# Tokenization of Gaze Data

arXiv: https://arxiv.org/abs/2503.22145 · HTML: https://mlsanity.com/paper/2503.22145/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 60 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [Fast WordPiece Tokenization](https://mlsanity.com/paper/2012.15524/) (2020)
- [Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks](https://mlsanity.com/paper/2305.08842/) (2023)
- [Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance](https://mlsanity.com/paper/2403.06265/) (2024)

## Built on by (most cited first, 1 of 1)

- [Motion-Based Tokenization for Cross-Dataset Egocentric Gaze Modeling](https://mlsanity.com/paper/2608.22926/) (2026)

## Abstract (arXiv)

A considerable part of the performance of today's large language models (LLM's) and multimodal large language models (MLLM's) depends on their tokenization strategies. While tokenizers are extensively researched for textual and visual input, there is no research on tokenization strategies for gaze data due to its nature. However, a corresponding tokenization strategy would allow using the vision capabilities of pre-trained MLLM's for gaze data, for example, through fine-tuning. In this paper, we aim to close this research gap by analyzing five different tokenizers for gaze data on three different datasets for the forecasting and generation of gaze data through LLMs (cf.~creffig:teaser). We evaluate the tokenizers regarding their reconstruction and compression abilities. Further, we train an LLM for each tokenization strategy, measuring its generative and predictive performance. Overall, we found that a quantile tokenizer outperforms all others in predicting the gaze positions and k-means is best when predicting gaze velocities.