MKD2World: A Typed Spatial MarkDown World Model For Web Agents
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/OmniAI-Lab-CUHKSZ/MKD2World
Terminology
Sources
- ScreenAI: A Vision-Language Model for UI and Infographics Understanding
- Xiaomi-GUI-0 Technical Report
- MobileDreamer: Generative Sketch World Model for GUI Agent
- SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
- WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
- WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
- Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
- Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
- Computer-Using World Model
- MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
- ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
- Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
- VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
- Generative Visual Code Mobile World Models
- Harnessing Webpage UIs for Text-Rich Visual Understanding
- OmniParser for Pure Vision Based GUI Agent
- ViMo: A Generative Visual GUI World Model for App Agents
- R-WoM: Retrieval-augmented World Model For Computer-use Agents
- UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
- WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs