Distributed coordination and resource allocation benchmarks for evaluating multi-agent autonomy.
SPAR (Scalable LLM-based PDDL Domain Generation for Aerial Robotics) is a framework that leverages the generative capabilities of LLMs to automatically produce valid, diverse, and semantically accurate PDDL domains from natural language input.
First rigorous benchmark for advancing multimodal dataset creation.
Data synthesis pipeline generating high-quality alignment data for LLMs
The state-of-the-art open-source platform to design, simulate, and train AI-based robots.
An open source implementation of OpenAI's CLIP
An open-source framework for training large multimodal models
Democratizing Hardware Design: leading open-source application for semiconductor digital design
Fully open data curation for reasoning models