Error covariance of an Unscented Kalman Filter is determined for both cases and compared to randomly placed sensors to demonstrate effectiveness of the techniques.
Multi-phase injection-locked ring oscillators (MP-ILROs) are widely used for multi-phase clock generation, with their phase accuracy primarily determined by the inherent accuracy of the oscillator itself, due to the suppression of input signal errors. However, a quantitative analysis of the oscillator's sensitivity to input errors remains largely unexplored. This paper presents a phasor-based analysis of injection locking, revealing that the phase error sensitivity is influenced by factors such as injection strength and the free-running frequency of the oscillator. Simulation results align closely with theoretical calculations, validating the effectiveness of the proposed method.
Modeling the associations between real world entities from their multivariate cross-sectional profiles can provide cues into the concerted working of these entities as a system. Several techniques have been proposed for deciphering these associations including constraint-based Bayesian structure learning (BSL) algorithms that model them as directed acyclic graphs. Benchmarking these algorithms have typically focused on assessing the variation in performance measures such as sensitivity as a function of the dimensionality represented by the number of nodes in the DAG, and sample size. The present study elucidates the importance of network topology in benchmarking exercises. More specifically, it investigates variations in sensitivity across distinct network topologies while constraining the nodes, edges, and sample-size to be identical, eliminating these as potential confounders. Sensitivity of three popular constraint-based BSL algorithms (Peter-Clarke, Grow-Shrink, Incremental Association Markov Blanket) in learning the network structure from multivariate cross-sectional profiles sampled from network models with sub-linear, linear, and super-linear DAG topologies generated using preferential attachment is investigated. Results across linear and nonlinear models revealed statistically significant $(\alpha=0.05)$ decrease in sensitivity estimates from sub-linear to super-linear topology constitutively across the three algorithms. These results are demonstrated on networks with nodes $(N_{nods}=48,64)$, noise strengths $(\sigma =3,6)$ and sample size $(N = 2^{10})$. The findings elucidate the importance of accommodating the network topology in constraint-based BSL benchmarking exercises.
Advances in healthcare research have significantly enhanced our understanding of disease mechanisms, diagnostic precision, and therapeutic options. Yet, lung cancer remains one of the leading causes of cancer-related mortality worldwide due to challenges in early and accurate diagnosis. While current lung cancer detection models show promise, there is considerable potential for further improving the accuracy for timely intervention. To address this challenge, we introduce a hybrid deep convolution model leveraging transfer learning, named the Maximum Sensitivity Neural Network (MSNN). MSNN is designed to improve the precision of lung cancer detection by refining sensitivity and specificity. This model has surpassed existing deep learning approaches through experimental validation, achieving an accuracy of 98% and a sensitivity of 97%. By overlaying sensitivity maps onto lung Computed Tomography (CT) scans, it enables the visualization of regions most indicative of malignant or benign classifications. This innovative method demonstrates exceptional performance in distinguishing lung cancer with minimal false positives, thereby enhancing the accuracy of medical diagnoses.
Changes in room acoustics, such as modifications to surface absorption or the insertion of a scattering object, significantly impact measured room impulse responses (RIRs). These changes can affect the performance of systems used in echo cancellation and active acoustics and support tasks such as navigation and object tracking. Recognizing and quantifying such changes is, therefore, critical for advancing technologies based on room acoustics. This study introduces a method for analyzing acoustic environment changes by evaluating the similarity of consecutively recorded RIRs. Short-time coherence is employed to characterize modifications, including changes in wall absorption or the presence of a moving person in the room. A sensitivity rating is further used to quantify the magnitude of these changes. The results clearly differentiate between types of modifications -- atmospheric variation, changes in absorption, and human presence. The methods described provide a novel approach to analyzing and interpreting room acoustics, emphasizing RIR similarity and extracting information from temporal and spectral signal properties.
This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of writing style in shaping embedding spaces. Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English. By analyzing the particular impact of style on embedding dispersion, we aim to better understand how language models process stylistic information, contributing to their overall interpretability.
Efficiently retrieving a concise set of candidates from a large document corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transformers and pretrained language models, have been popular due to their superior performance. However, criticisms have also been raised on their lack of explainability and vulnerability to adversarial attacks. In response to these challenges, we propose to improve the robustness of dense retrieval models by enhancing their sensitivity of fine-graned relevance signals. A model achieving sensitivity in this context should exhibit high variances when documents' key passages determining their relevance to queries have been modified, while maintaining low variances for other changes in irrelevant passages. This sensitivity allows a dense retrieval model to produce robust results with respect to attacks that try to promote documents without actually increasing their relevance. It also makes it possible to analyze which part of a document is actually relevant to a query, and thus improve the explainability of the retrieval model. Motivated by causality and counterfactual analysis, we propose a series of counterfactual regularization methods based on game theory and unsupervised learning with counterfactual passages. Experiments show that, our method can extract key passages without reliance on the passage-level relevance annotations. Moreover, the regularized dense retrieval models exhibit heightened robustness against adversarial attacks, surpassing the state-of-the-art anti-attack methods.
This study investigates products sold before consumption and examines how the duration of the consumption periods and the choice of selling mechanism influence sellers' revenue. Using empirical data from timber auctions, we identify buyers' tendency to delay consumption to resolve payoff uncertainty and reveal heterogeneous motivations among buyers. Through structural estimation, we uncover key parameters for each buyer type, including sensitivity to realized payoffs and consumption-related costs. Leveraging these estimates, we perform counterfactual analyses to propose revenue-enhancing consumption periods and selling mechanisms. Our findings suggest that extending the consumption periods is likely to increase revenue, with the magnitude depending on the selling mechanism, the composition of buyer types, and the number of interested buyers.
Top-$K$ recommendation involves inferring latent user preferences and generating personalized recommendations accordingly, which is now ubiquitous in various decision systems. Nonetheless, recommender systems usually suffer from severe \textit{popularity bias}, leading to the over-recommendation of popular items. Such a bias deviates from the central aim of reflecting user preference faithfully, compromising both customer satisfaction and retailer profits. Despite the prevalence, existing methods tackling popularity bias still have limitations due to the considerable accuracy-debias tradeoff and the sensitivity to extensive parameter selection, further exacerbated by the extreme sparsity in positive user-item interactions. In this paper, we present a \textbf{Pop}ularity-aware top-$K$ recommendation algorithm integrating multi-behavior \textbf{S}ide \textbf{I}nformation (PopSI), aiming to enhance recommendation accuracy and debias performance simultaneously. Specifically, by leveraging multiple user feedback that mirrors similar user preferences and formulating it as a three-dimensional tensor, PopSI can utilize all slices to capture the desiring user preferences effectively. Subsequently, we introduced a novel orthogonality constraint to refine the estimated item feature space, enforcing it to be invariant to item popularity features thereby addressing our model's sensitivity to popularity bias. Comprehensive experiments on real-world e-commerce datasets demonstrate the general improvements of PopSI over state-of-the-art debias methods with a marginal accuracy-debias tradeoff and scalability to practical applications. The source code for our algorithm and experiments is available at \url{https://github.com/Eason-sys/PopSI}.
Cardiac disease evaluation depends on multiple diagnostic modalities: electrocardiogram (ECG) to diagnose abnormal heart rhythms, and imaging modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and echocardiography to detect signs of structural abnormalities. Each of these modalities brings complementary information for a better diagnosis of cardiac dysfunction. However, training a machine learning (ML) model with data from multiple modalities is a challenging task, as it increases the dimension space, while keeping constant the number of samples. In fact, as the dimension of the input space increases, the volume of data required for accurate generalisation grows exponentially. In this work, we address this issue, for the application of Ventricular Arrhythmia (VA) prediction, based on the combined clinical and CT imaging features, where we constrained the learning process on medical images (CT) based on the prior knowledge acquired from clinical data. The VA classifier is fed with features extracted from a 3D myocardium thickness map (TM) of the left ventricle. The TM is generated by our pipeline from the imaging input and a Graph Convolutional Network is used as the feature extractor of the 3D TM. We introduce a novel Sequential Fusion method and evaluate its performance against traditional Early Fusion techniques and single-modality models. The crossvalidation results show that the Sequential Fusion model achieved the highest average scores of 80.7% $\pm$ 4.4 Sensitivity and 73.1% $\pm$ 6.0 F1 score, outperforming the Early Fusion model at 65.0% $\pm$ 8.9 Sensitivity and 63.1% $\pm$ 6.3 F1 score. Both fusion models achieved better scores than the single-modality models, where the average Sensitivity and F1 score are 62.8% $\pm$ 10.1; 52.1% $\pm$ 6.5 for the clinical data modality and 62.9% $\pm$ 6.3; 60.7% $\pm$ 5.3 for the medical images modality.
In this work, a large area, low cost and flexible polymer/paper-based double touch mode capacitive pressure sensor is demonstrated. Garage fabrication processes are used which only require cutting, taping and assembly of aluminum (Al) coated polyimide (PI) foil, PI tape and double-sided scotch tape. The presented pressure sensor operates in different pressure regions i.e. normal (0 to 7.5 kPa), transition (7.5 to 14.24 kPa), linear (14.24 to 54.9 kPa) and saturation (above 54.9 kPa). The advantages of the demonstrated double touch mode capacitive pressure sensors are low temperature drift, long linear range, high pressure sensitivity, precise pressure measurement and large die area. The linear output along with a high sensitivity range (14.24 to 54.9 kPa pressure range) of the sensor are utilized to wirelessly control the movement of a robotic arm with precise rotation and tilt movement capabilities.
Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, which are typically unconditional -- generating images from random variables -- or conditioned only by tumor shapes, lack controllability over specific tumor characteristics such as texture, heterogeneity, boundaries, and pathology type. As a result, the generated tumors may be overly similar or duplicates of existing training data, failing to effectively address AI's weaknesses. We propose a new text-driven tumor synthesis approach, termed TextoMorph, that provides textual control over tumor characteristics. This is particularly beneficial for examples that confuse the AI the most, such as early tumor detection (increasing Sensitivity by +8.5%), tumor segmentation for precise radiotherapy (increasing DSC by +6.3%), and classification between benign and malignant tumors (improving Sensitivity by +8.2%). By incorporating text mined from radiology reports into the synthesis process, we increase the variability and controllability of the synthetic tumors to target AI's failure cases more precisely. Moreover, TextoMorph uses contrastive learning across different texts and CT scans, significantly reducing dependence on scarce image-report pairs (only 141 pairs used in this study) by leveraging a large corpus of 34,035 radiology reports. Finally, we have developed rigorous tests to evaluate synthetic tumors, including Text-Driven Visual Turing Test and Radiomics Pattern Analysis, showing that our synthetic tumors is realistic and diverse in texture, heterogeneity, boundaries, and pathology.
Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already include visual spatial reasoning(VSR). There is still a lack of sufficient quantity and quality evaluation and optimization datasets for Vision Large Language Models(VLLMs) specifically targeting visual positional reasoning. To handle this, we first diagnosed current VLLMs with the VSR dataset and proposed a unified test set. We found current VLLMs to exhibit a contradiction of over-sensitivity to language instructions and under-sensitivity to visual positional information. By expanding the original benchmark from two aspects of tunning data and model structure, we mitigated this phenomenon. To our knowledge, we expanded spatially positioned image data controllably using diffusion models for the first time and integrated original visual encoding(CLIP) with other 3 powerful visual encoders(SigLIP, SAM and DINO). After conducting combination experiments on scaling data and models, we obtained a VLLM VSR Expert(VSRE) that not only generalizes better to different instructions but also accurately distinguishes differences in visual positional information. VSRE achieved over a 27\% increase in accuracy on the VSR test set. It becomes a performant VLLM on the position reasoning of both the VSR dataset and relevant subsets of other evaluation benchmarks. We open-sourced the expanded model with data and Appendix at \url{https://github.com/peijin360/vsre} and hope it will accelerate advancements in VLLM on VSR learning.
This paper studies the parameter sensitivity of grid-forming inverters to Hopf bifurcations to address oscillatory instability. An analytical expression for the sensitivity of the stability margin is derived based on the normal vector to the bifurcation hypersurface. We identify the most effective control parameters through comprehensive analysis. In particular, the impacts of line dynamics on the stability margin to Hopf bifurcation are investigated. The results indicate that the feedforward gain in the voltage control loop is the most effective parameter for enhancing the stability margin. Furthermore, it is observed that line dynamics introduce a uniform reduction in the stability margin across all parameters. However, the reduction is generally small for most parameters except for the voltage-reactive power droop gain, which shows a more pronounced effect.
This study investigates the behavior of model-integrated routers in Mixture of Experts (MoE) models, focusing on how tokens are routed based on their linguistic features, specifically Part-of-Speech (POS) tags. The goal is to explore across different MoE architectures whether experts specialize in processing tokens with similar linguistic traits. By analyzing token trajectories across experts and layers, we aim to uncover how MoE models handle linguistic information. Findings from six popular MoE models reveal expert specialization for specific POS categories, with routing paths showing high predictive accuracy for POS, highlighting the value of routing paths in characterizing tokens.