iiinova — where your digital self keeps evolving

Aviv Netanyahu

@avivnet.bsky.social

12 followers 12 following 5 posts

PhD candidate @MIT_CSAIL

Posts Replies Media

Aviv Netanyahu @avivnet.bsky.social · 06/12/2024

Joint work with awesome collaborators @yilundu.bsky.social, Antonia Bronars, Jyo Pari, @joshtenenbaum.bsky.social, @tianminshu.bsky.social and Pulkit Agrawal. Drop by our poster Thu, 4:30-7:30pm PT, West Ballroom A-D #6602! neurips.cc/virtual/2024...

neurips.cc

NeurIPS Poster Few-Shot Task Learning through Inverse Generative ModelingNeurIPS 2024

100

Aviv Netanyahu @avivnet.bsky.social · 06/12/2024

We evaluate our approach extensively and demonstrate that we successfully learn novel tasks and generate corresponding agent plans and motion in (1) unseen configurations and (2) in composition with training tasks.

100

Aviv Netanyahu @avivnet.bsky.social · 06/12/2024

Thanks to generative models’ compositional properties, in addition to inverting demos to a single latent representation, we invert demos into the latent space of composed generative models, enabling us to learn new tasks that are substantially different from the training tasks.

200

Aviv Netanyahu @avivnet.bsky.social · 06/12/2024

Tasks are often defined by a policy, reward, or trajectory, requiring retraining for new tasks. Inspired by few-shot visual concept learning via inverting generative models, we infer tasks represented as latent vectors without retraining.

200

Aviv Netanyahu @avivnet.bsky.social · 06/12/2024

Learning new tasks with imitation learning often requires hundreds of demos. Check out our #NeurIPS paper in which we learn new tasks from few demos by inverting them into the latent space of a generative model pre-trained on a set of base tasks. avivne.github.io/ftl-igm/

340