Open research questions in Gaze Tracking and Assistive Technology

What the literature leaves open

• The study had methodological limitations, such as small sample sizes. The studies relied on default equipment configurations. The overall validity of eye-tracking measures remains limited.

  Validity of Eye-Tracking Measures in Immersive Virtual Reality: Using Cognitive Theories of Learning · 2026 · DOI

• Many IVR studies focus on user experience rather than learning mechanisms. The evaluation methods often lack grounding in established theoretical foundations. There is a need for strengthening methodological foundations and providing detailed documentation of experimental setups.

  Validity of Eye-Tracking Measures in Immersive Virtual Reality: Using Cognitive Theories of Learning · 2026 · DOI

• However, there is limited knowledge of the key factors in these compositions in photography that actually affect the viewing process, and also no empirical support for the relationship between emotional responses and visual cognition.

  Using Eye Movement to Determine Whether Closed-Frame Shots Attract Viewers’ Attention · 2024 · DOI

• My research will extend resource-rational modeling of visual attention toward increasingly adaptive and interactive settings. From a theoretical perspective, a key next step is to generalize computationally rational control from single-agent behavior to multi-agent and socially situated scenarios. Many real-world tasks, such as collaborative reading in classrooms or shared attention in AR/VR environments require coordination among multiple agents with overlapping but distinct goals. Modeling such settings will enable the study of how attention is allocated not only within individuals but also across groups, opening new avenues for understanding joint cognition and collaborative human–computer interaction. On the application side, I plan to leverage my models to inform adaptive interface design across a broader range of HCI scenarios. While reading provides a controlled and cognitively rich testbed, the same simulation framework can be extended to interactions with visualizations, images, and complex user interfaces, where users must strategically allocate attention under time and resource constraints. By simulating how users adjust attention during multitasking, time pressure, or high cognitive load, these models can support systematic analysis of design alternatives prior to extensive user studies, and guide the development of time-aware reading interfaces, anticipatory safety prompts in AR systems, and adaptive visual and educational interfaces that respond to predicted user states [2, 24]. Technically, I aim to integrate deep generative models into the simulation pipeline to enhance scalability and realism. Large language models can provide rich contextual predictions to support semantic inference and memory construction, while diffusion- A Resource-Rational Principle for Modeling Visual Attention Control CHI EA ’26, April 13–17, 2026, Barcelona, Spain Figure 3: Reading behavior under different time constraints (30 s, 60 s, 90 s). The model and human readers adapt their visual attention strategies as available reading time changes, reflecting resource-rational control of comprehension. (a) Heatmaps. With increasing time (from left to right), both humans and the simulation allocate attention more broadly across the text and invest more fixation time, whereas under tight deadlines attention is concentrated on high-coverage regions. (b) Recall. Free-recall responses exhibit the same trade-off, with longer reading time yielding richer gist-level recall and more complete and detailed memory. or transformer-based generative models can be used to synthesize realistic eye-movement patterns or controlled interaction corpora [5, 6, 9]. Incorporating these components will allow simulationbased analyses of nuanced comprehension and interaction processes and support interfaces that adapt dynamically to inferred user states.

  A Resource-Rational Principle for Modeling Visual Attention Control · 2026 · DOI

• The availability of VR hardware with eye tracking and a fairly powerful PC system. The use of a high-end laser scanner may limit the applicability of the method to other domains. The need for a paradigm change in the construction industry.

  Eyes in the clouds: spatial data analysis with gaze-enhanced point clouds · 2026 · DOI

• The application of the method to other domains such as architecture and geodesy. The use of alternative means to create point clouds such as low-cost laser scanners or photogrammetry.

  Eyes in the clouds: spatial data analysis with gaze-enhanced point clouds · 2026 · DOI

• Traditional Human Reliability Analysis methods are mostly static and look back in time, lacking real-time monitoring capabilities - There is a need for a more effective and efficient method for monitoring operator fatigue and evaluating human reliability

  Integration of eye tracking technology for human reliability in railway engineering · 2026 · DOI

• Improving the accuracy of the system - Expanding the system to work with different types of documents - Integrating the system with other assistive technologies

  An Intelligent Eye Gaze–Driven E-Book Reader using MediaPipe and OpenCV · 2026 · DOI

• The lack of a gaze-assisted web-based reading platform - The need for a system that can track the eye gaze of users and allow them to navigate through pages using gestures

  An Intelligent Eye Gaze–Driven E-Book Reader using MediaPipe and OpenCV · 2026 · DOI

• Developing a system that can accurately track eye movements and recognize hand gestures in real-time. Overcoming the limitations of existing approaches, such as the need for specialized hardware. Providing a natural and intuitive way for individuals to interact with computers.

  Virtual Cursor Control Using Eye Tracking and Hand Gestures · 2026 · DOI

• Improving the system's performance in varying lighting conditions. Enhancing the system's robustness to hand orientation and camera positioning. Exploring the use of the system in various applications, such as gaming and education.

  Virtual Cursor Control Using Eye Tracking and Hand Gestures · 2026 · DOI

• To evaluate the proposed methods in various domains, such as gaming and education. To compare the performance of the proposed methods with other existing methods. To investigate the use of other modalities, such as voice or gesture, to support one-handed interaction in XR.

  Align-to-Scale: Mode Switching Technique for Unimanual 3D Object Manipulation with Gaze-Hand-Object Alignment in Extended Reality · 2026 · DOI

• The prevalent Gaze + Pinch interaction model partially supports unimanual interaction, but scaling typically requires both hands. There is a need for alternative unimanual scaling methods to support one-handed manipulation in XR. The paper aims to fill in the gap of previous mode-switching research by integrating gaze and hand as a mode-switching cue.

  Align-to-Scale: Mode Switching Technique for Unimanual 3D Object Manipulation with Gaze-Hand-Object Alignment in Extended Reality · 2026 · DOI

• Visually impaired users face significant barriers in performing basic email operations. Prior assistive technologies often require prior technical knowledge, are not fully voice-driven, or lack real-time responsiveness and accuracy.

  Voice Based Mail System for Visually Impaired Using AI/ML · 2026 · DOI

• Achieving low-latency gaze tracking using a fully passive optical encoder. Eliminating the need for high-bandwidth image readout and substantially reducing computational overhead. Enabling a high sampling rate with minimal data volume.

  Low Latency Gaze Tracking via Latent Optical Sensing · 2026

• Conventional image-based gaze estimation systems are limited by CMOS frame rates and massive data readout. There is a need for ultra-low-latency gaze tracking systems that can achieve high accuracy and efficiency.

  Low Latency Gaze Tracking via Latent Optical Sensing · 2026

• Future studies should test multiple headsets and implementations of passthrough and MR. Research should examine the effects of HMD-mediated viewing on visual performance in different tasks and environments. The study's findings should be generalized to other populations and use cases.

  Visual performance in head-mounted displays: Movement-dependent costs of video passthrough and mixed reality · 2026 · DOI

• The lack of understanding of how HMD-mediated viewing affects visual performance during locomotion. The need to evaluate HMDs under intended use conditions. The gap in knowledge about the effects of video passthrough and mixed reality on visual performance.

  Visual performance in head-mounted displays: Movement-dependent costs of video passthrough and mixed reality · 2026 · DOI

• To explore the application of the AISSM to other event-based data streams. To investigate the use of the AISSM for real-time eye tracking applications. To develop more efficient training methods for the AISSM.

  Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling · 2026 · DOI

• Few eye feature extractors are designed to handle sudden changes in event density. Prior work has not addressed the problem of dynamically adjusting the relative weight placed on current versus recent information.

  Enhancing Eye Feature Estimation from Event Data Streams through Adaptive Inference State Space Modeling · 2026 · DOI

• Multi-glint detection remains challenging in practice. Glints can be unreliable, partly occluded, duplicated by spurious reflections, or disappear entirely. The full matching pipeline is rarely described in detail in literature.

  Night Eyes: A Reproducible Framework for Constellation-Based Corneal Reflection Matching · 2026 · DOI

• Improving performance in very low-contrast conditions. Developing more advanced template structures and alignment methods. Applying the framework to various eye tracking applications.

  Night Eyes: A Reproducible Framework for Constellation-Based Corneal Reflection Matching · 2026 · DOI

• Interpreting what people see from eye-tracking data remains a challenge. Classical scanpath similarity metrics ignore the semantic content of attended regions. Recent advances in vision-language models require integration into eye-tracking analysis.

  What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metrics · 2026 · DOI

• Classical scanpath similarity metrics neglect semantic equivalence between attended image regions. Recent works have not converted entire scanpaths into structured narratives suitable for pairwise similarity computation.

  What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metrics · 2026 · DOI

• Existing methods for scanpath comparison lack privacy-preserving capabilities for real-world use. There is a need for a secure and efficient protocol for processing eye-tracking data.

  Secure Storage and Privacy-Preserving Scanpath Comparison via Garbled Circuits in Eye Tracking ETRA008 · 2026 · DOI

Most-cited papers in Gaze Tracking and Assistive Technology

• Eye movements in reading and information processing: 20 years of research. · Psychological Bulletin · 1998 · 5,581 citations
• Integration of Visual and Linguistic Information in Spoken Language Comprehension · Science · 1995 · 1,640 citations
• Some functions of gaze-direction in social interaction · Acta Psychologica · 1967 · 1,374 citations
• Visual Instruction Tuning · 2023 · 1,302 citations
• Gaze cueing of attention: Visual attention, social cognition, and individual differences. · Psychological Bulletin · 2007 · 1,136 citations
• Gaze and eye contact: A research review. · Psychological Bulletin · 1986 · 1,070 citations
• Tracking the Time Course of Spoken Word Recognition Using Eye Movements: Evidence for Continuous Mapping Models · Journal of Memory and Language · 1998 · 996 citations
• SWIFT: A Dynamical Model of Saccade Generation During Reading. · Psychological Review · 2005 · 729 citations
• Animate vision · Artificial Intelligence · 1991 · 677 citations
• Eye movements in reading and information processing. · Psychological Bulletin · 1978 · 642 citations

Most recent work

• EV-GazeLock: A User Authentication System Based on Micro Eye Movement with Event Cameras · ACM Transactions on Sensor Networks · 2026
• Student teachers' and experienced teachers’ situation awareness and professional vision in real-life classrooms · Teaching and Teacher Education · 2026
• Professional vision in teaching: review of methodological concepts using eye-tracking · Quality & Quantity · 2026
• PyeLink and SyeLink: Open-source Python tools for low-level EyeLink experiment control and data parsing · 2026
• The fundamentals of eye tracking, Part 7: Determining data quality · Behavior Research Methods · 2026
• eyeris: A flexible, extensible, and reproducible pupillometry preprocessing framework in R · bioRxiv · 2026
• Post-Decision Gaze as a Behavioral Manifestation of Decision Confidence · bioRxiv · 2026
• Recurrent visual behavior and viewpoint-specific spatial features in a heritage environment: immersive eye-tracking evidence from Jichang Garden · Journal of Environmental Psychology · 2026
• Gaze Estimation Based on Visual State Space Model with Hybrid Features · ACM Transactions on Sensor Networks · 2026
• Bat eye movements resolve a long-standing question in gaze control · Current Biology · 2026

Related topics in Computer Science