P
Pierre Sermanet
Researcher at Google
Publications - 66
Citations - 53384
Pierre Sermanet is an academic researcher from Google. The author has contributed to research in topics: Feature learning & Computer science. The author has an hindex of 29, co-authored 56 publications receiving 40360 citations. Previous affiliations of Pierre Sermanet include New York University & Courant Institute of Mathematical Sciences.
Papers
More filters
Proceedings ArticleDOI
Temporal Cycle-Consistency Learning
TL;DR: It is shown that the learned embeddings enable few-shot classification of these action phases, significantly reducing the supervised training requirements; and TCC is complementary to other methods of self-supervised learning in videos, such as Shuffle and Learn and Time-Contrastive Networks.
Journal ArticleDOI
PaLM-E: An Embodied Multimodal Language Model
Danny Driess,Fei Xia,Mehdi Sajjadi,Corey Lynch,Aakanksha Chowdhery,Brian Ichter,Ayzaan Wahid,Jonathan James Richard Tompson,Quan Vuong,Tianhe Yu,Wenrong Huang,Yevgen Chebotar,Pierre Sermanet,Daniel Duckworth,Sergey Levine,Vincent Vanhoucke,Karol Hausman,Marc Toussaint,Klaus Greff,Andy Zeng,Igor Mordatch,Peter R. Florence +21 more
TL;DR: In this paper , an embodied language model is proposed to directly incorporate real-world continuous sensor modalities into language models and establish the link between words and percepts for embodied reasoning tasks, including sequential robotic manipulation planning, visual question answering, and captioning.
Posted Content
Learning Latent Plans from Play
Corey Lynch,Mohi Khansari,Ted Xiao,Vikash Kumar,Jonathan Tompson,Sergey Levine,Pierre Sermanet +6 more
TL;DR: Play-LMP is introduced, a method designed to handle variability in the LfP setting by organizing it in an embedding space and finding that play-supervised models, unlike their expert-trained counterparts, are more robust to perturbations and exhibit retrying-till-success.
Proceedings ArticleDOI
Unsupervised Perceptual Rewards for Imitation Learning
TL;DR: In this paper, a method was proposed to identify key intermediate steps of a task from only a handful of demonstration sequences, and automatically identify the most discriminative features for identifying these steps.
Learning Latent Plans from Play
Corey Lynch,Mohi Khansari,Ted Xiao,Vikash Kumar,Jonathan Tompson,Sergey Levine,Pierre Sermanet +6 more
TL;DR: In this article, a self-supervised method that learns to organize play behaviors in a latent space, then reuse them at test time to achieve specific goals is proposed. But this method requires a large amount of play data.