Introducing GEN-1.5, a one-shot learner
Humans have a remarkable ability to perform new physical skills from only one or a few examples. Our latest robot foundation model, GEN-1.5, exhibits the beginnings of that same ability: it can learn a new task in seconds, from a single example, without gradient updates or fine-tuning. It displays broad capabilities across one-shot and few-shot learning from demonstration, as well as zero-shot physical generalization. Although the tasks are simple and short-horizon, this is the first model we know for which one-shot and few-shot learning of physical skills have emerged at scale. We view these results as a significant step towards our mission of building general intelligence for the physical world. Read more about our work at https://generalistai.com/blog/gen-1.5
Video Chapters
- 0:00 Introduction to the GEN-1.5 One-Shot Learner Robot Foundation Model
- 1:01 How Physical Prompting Enables Instant Generalization Without Model Training
- 1:51 Demonstrating Novel Tool Use and Real-Time Improvisational Intelligence
- 2:58 Human-to-Robot In-Context Learning Through Live Physical Mimicry Demonstrations
Original Output
0:00 Introduction to the GEN-1.5 One-Shot Learner Robot Foundation Model 1:01 How Physical Prompting Enables Instant Generalization Without Model Training 1:51 Demonstrating Novel Tool Use and Real-Time Improvisational Intelligence 2:58 Human-to-Robot In-Context Learning Through Live Physical Mimicry Demonstrations Timestamps by StampBot 🤖 (590-introducing-gen-1-5-a-one-shot-learner)
Unprocessed Timestamp Content
0:00 Introduction to the GEN-1.5 One-Shot Learner Robot Foundation Model 1:01 How Physical Prompting Enables Instant Generalization Without Model Training 1:51 Demonstrating Novel Tool Use and Real-Time Improvisational Intelligence 2:58 Human-to-Robot In-Context Learning Through Live Physical Mimicry Demonstrations Timestamps by StampBot 🤖 (590-introducing-gen-1-5-a-one-shot-learner)