act_slow_v2 is an open source imitation learning model for robotics, implementing action chunking with transformers. It enables researchers and developers to train and deploy robotic control policies using teleoperated data, with open weights and support for local and cloud inference.
Act Slow is an Other AI product. It focuses on providing an open source imitation learning model for robotics control using action chunking with transformers. It is built as an open-source project for robotics researchers and developers. Act Slow is open source under the Apache-2.0 license. Act Slow is available on the web and the command line, and it can be self-hosted.
siangyi-br builds and maintains Act Slow, and the product first shipped in 2024. Development happens publicly on GitHub with 25.8k stars and 155 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Act Slow occupies a relatively distinct niche. Key capabilities include imitation learning, action chunking, and robotics control.
Latest indexed changes and source events
siangyi-br/act_slow_v2 discovered by the PulseGate indexer
Other apps tracked under the same category.
