# Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE

arXiv: https://arxiv.org/abs/2610.19635 · HTML: https://mlsanity.com/paper/2610.19635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)
- [Smile Like You Mean It: Driving Animatronic Robotic Face with Learned Models](https://mlsanity.com/paper/2105.12724/) (2021)
- [GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction](https://mlsanity.com/paper/2312.12090/) (2023)
- [Knowing Where to Look: A Planning-based Architecture to Automate the Gaze Behavior of Social Robots](https://mlsanity.com/paper/2210.02866/) (2022)
- [HAPI: A Model for Learning Robot Facial Expressions from Human Preferences](https://mlsanity.com/paper/2503.17046/) (2025)

## Abstract (arXiv)

Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous vision-language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze Transformer (RGT) that generates target-conditioned motion. RGT is a Transformer-VAE trained on markerless human recordings retargeted to the robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.