# Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning

arXiv: https://arxiv.org/abs/2412.10840 · HTML: https://mlsanity.com/paper/2412.10840/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [OS-Copilot: Towards Generalist Computer Agents with Self-Improvement](https://mlsanity.com/paper/2402.07456/) (2024)
- [Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs](https://mlsanity.com/paper/2404.05719/) (2024)
- [OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web](https://mlsanity.com/paper/2402.17553/) (2024)
- [GUICourse: From General Vision Language Models to Versatile GUI Agents](https://mlsanity.com/paper/2406.11317/) (2024)
- [CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation](https://mlsanity.com/paper/2402.11941/) (2024)
- [MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents](https://mlsanity.com/paper/2406.08184/) (2024)
- [Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus](https://mlsanity.com/paper/2209.14927/) (2022)
- [MobileFlow: A Multimodal LLM For Mobile GUI Agent](https://mlsanity.com/paper/2407.04346/) (2024)
- [Dual-View Visual Contextualization for Web Navigation](https://mlsanity.com/paper/2402.04476/) (2024)
- [Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding](https://mlsanity.com/paper/2406.19263/) (2024)
- [Devil's Advocate: Anticipatory Reflection for LLM Agents](https://mlsanity.com/paper/2405.16334/) (2024)

## Built on by (most cited first, 14 of 14)

- [GUI Agents: A Survey](https://mlsanity.com/paper/2412.13501/) (2024)
- [GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents](https://mlsanity.com/paper/2506.03143/) (2025)
- [LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects](https://mlsanity.com/paper/2504.19838/) (2025)
- [MVP: Multiple View Prediction Improves GUI Grounding](https://mlsanity.com/paper/2512.08529/) (2025)
- [GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding](https://mlsanity.com/paper/2511.00810/) (2025)
- [Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding](https://mlsanity.com/paper/2512.05941/) (2025)
- [Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding](https://mlsanity.com/paper/2604.21268/) (2026)
- [Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents](https://mlsanity.com/paper/2508.01858/) (2025)
- [How Auxiliary Reasoning Unleashes GUI Grounding in VLMs](https://mlsanity.com/paper/2509.11548/) (2025)
- [ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents](https://mlsanity.com/paper/2602.02548/) (2026)
- [Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion](https://mlsanity.com/paper/2602.06351/) (2026)
- [Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows](https://mlsanity.com/paper/2604.23855/) (2026)
- [Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents](https://mlsanity.com/paper/2605.28629/) (2026)
- [Seg2Click: Learning Pixel-Level Action Masks for GUI Visual Grounding](https://mlsanity.com/paper/2610.16234/) (2026)

## Abstract (arXiv)

Recent advancements in Multimodal Large Language Models (MLLMs) have generated significant interest in their ability to autonomously interact with and interpret Graphical User Interfaces (GUIs). A major challenge in these systems is grounding-accurately identifying critical GUI components such as text or icons based on a GUI image and a corresponding text query. Traditionally, this task has relied on fine-tuning MLLMs with specialized training data to predict component locations directly. However, in this paper, we propose a novel Tuning-free Attention-driven Grounding (TAG) method that leverages the inherent attention patterns in pretrained MLLMs to accomplish this task without the need for additional fine-tuning. Our method involves identifying and aggregating attention maps from specific tokens within a carefully constructed query prompt. Applied to MiniCPM-Llama3-V 2.5, a state-of-the-art MLLM, our tuning-free approach achieves performance comparable to tuning-based methods, with notable success in text localization. Additionally, we demonstrate that our attention map-based grounding technique significantly outperforms direct localization predictions from MiniCPM-Llama3-V 2.5, highlighting the potential of using attention maps from pretrained MLLMs and paving the way for future innovations in this domain.