Latent World Action Model for GUI Agents
cs.CV, cs.AI, cs.HC
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/sjyu001/latent2world
Project page: https://hchoi256.github.io/projects/latent2world/1
Sources
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- MobileDreamer: Generative Sketch World Model for GUI Agent
- LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
- ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
- Qwen3-VL Technical Report
- SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
- How Mobile World Model Guides GUI Agents?
- Mobile-Agent-v3: Fundamental Agents for GUI Automation
- Code2World: A GUI World Model via Renderable Code Generation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models