Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language models (MLLMs), given the same foveated input, search as humans do bears on their use as models of human vision and on attention-alignment scores. We compare three general-purpose MLLMs with human eye-movement scanpaths on goal-directed search (COCO-Search18), driving each model fixation by fixation through an identical, human-matched foveated view and assessing it along three axes: the decision of target presence, the efficiency of reaching the target, and the gaze process itself. The axes dissociate. On the decision and on target acquisition the models match or exceed humans, detecting present targets near ceiling and reaching them on the first saccade more often than people do. The gaze process is not human. Under the human-matched condition, all three share one signature: low-entropy, large-amplitude, self-consistent scanpaths that agree with themselves far more closely than two humans agree with each other. That is consistent with a single-pass, non-serial architecture rather than a limit of acuity. Matched retinal input reproduces where humans look but not how the looking unfolds in time, and no degradation regime recovers human-like search at human-like success. The gap sits on a process axis that answer-alignment and saliency metrics do not measure. Because they miss it, such metrics cannot certify human-like vision, and zero-shot models suit outcome and spatial questions but not temporal, process-level ones.

What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric

Scanpath similarity metrics are central to eye-movement research, yet existing methods predominantly evaluate spatial and temporal alignment while neglecting semantic equivalence between attended image regions. We present a semantic scanpath similarity framework that integrates vision-language models (VLMs) into eye-tracking analysis. Each fixation is encoded under controlled visual context (patch-based and marker-based strategies) and transformed into concise textual descriptions, which are aggregated into scanpath-level representations. Semantic similarity is then computed using embedding-based and lexical NLP metrics and compared against established spatial measures, including MultiMatch and DTW. Experiments on free-viewing eye-tracking data demonstrate that semantic similarity captures partially independent variance from geometric alignment, revealing cases of high content agreement despite spatial divergence. We further analyze the impact of contextual encoding on description fidelity and metric stability. Our findings suggest that multimodal foundation models enable interpretable, content-aware extensions of classical scanpath analysis, providing a complementary dimension for gaze research within the ETRA community.

SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation

Understanding human visual attention is key to preserving cultural heritage We introduce SPGen a novel deep learning model to predict scanpaths the sequence of eye movementswhen viewers observe paintings. Our architecture uses a Fully Convolutional Neural Network FCNN with differentiable fixation selection and learnable Gaussian priors to simulate natural viewing biases To address the domain gap between photographs and artworks we employ unsupervised domain adaptation via a gradient reversal layer allowing the model to transfer knowledge from natural scenes to paintings Furthermore a random noise sampler models the inherent stochasticity of eyetracking data. Extensive testing shows SPGen outperforms existing methods offering a powerful tool to analyze gaze behavior and advance the preservation and appreciation of artistic treasures.

Modeling Beyond MOS: Quality Assessment Models Must Integrate Context, Reasoning, and Multimodality

This position paper argues that Mean Opinion Score (MOS), while historically foundational, is no longer sufficient as the sole supervisory signal for multimedia quality assessment models. MOS reduces rich, context-sensitive human judgments to a single scalar, obscuring semantic failures, user intent, and the rationale behind quality decisions. We contend that modern quality assessment models must integrate three interdependent capabilities: (1) context-awareness, to adapt evaluations to task-specific goals and viewing conditions; (2) reasoning, to produce interpretable, evidence-grounded justifications for quality judgments; and (3) multimodality, to align perceptual and semantic cues using vision-language models. We critique the limitations of current MOS-centric benchmarks and propose a roadmap for reform: richer datasets with contextual metadata and expert rationales, and new evaluation metrics that assess semantic alignment, reasoning fidelity, and contextual sensitivity. By reframing quality assessment as a contextual, explainable, and multimodal modeling task, we aim to catalyze a shift toward more robust, human-aligned, and trustworthy evaluation systems.

Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs

Generative Adversarial Networks (GANs) have many potential medical imaging applications. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models cannot scale to high-resolution or are susceptible to patchy artifacts. In this work, we propose an end-to-end novel GAN architecture that uses Conditional Random field (CRF) to model dependencies so that it can generate consistent 3D medical Images without exploiting memory. To achieve this purpose, the generator is divided into two parts during training, the first part produces an intermediate representation and CRF is applied to this intermediate representation to capture correlations. The second part of the generator produces a random sub-volume of image using a subset of the intermediate representation. This structure has two advantages: first, the correlations are modeled by using the features that the generator is trying to optimize. Second, the generator can generate full high-resolution images during inference. Experiments on Lung CTs and Brain MRIs show that our architecture outperforms state-of-the-art while it has lower memory usage and less complexity.

Comparative clinical evaluation of "memory-efficient" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest

Introduction: Generative Adversarial Networks (GANs) are increasingly used to generate synthetic medical images, addressing the critical shortage of annotated data for training Artificial Intelligence (AI) systems. This study introduces a novel memory-efficient GAN architecture, incorporating Conditional Random Fields (CRFs) to generate high-resolution 3D medical images and evaluates its performance against the state-of-the-art hierarchical (HA)-GAN model. Materials and Methods: The CRF-GAN was trained using the open-source lung CT LUNA16 dataset. The architecture was compared to HA-GAN through a quantitative evaluation, using Frechet Inception Distance (FID) and Maximum Mean Discrepancy (MMD) metrics, and a qualitative evaluation, through a two-alternative forced choice (2AFC) test completed by a pool of 12 resident radiologists, in order to assess the realism of the generated images. Results: CRF-GAN outperformed HA-GAN with lower FID (0.047 vs. 0.061) and MMD (0.084 vs. 0.086) scores, indicating better image fidelity. The 2AFC test showed a significant preference for images generated by CRF-Gan over those generated by HA-GAN with a p-value of 1.93e-05. Additionally, CRF-GAN demonstrated 9.34% lower memory usage at 256 resolution and achieved up to 14.6% faster training speeds, offering substantial computational savings. Discussion: CRF-GAN model successfully generates high-resolution 3D medical images with non-inferior quality to conventional models, while being more memory-efficient and faster. Computational power and time saved can be used to improve the spatial resolution and anatomical accuracy of generated images, which is still a critical factor limiting their direct clinical applicability.

Detection of subclinical atherosclerosis by image-based deep learning on chest x-ray

Aims. To develop a deep-learning based system for recognition of subclinical atherosclerosis on a plain frontal chest x-ray. Methods and Results. A deep-learning algorithm to predict coronary artery calcium (CAC) score (the AI-CAC model) was developed on 460 chest x-ray (80% training cohort, 20% internal validation cohort) of primary prevention patients (58.4% male, median age 63 [51-74] years) with available paired chest x-ray and chest computed tomography (CT) indicated for any clinical reason and performed within 3 months. The CAC score calculated on chest CT was used as ground truth. The model was validated on an temporally-independent cohort of 90 patients from the same institution (external validation). The diagnostic accuracy of the AI-CAC model assessed by the area under the curve (AUC) was the primary outcome. Overall, median AI-CAC score was 35 (0-388) and 28.9% patients had no AI-CAC. AUC of the AI-CAC model to identify a CAC>0 was 0.90 in the internal validation cohort and 0.77 in the external validation cohort. Sensitivity was consistently above 92% in both cohorts. In the overall cohort (n=540), among patients with AI-CAC=0, a single ASCVD event occurred, after 4.3 years. Patients with AI-CAC>0 had significantly higher Kaplan Meier estimates for ASCVD events (13.5% vs. 3.4%, log-rank=0.013). Conclusion. The AI-CAC model seems to accurately detect subclinical atherosclerosis on chest x-ray with elevated sensitivity, and to predict ASCVD events with elevated negative predictive value. Adoption of the AI-CAC model to refine CV risk stratification or as an opportunistic screening tool requires prospective evaluation.

Quantization Effects on Neural Networks Perception: How would quantization change the perceptual field of vision models?

Neural network quantization is an essential technique for deploying models on resource-constrained devices. However, its impact on model perceptual fields, particularly regarding class activation maps (CAMs), remains a significant area of investigation. In this study, we explore how quantization alters the spatial recognition ability of the perceptual field of vision models, shedding light on the alignment between CAMs and visual saliency maps across various architectures. Leveraging a dataset of 10,000 images from ImageNet, we rigorously evaluate six diverse foundational CNNs: VGG16, ResNet50, EfficientNet, MobileNet, SqueezeNet, and DenseNet. We uncover nuanced changes in CAMs and their alignment with human visual saliency maps through systematic quantization techniques applied to these models. Our findings reveal the varying sensitivities of different architectures to quantization and underscore its implications for real-world applications in terms of model performance and interpretability. The primary contribution of this work revolves around deepening our understanding of neural network quantization, providing insights crucial for deploying efficient and interpretable models in practical settings.

Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment

Conventional imaging diagnostics frequently encounter bottlenecks due to manual inspection, which can lead to delays and inconsistencies. Although deep learning offers a pathway to automation and enhanced accuracy, foundational models in computer vision often emphasize global context at the expense of local details, which are vital for medical imaging diagnostics. To address this, we harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. This method ensures that local features are not only preserved but are also enriched with task-specific information, enhancing their relevance and detail at every hierarchical level. By implementing this strategy, our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification. These results highlight our approach's effectiveness and its promising implications for the future of medical imaging diagnostics. Our implementation is available on https://github.com/mtliba/KOA_NLCS2024

Insights into Classifying and Mitigating LLMs' Hallucinations

The widespread adoption of large language models (LLMs) across diverse AI applications is proof of the outstanding achievements obtained in several tasks, such as text mining, text generation, and question answering. However, LLMs are not exempt from drawbacks. One of the most concerning aspects regards the emerging problematic phenomena known as "Hallucinations". They manifest in text generation systems, particularly in question-answering systems reliant on LLMs, potentially resulting in false or misleading information propagation. This paper delves into the underlying causes of AI hallucination and elucidates its significance in artificial intelligence. In particular, Hallucination classification is tackled over several tasks (Machine Translation, Question and Answer, Dialog Systems, Summarisation Systems, Knowledge Graph with LLMs, and Visual Question Answer). Additionally, we explore potential strategies to mitigate hallucinations, aiming to enhance the overall reliability of LLMs. Our research addresses this critical issue within the HeReFaNMi (Health-Related Fake News Mitigation) project, generously supported by NGI Search, dedicated to combating Health-Related Fake News dissemination on the Internet. This endeavour represents a concerted effort to safeguard the integrity of information dissemination in an age of evolving AI technologies.