cube-to-cup-act is an open-source imitation learning policy for robotics, implementing action chunking with transformers. Distributed via Hugging Face, it allows researchers and developers to train, evaluate, and deploy robotic policies for manipulation tasks. The model supports integration with robotics frameworks and fine-tuning for custom use cases.
Cube To Cup Act sits in PulseGate's Other AI category. It focuses on enabling robotics researchers to use and fine-tune an open-source imitation learning policy for action chunking tasks. It is built as an open-source project for robotics researchers and developers. Cube To Cup Act is open source under the Apache-2.0 license. Cube To Cup Act is available on the web, API, and the command line, and it can be self-hosted.
It is developed by andresrcom, and the product first shipped in 2024. Development happens publicly on GitHub with 25.8k stars and 158 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Cube To Cup Act occupies a relatively distinct niche. Key capabilities include imitation learning, action chunking, and robotics policy.
Latest indexed changes and source events
andresrcom/cube-to-cup-act discovered by the PulseGate indexer
Other apps tracked under the same category.
