paper-with-me

홈 › Papers

ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction

2025-03-26 · Yiqiao Jin, Stefano Petrangeli, Yu Shen, Gang Wu

Graphical User Interface (GUI) agents are autonomous systems that interpret and generate actions, enabling intelligent user assistance and automation. Effective training of these agent presents unique challenges, such as sparsity in supervision signals, scalability for large datasets, and the need for nuanced user understanding. We propose stateful screen schema, an efficient representation of GUI interactions that captures key user actions and intentions over time. Building on this foundation, we introduce ScreenLLM, a set of multimodal large language models (MLLMs) tailored for advanced UI understanding and action prediction. Extensive experiments on both open-source and proprietary models show that ScreenLLM accurately models user behavior and predicts actions. Our work lays the foundation for scalable, robust, and intelligent GUI agents that enhance user interaction in diverse software environments.

📄 PDF Abstract BibTeX arXiv:2503.20978

Code (0)

등록된 구현이 없습니다.

Tasks

Action Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction

2026-04-30 · Alex Petrov, Alexander Gusak, Denis Mukha, Dima Korolev arxiv

Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismat…

Object Detection

Learning to Represent State with Perceptual Schemata

2021-06-13 · ICML Workshop URL 2021 7 · Wilka Torrico Carvalho, Murray Shanahan

The real world is large and complex. It is filled with many objects besides those defined by a task and objects can move with their own interesting dynamics. How should an agent learn to represent state to support effici…

Zero-shot Generalization

DiagramBank: A Quality-Audited Dataset of Scientific Schematic Diagrams with Multi-Level Document Context

2026-02-28 · Ling Yue, Tingwen Zhang, Jiaying Wang, Zhen Xu 외 arxiv

Scientific papers use schematic diagrams to communicate methods, workflows, and system structure, yet existing scientific-figure corpora often mix them with plots, screenshots, and photographs and rarely preserve documen…

VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening

2026-07-28 · Syed Mhamudul Hasan, Anas AlSobeh, Hussein Zangoti, Abdur R. Shahid arxiv

We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing device and sends captured images, together with optional symptom descrip…

Image Classification

Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks

2020-06-13 · Adrian Sanchez-Caballero, David Fuentes-Jimenez, Cristina Losada-Gutiérrez

As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition …

Action RecognitionObject RecognitionScene UnderstandingTemporal Action Localization