Cover Image

UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Yuhao, Yang, Zhen, Dou, Zi-Yi, Nguyen, Anh, You, Keen, Attia, Omar, Szot, Andrew, Feng, Michael, Ramrakhya, Ram, Toshev, Alexander, Huang, Chao, Yang, Yinfei, Gan, Zhe
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
by: Yang, Zhen, et al.
Published: (2025)

Scaling Synthetic Task Generation for Agents via Exploration
by: Ramrakhya, Ram, et al.
Published: (2025)

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
by: You, Keen, et al.
Published: (2024)

OpenCUA: Open Foundations for Computer-Use Agents
by: Wang, Xinyuan, et al.
Published: (2025)

Expanding LLM Agent Boundaries with Strategy-Guided Exploration
by: Szot, Andrew, et al.
Published: (2026)

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
by: Qian, Yusu, et al.
Published: (2024)

Contrastive Localized Language-Image Pre-Training
by: Chen, Hong-You, et al.
Published: (2024)

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
by: Li, Zhangheng, et al.
Published: (2024)

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
by: Liao, Zeyi, et al.
Published: (2025)

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
by: Qian, Yusu, et al.
Published: (2024)

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
by: Szot, Andrew, et al.
Published: (2024)

Guiding Instruction-based Image Editing via Multimodal Large Language Models
by: Fu, Tsu-Jui, et al.
Published: (2023)

PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
by: Qian, Yusu, et al.
Published: (2025)

Compressing LLMs: The Truth is Rarely Pure and Never Simple
by: Jaiswal, Ajay, et al.
Published: (2023)

Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
by: Zhang, Yuhui, et al.
Published: (2023)

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
by: Liu, Zhaoyang, et al.
Published: (2025)

UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing
by: Fu, Tsu-Jui, et al.
Published: (2025)

LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
by: Mei, Kai, et al.
Published: (2025)

A11y-CUA Dataset: Characterizing the Accessibility Gap in Computer Use Agents
by: Mohanbabu, Ananya Gubbi, et al.
Published: (2026)

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
by: Jian, Xiangru, et al.
Published: (2026)

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
by: Qian, Yusu, et al.
Published: (2025)

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
by: Lai, Zhengfeng, et al.
Published: (2024)

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models
by: Zhang, Haotian, et al.
Published: (2024)

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
by: Zhang, Haotian, et al.
Published: (2024)

UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning
by: Tian, Rui, et al.
Published: (2025)

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
by: Li, Yanghao, et al.
Published: (2025)

Learning Next Action Predictors from Human-Computer Interaction
by: Shaikh, Omar, et al.
Published: (2026)

GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing
by: Qian, Yusu, et al.
Published: (2025)

The MUG-10 Framework for Preventing Usability Issues in Mobile Application Development
by: Weichbroth, Pawel, et al.
Published: (2025)

Improve Vision Language Model Chain-of-thought Reasoning
by: Zhang, Ruohong, et al.
Published: (2024)

Large Language Models as Generalizable Policies for Embodied Tasks
by: Szot, Andrew, et al.
Published: (2023)

Grounding Multimodal Large Language Models in Actions
by: Szot, Andrew, et al.
Published: (2024)

Seeing the Unseen: Visual Common Sense for Semantic Placement
by: Ramrakhya, Ram, et al.
Published: (2024)

IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents
by: Lee, Seoyoung, et al.
Published: (2026)

Conditional Font Generation With Content Pre‐Train and Style Filter
by: Yang Hong, et al.
Published: (2024)

Versatile SPH Open Boundary Conditions for Multiphase Flows in Extreme Condition
by: Zhan, Zi-Yang, et al.
Published: (2025)

A Survey on Trustworthiness in Foundation Models for Medical Image Analysis
by: Shi, Congzhen, et al.
Published: (2024)

Advancing Egocentric Video Question Answering with Multimodal Large Language Models
by: Patel, Alkesh, et al.
Published: (2025)

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
by: Narayan, Kartik, et al.
Published: (2025)

Understanding Alignment in Multimodal LLMs: A Comprehensive Study
by: Amirloo, Elmira, et al.
Published: (2024)