Zobrazeno 1 - 10
of 46 218
pro vyhledávání: '"A P Levine"'
Locally Markov walks are natural generalizations of classical Markov chains, where instead of a particle moving independently of the past, it decides where to move next depending on the last action performed at the current location. We introduce the
Externí odkaz:
http://arxiv.org/abs/2412.13766
Autor:
Zhou, Yifei, Yang, Qianlan, Lin, Kaixiang, Bai, Min, Zhou, Xiong, Wang, Yu-Xiong, Levine, Sergey, Li, Erran
The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation models. Such
Externí odkaz:
http://arxiv.org/abs/2412.13194
Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the quality of their training data.
Externí odkaz:
http://arxiv.org/abs/2412.09858
The modern paradigm in machine learning involves pre-training on diverse data, followed by task-specific fine-tuning. In reinforcement learning (RL), this translates to learning via offline RL on a diverse historical dataset, followed by rapid online
Externí odkaz:
http://arxiv.org/abs/2412.07762
Autor:
Hess, Rowan, Levine, Lionel
Given conflicting probability estimates for a set of events, how can we quantify how much they conflict? How can we find a single probability distribution that best encapsulates the given estimates? One approach is to minimize a loss function such as
Externí odkaz:
http://arxiv.org/abs/2412.02777
Autor:
Shalev-Shwartz, Shai, Shashua, Amnon, Beniamini, Gal, Levine, Yoav, Sharir, Or, Wies, Noam, Ben-Shaul, Ido, Nussbaum, Tomer, Peled, Shir Granot
Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human expe
Externí odkaz:
http://arxiv.org/abs/2412.02441
We study 2d dilaton gravity theories with a periodic potential, with special emphasis on sine dilaton gravity, which is holographically dual to double-scaled SYK. The periodicity of the potentials implies a symmetry under (discrete) shifts in the mom
Externí odkaz:
http://arxiv.org/abs/2411.16922
A fundamental open challenge in modern LLM scaling is the lack of understanding around emergent capabilities. In particular, language model pretraining loss is known to be highly predictable as a function of compute. However, downstream capabilities
Externí odkaz:
http://arxiv.org/abs/2411.16035
Autor:
Lu, Yiwen, Tong, Jiayi, Lei, Yuqing, Sutton, Alex J., Chu, Haitao, Levine, Lisa D., Lumley, Thomas, Asch, David A., Duan, Rui, Schmid, Christopher H., Chen, Yong
We introduce OrigamiPlot, an open-source R package and Shiny web application designed to enhance the visualization of multivariate data. This package implements the origami plot, a novel visualization technique proposed by Duan et al. in 2023, which
Externí odkaz:
http://arxiv.org/abs/2411.12674
Autor:
Kang, Katie, Setlur, Amrith, Ghosh, Dibya, Steinhardt, Jacob, Tomlin, Claire, Levine, Sergey, Kumar, Aviral
Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better understand how the learning dynamics of LLM finetuning shapes downstream
Externí odkaz:
http://arxiv.org/abs/2411.07681