rese1f/STEVE
[ECCV 2024] STEVE in Minecraft is for See and Think: Embodied Agent in Virtual Environment
This project helps researchers and developers create embodied AI agents that can 'see' and 'think' in virtual environments like Minecraft. It takes visual input (images/videos) and agent status, along with a task description, and outputs a series of actions or code to accomplish complex goals. This is designed for AI researchers working on advanced agent behavior and autonomous systems.
No commits in the last 6 months.
Use this if you are an AI researcher developing intelligent agents that need to interpret complex visual information and perform multi-step tasks in dynamic virtual worlds.
Not ideal if you need a simple script to automate basic game functions or are looking for a tool for general-purpose game development without advanced AI reasoning.
Stars
41
Forks
—
Language
—
License
MIT
Category
Last pushed
Dec 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/rese1f/STEVE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TinyLLaVA/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
zjunlp/EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
rese1f/MovieChat
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies