Zobrazeno 1 - 10
of 705
pro vyhledávání: '"Abbeel, Pieter"'
Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise from a sing
Externí odkaz:
http://arxiv.org/abs/2406.07398
Hierarchical control for robotics has long been plagued by the need to have a well defined interface layer to communicate between high-level task planners and low-level policies. With the advent of LLMs, language has been emerging as a prospective in
Externí odkaz:
http://arxiv.org/abs/2405.04798
Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile
Externí odkaz:
http://arxiv.org/abs/2403.10506
Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult for some tasks. Sim-to-real tran
Externí odkaz:
http://arxiv.org/abs/2403.04114
Open-vocabulary generalization requires robotic systems to perform tasks involving complex and diverse environments and task goals. While the recent advances in vision language models (VLMs) present unprecedented opportunities to solve unseen problem
Externí odkaz:
http://arxiv.org/abs/2403.03174
Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, attributed to the contact-rich nature of many manipulation tasks and the complexity inherent in coordinating a high-dimensional bimanual system. In thi
Externí odkaz:
http://arxiv.org/abs/2403.02338
Autor:
Yang, Sherry, Walker, Jacob, Parker-Holder, Jack, Du, Yilun, Bruce, Jake, Barreto, Andre, Abbeel, Pieter, Schuurmans, Dale
Both text and video data are abundant on the internet and support large-scale self-supervised learning through next token or frame prediction. However, they have not been equally leveraged: language models have had significant real-world impact, wher
Externí odkaz:
http://arxiv.org/abs/2402.17139
Can we pre-train a generalist agent from a large amount of unlabeled offline trajectories such that it can be immediately adapted to any new downstream tasks in a zero-shot manner? In this work, we present a functional reward encoding (FRE) as a gene
Externí odkaz:
http://arxiv.org/abs/2402.17135
Autor:
Souly, Alexandra, Lu, Qingyuan, Bowen, Dillon, Trinh, Tu, Hsieh, Elvis, Pandey, Sana, Abbeel, Pieter, Svegliato, Justin, Emmons, Scott, Watkins, Olivia, Toyer, Sam
The rise of large language models (LLMs) has drawn attention to the existence of "jailbreaks" that allow the models to be used maliciously. However, there is no standard benchmark for measuring the severity of a jailbreak, leaving authors of jailbrea
Externí odkaz:
http://arxiv.org/abs/2402.10260
Current language models fall short in understanding aspects of the world not easily described in words, and struggle with complex, long-form tasks. Video sequences offer valuable temporal information absent in language and static images, making them
Externí odkaz:
http://arxiv.org/abs/2402.08268