# Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications

arXiv: https://arxiv.org/abs/2606.25084 · HTML: https://mlsanity.com/paper/2606.25084/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks](https://mlsanity.com/paper/2311.01361/) (2023)
- [LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge](https://mlsanity.com/paper/2311.11860/) (2023)
- [Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users](https://mlsanity.com/paper/2503.22610/) (2025)

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

- [PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance](https://mlsanity.com/paper/2609.14473/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have redefined visual understanding by combining vision encoders with large-scale language models. This unified architecture enables strong performance on tasks like image captioning, visual question answering, and multimodal dialogue, often in zero- and few-shot settings. Their general-purpose capabilities and flexible interfaces make MLLMs a promising foundation for real-world vision-language applications. Assistive AI aims to help users interact with their environments through natural language. These scenarios demand robust visual recognition, contextual reasoning, and multilingual comprehension-capabilities that MLLMs are believed to offer. However, their effectiveness in assistive settings remains to be fully understood. In this work, we explore whether MLLMs can support Assistive AI by evaluating state-of-the-art models on real-world tasks: recognizing everyday objects like currency, answering questions based on scene text, and reading visually presented content across multiple languages. To this end, we developed a system, NetraLink, using a head-mounted GoPro to capture real-world egocentric data, and collected a benchmark covering these assistive scenarios. Our findings provide a comprehensive diagnostic of current MLLMs, highlighting their strengths and limitations in enabling assistive technologies grounded in visual perception and language interaction.