We report state-of-the-art results in predicting the locations of human gaze fixations, even though our model is trained only on image-level labels without object location annotations.

Deep reinforcement learning (RL) algorithms are powerful tools for solving visuo-motor decision tasks.

Recent large vision-language models (LVLMs) has advanced capabilities in visual question answering (VQA). However, interpreting where LVLMs direct their visual attention remains a challenge, yet is essential for understanding model behavior . W e introduce GLIMPSE (Gradient-Layer Importance Mapping for Prompted Visual Saliency Explanation), a lightweight, model-agnostic framework that jointly attributes LVLM outputs to the most relevant visual evidence and textual signals that support open-ended generation. GLIMPSE fuses gradient-weighted attention, adaptive layer propagation, and relevance-weighted token aggregation to produce holistic response-level heat maps for interpreting cross-modal reasoning, outperforming prior methods in faithfulness and pushing the state-of-the-art in human-attention alignment. W e demonstrate an analytic explainable AI (XAI) approach to uncover fine-grained insights into LVLM cross-modal attribution, trace reasoning dynamics, analyze systematic misalignment, diagnose hallucination and bias, and ensure transparency.

Visual attention mechanisms play a crucial role in human perception and aesthetic evaluation. Recent advances in Vision Transformers (ViTs) have demonstrated remarkable capabilities in computer vision tasks, yet their alignment with human visual attention patterns remains underexplored, particularly in aesthetic contexts. This study investigates the correlation between human visual attention and ViT attention mechanisms when evaluating handcrafted objects. We conducted an eye-tracking experiment with 30 participants (9 female, 21 male, mean age 24.6 years) who viewed 20 artisanal objects comprising basketry bags and ginger jars. Using a Pupil Labs eye-tracker, we recorded gaze patterns and generated heat maps representing human visual attention. Simultaneously, we analyzed the same objects using a pre-trained ViT model with DINO (Self-DIstillation with NO Labels), extracting attention maps from each of the 12 attention heads. We compared human and ViT attention distributions using Kullback-Leibler divergence across varying Gaussian parameters (sigma=0.1 to 3.0). Statistical analysis revealed optimal correlation at sigma=2.4 +-0.03, with attention head #12 showing the strongest alignment with human visual patterns. Significant differences were found between attention heads, with heads #7 and #9 demonstrating the greatest divergence from human attention (p< 0.05, Tukey HSD test). Results indicate that while ViTs exhibit more global attention patterns compared to human focal attention, certain attention heads can approximate human visual behavior, particularly for specific object features like buckles in basketry items. These findings suggest potential applications of ViT attention mechanisms in product design and aesthetic evaluation, while highlighting fundamental differences in attention strategies between human perception and current AI models.

Improving decision-making capabilities in Autonomous Intelligent Vehicles (AIVs) has been a heated topic in recent years. Despite advancements, training machines to capture regions of interest for comprehensive scene understanding, like human perception and reasoning, remains a significant challenge. This study introduces a novel framework, Human Attention-based Explainable Guidance for Intelligent Vehicle Systems (AEGIS). AEGIS utilizes human attention, converted from eye-tracking, to guide reinforcement learning (RL) models to identify critical regions of interest for decision-making. AEGIS uses a pre-trained human attention model to guide RL models to identify critical regions of interest for decision-making. By collecting 1.2 million frames from 20 participants across six scenarios, AEGIS pre-trains a model to predict human attention patterns.

When I interviewed a nurse practitioner in California about what she cherished most about nursing, it was the "human element" of being present with others. "I think we all just want acknowledgment of our suffering, even if you can't cure it or do anything about it," she told me. She still remembered when a homeless man came into her clinic, his back hunched, feet gnarled and callused from being on the streets for years, and she "just sat and did wound care for his feet". The moment stood out for her, in part because the opportunity to take that kind of time is getting rarer in clinics and hospitals as drives for efficiency impose time constraints. Washing his feet captured what nursing was about for her: the humility, the service, the witnessing.

Attention can be used to inform choice selection in contextual bandit tasks even when context features have not been previously experienced. One example of this is in dimensional shifts, where additional feature values are introduced and the relationship between features and outcomes can either be static or variable. Attentional mechanisms have been extensively studied in contextual bandit tasks where the feedback of choices is provided immediately, but less research has been done on tasks where feedback is delayed or in counterfactual feedback cases. Some methods have successfully modeled human attention with immediate feedback based on reward prediction errors (RPEs), though recent research raises questions of the applicability of RPEs onto more general attentional mechanisms. Alternative models suggest that information theoretic metrics can be used to model human attention, with broader applications to novel stimuli. In this paper, we compare two different methods for modeling how humans attend to specific features of decision making tasks, one that is based on calculating an information theoretic metric using a memory of past experiences, and another that is based on iteratively updating attention from reward prediction errors. We compare these models using simulations in a contextual bandit task with both intradimensional and extradimensional domain shifts, as well as immediate, delayed, and counterfactual feedback. We find that calculating an information theoretic metric over a history of experiences is best able to account for human-like behavior in tasks that shift dimensions and alter feedback presentation. These results indicate that information theoretic metrics of attentional mechanisms may be better suited than RPEs to predict human attention in decision making, though further studies of human behavior are necessary to support these results.

Robots are now increasingly integrated into various real world applications and domains. In these new domains, robots are mostly employed to improve, in some ways, the work done by humans. So, the need for effective Human-Robot Teaming (HRT) capabilities grows. These capabilities usually involve the dynamic collaboration between humans and robots at different levels of involvement, leveraging the strengths of both to efficiently navigate complex situations. Crucial to this collaboration is the ability of robotic systems to adjust their level of autonomy to match the needs of the task and the human team members. This paper introduces a system designed to control attention using HRT through the use of ground robots and augmented reality (AR) technology. Traditional methods of controlling attention, such as pointing, touch, and voice commands, sometimes fall short in precision and subtlety. Our system overcomes these limitations by employing AR headsets to display virtual visual markers. These markers act as dynamic cues to attract and shift human attention seamlessly, irrespective of the robot's physical location.

Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we introduce CapMIT1003, a dataset with captions and click-contingent image explorations, to study human attention during the captioning task. We also present NevaClip, a zero-shot method for predicting visual scanpaths by combining CLIP models with NeVA algorithms. NevaClip generates fixations to align the representations of foveated visual stimuli and captions. The simulated scanpaths outperform existing human attention models in plausibility for captioning and free-viewing tasks. This research enhances the understanding of human attention and advances scanpath prediction models.