Zobrazeno 1 - 10
of 9 156
pro vyhledávání: '"Sungjin An"'
Significant advances have been made in developing general-purpose embodied AI in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. While these approaches, which combine high-level planners with low-level contr
Externí odkaz:
http://arxiv.org/abs/2411.06736
The facility location with strategic agents is a canonical problem in the literature on mechanism design without money. Recently, Agrawal et. al. considered this problem in the context of machine learning augmented algorithms, where the mechanism des
Externí odkaz:
http://arxiv.org/abs/2410.07497
In this paper, we explore how a natural generalization of Shortest Remaining Processing Time (SRPT) can be a powerful \emph{meta-algorithm} for online scheduling. The meta-algorithm processes jobs to maximally reduce the objective of the correspondin
Externí odkaz:
http://arxiv.org/abs/2409.03020
Large Language Models (LLMs) have great success in natural language processing tasks such as response generation. However, their use in tabular data has been limited due to their inferior performance compared to traditional machine learning models (T
Externí odkaz:
http://arxiv.org/abs/2408.10923
Recent State Space Models (SSMs) such as S4, S5, and Mamba have shown remarkable computational benefits in long-range temporal dependency modeling. However, in many sequence modeling problems, the underlying process is inherently modular and it is of
Externí odkaz:
http://arxiv.org/abs/2406.12272
Despite the recent advancements in offline RL, no unified algorithm could achieve superior performance across a broad range of tasks. Offline \textit{value function learning}, in particular, struggles with sparse-reward, long-horizon tasks due to the
Externí odkaz:
http://arxiv.org/abs/2406.06793
Online load balancing for heterogeneous machines aims to minimize the makespan (maximum machine workload) by scheduling arriving jobs with varying sizes on different machines. In the adversarial setting, where an adversary chooses not only the collec
Externí odkaz:
http://arxiv.org/abs/2405.07949
Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on auto-encoding objective, while t
Externí odkaz:
http://arxiv.org/abs/2405.00646
Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefo
Externí odkaz:
http://arxiv.org/abs/2402.18866
Autor:
Singh, Gautam, Wang, Yue, Yang, Jiawei, Ivanovic, Boris, Ahn, Sungjin, Pavone, Marco, Che, Tong
While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particular, existing object-centric models for handling sequential inputs, du
Externí odkaz:
http://arxiv.org/abs/2402.17077