AkimotoAyako / VisionTasker
VisionTasker introduces a novel two-stage framework combining vision-based UI understanding and LLM task planning for mobile task automation in a step-by-step manner.
☆69Updated 2 months ago
Alternatives and similar repositories for VisionTasker:
Users that are interested in VisionTasker are comparing it to the libraries listed below
- Official implementation for "Android in the Zoo: Chain-of-Action-Thought for GUI Agents" (Findings of EMNLP 2024)☆85Updated 6 months ago
- GUI Odyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUI Odyssey consists of 7,735 episodes fr…☆109Updated 5 months ago
- ☆29Updated 7 months ago
- AndroidWorld is an environment and benchmark for autonomous agents☆297Updated this week
- A Universal Platform for Training and Evaluation of Mobile Interaction☆44Updated 2 months ago
- Official implementation of AppAgentX: Evolving GUI Agents as Proficient Smartphone Users☆345Updated 3 weeks ago
- The model, data and code for the visual GUI Agent SeeClick☆365Updated 5 months ago
- SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation☆30Updated last week
- LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation☆57Updated 8 months ago
- Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis☆130Updated last month
- GitHub page for "Large Language Model-Brained GUI Agents: A Survey"☆149Updated last week
- Code for "UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning"☆88Updated this week
- ☆29Updated 7 months ago
- Towards Large Multimodal Models as Visual Foundation Agents☆209Updated last week
- Source code for the paper "Empowering LLM to use Smartphone for Intelligent Task Automation"☆350Updated last year
- GUI Grounding for Professional High-Resolution Computer Use☆192Updated 2 months ago
- ✨✨Latest Papers and Datasets on Mobile and PC GUI Agent☆124Updated 5 months ago
- ☆214Updated 2 weeks ago
- Official implementation for "You Only Look at Screens: Multimodal Chain-of-Action Agents" (Findings of ACL 2024)☆233Updated 9 months ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆215Updated this week
- ☆41Updated last year
- GUICourse: From General Vision Langauge Models to Versatile GUI Agents☆114Updated 9 months ago
- ☆90Updated last year
- ☆40Updated last year
- Benchmarking Mobile Device Control Agents across Diverse Configurations (ICLR 2024 workshop GenAI4DM spotlight presentation)☆31Updated 4 months ago
- (ICLR 2025) The Official Code Repository for GUI-World.☆54Updated 4 months ago
- ☆34Updated 10 months ago
- MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding☆58Updated 2 months ago
- GPT-4V in Wonderland: LMMs as Smartphone Agents☆134Updated 9 months ago
- PC Agent: While You Sleep, AI Works - A Cognitive Journey into Digital World☆235Updated 4 months ago