google-research-datasets / seq2actLinks
This repository contains the opensource version of the datasets were used for different parts of training and testing of models that ground natural language to UI actions as described in the paper: "Mapping Natural Language Instructions to Mobile UI Action Sequences" by Yang Li, Jiacong He, Xin Zhou, Yuan Zhang, and Jason Baldridge, which is acc…
☆32Updated 5 years ago
Alternatives and similar repositories for seq2act
Users that are interested in seq2act are comparing it to the libraries listed below
Sorting:
- Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments☆60Updated last year
- A Universal Platform for Training and Evaluation of Mobile Interaction☆58Updated 3 months ago
- Official implementation for "You Only Look at Screens: Multimodal Chain-of-Action Agents" (Findings of ACL 2024)☆254Updated last year
- [EMNLP 2022] The baseline code for META-GUI dataset☆14Updated last year
- [ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control☆63Updated 11 months ago
- It includes two datasets that are used in the downstream tasks for evaluating UIBert: App Similar Element Retrieval data and Visual Item …☆46Updated 4 years ago
- ☆20Updated last year
- GUICourse: From General Vision Langauge Models to Versatile GUI Agents☆134Updated last year
- [ICLR 2024] MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use☆101Updated last year
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆147Updated last year
- ☆54Updated 2 years ago
- The dataset includes screen summaries that describes Android app screenshot's functionalities. It is used for training and evaluation of …☆60Updated 4 years ago
- GPT-4V in Wonderland: LMMs as Smartphone Agents☆135Updated last year
- The dataset includes widget captions that describes UI element's functionalities. It is used for training and evaluation of the widget ca…☆23Updated 4 years ago
- ☆31Updated last year
- InstructCoder: Instruction Tuning Large Language Models for Code Editing | Oral ACL-2024 srw☆64Updated last year
- [ICML'24] TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks☆31Updated last year
- The dataset includes UI object type labels (e.g., BUTTON, IMAGE, CHECKBOX) that describes the semantic type of an UI object on Android ap…☆53Updated 3 years ago
- Seq2act: Mapping Natural Language Instructions to Mobile UI Action Sequences from Google research☆15Updated 5 years ago
- Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding☆28Updated last year
- The Screen Annotation dataset consists of pairs of mobile screenshots and their annotations. The annotations are in text format, and desc…☆80Updated last year
- Consists of ~500k human annotations on the RICO dataset identifying various icons based on their shapes and semantics, and associations b…☆32Updated last year
- VisualWebArena is a benchmark for multimodal agents.☆420Updated last year
- DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems☆60Updated last year
- ☆28Updated last month
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆63Updated last year
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆85Updated last year
- ☆41Updated last year
- Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23)☆90Updated 2 years ago
- [ACL 2024] On the Multi-turn Instruction Following for Conversational Web Agents☆16Updated last year