# Resolving Ambiguity in Gaze-Facilitated Visual Assistant Interaction Paradigm

arXiv: https://arxiv.org/abs/2509.21980 · HTML: https://mlsanity.com/paper/2509.21980/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 25 of 25)

- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [Oops! Predicting Unintentional Action in Video](https://mlsanity.com/paper/1911.11206/) (2019)
- [GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Reality](https://mlsanity.com/paper/2404.08213/) (2024)
- [Voila-A: Aligning Vision-Language Models with User's Gaze Attention](https://mlsanity.com/paper/2401.09454/) (2023)
- [Connecting Vision and Language with Video Localized Narratives](https://mlsanity.com/paper/2302.11217/) (2023)
- [Discovering Spatio-Temporal Rationales for Video Question Answering](https://mlsanity.com/paper/2307.12058/) (2023)
- [VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering](https://mlsanity.com/paper/2109.13116/) (2021)
- [GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear](https://mlsanity.com/paper/2401.17217/) (2024)
- [A High-Level Description and Performance Evaluation of Pupil Invisible](https://mlsanity.com/paper/2009.00508/) (2020)
- [G-VOILA: Gaze-Facilitated Information Querying in Daily Scenarios](https://mlsanity.com/paper/2405.07652/) (2024)

## Abstract (arXiv)

With the rise in popularity of smart glasses, users' attention has been integrated into Vision-Language Models (VLMs) to streamline multi-modal querying in daily scenarios. However, leveraging gaze data to model users' attention may introduce ambiguity challenges: (1) users' verbal questions become ambiguous by using pronouns or skipping context, (2) humans' gaze patterns can be noisy and exhibit complex spatiotemporal relationships with their spoken questions. Previous works only consider single image as visual modality input, failing to capture the dynamic nature of the user's attention. In this work, we introduce GLARIFY, a novel method to leverage spatiotemporal gaze information to enhance the model's effectiveness in real-world applications. Initially, we analyzed hundreds of querying samples with the gaze modality to demonstrate the noisy nature of users' gaze patterns. We then utilized GPT-4o to design an automatic data synthesis pipeline to generate the GLARIFY-Ambi dataset, which includes a dedicated chain-of-thought (CoT) process to handle noisy gaze patterns. Finally, we designed a heatmap module to incorporate gaze information into cutting-edge VLMs while preserving their pretrained knowledge. We evaluated GLARIFY using a hold-out test set. Experiments demonstrate that GLARIFY significantly outperforms baselines. By robustly aligning VLMs with human attention, GLARIFY paves the way for a usable and intuitive interaction paradigm with a visual assistant.