PulseAugur
EN
LIVE 10:12:54

Diffusion models generate realistic eye-gaze trajectories for research and biometrics

By PulseAugur Editorial · [3 sources] ·

Researchers have developed new diffusion models for generating realistic eye-gaze trajectories, addressing the challenge of expensive and privacy-constrained data collection. One model focuses on generating raw 2D gaze positions, achieving high accuracy in kinematic features and fixation duration. Another model synthesizes high-frequency gaze velocity sequences, conditioned on identity, task, and subjective states, showing promise for applications like eye movement biometrics. AI

IMPACT Advances in synthetic gaze data generation could reduce reliance on expensive hardware and enable new applications in biometrics and human-computer interaction.

RANK_REASON Two research papers detailing novel diffusion models for eye-gaze trajectory generation.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Diffusion models generate realistic eye-gaze trajectories for research and biometrics

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Two research papers detailing novel diffusion models for eye-gaze trajectory generation.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
74 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · Laxman Basnet, Alexander Szorkovszky, Pedro G. Lind, Anis Yazidi, Shailendra Bhandari ·

    Diffusion models for eye-gaze trajectory generation using position and velocity representations

    arXiv:2609.05522v1 Announce Type: cross Abstract: Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints. We address this using two complementary denoising diffusion pr…

  2. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Shailendra Bhandari ·

    Diffusion models for eye-gaze trajectory generation using position and velocity representations

    Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints. We address this using two complementary denoising diffusion probabilistic models (DDPMs) for unconditional gener…

  3. arXiv cs.CV TIER_1 English(EN) · Kamrul Hasan, Mehedi Hasan Raju, Oleg V. Komogortsev ·

    EyeMakeYou: Identity-, Task-, and Subjective-State-Conditioned Diffusion for High-Frequency Gaze Synthesis

    arXiv:2609.04501v1 Announce Type: cross Abstract: Eye movement biometrics (EMB) is an emerging behavioral modality for user authentication, particularly in virtual- and augmented-reality systems, where gaze dynamics contain distinctive subject-specific features. However, robust E…

RELATED ENTITIES

RELATED TOPICS