Projects sharing features with Dobb E

Voyager is an autonomous embodied agent and lifelong learning framework that uses a large language model to explore virtual environments. It functions as a code-based action controller, translating natural language instructions into executable scripts to interact with its surroundings. The system features an automatic curriculum generator that creates sequences of exploration goals to discover new items and behaviors without human intervention. It maintains a skill library manager that stores learned behaviors as reusable code fragments, which can be composed to execute complex tasks. The fr

[Paper](https://arxiv.org/abs/2210.05663) [Website](https://mahis.life/clip-fields/) [Code](https://github.com/notmahi/clip-fields) [Data](https://osf.io/famgv) [Video](https://youtu.be/bKu7GvRiSQU)

Unified Human-Scene Interaction via Prompted Chain-of-Contacts Zeqi Xiao   Tai Wang   Jingbo Wang   Jinkun Cao   Wenwei Zhang   Bo Dai   Dahua Lin   Jiangmiao Pang*   Shanghai AI Laboratory Nanyang Technological University Carnegie Mellon University

Code for LLM-Planner.

STEVE, named after the protagonist of the game Minecraft, is our proposed framework aims to build an embodied agent based on the vision model and LLMs within an open world.

ReAct is an agentic workflow template and prompting framework for large language models. It implements a logic pattern that integrates chain-of-thought reasoning with external tool execution to solve complex, multi-step tasks. The framework uses an interleaved reasoning and acting logic, forcing the model to document its internal thought process before executing an action. This cycle of planning and acting allows the system to interact with external APIs or databases and inject real-world data back into the model context to refine reasoning paths. The project covers autonomous task execution

[Website](http://craftjarvis-jarvis1.github.io/) [Paper](https://arxiv.org/abs/2311.05997) [Twitter](https://twitter.com/jeasinema/status/1723900032653643796)

CVPR 2024 The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'