Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Jin, Kebing"'
Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture implied rules from free-form
Externí odkaz:
http://arxiv.org/abs/2308.13782
Traditional Chinese Medicine (TCM) has a rich history of utilizing natural herbs to treat a diversity of illnesses. In practice, TCM diagnosis and treatment are highly personalized and organically holistic, requiring comprehensive consideration of th
Externí odkaz:
http://arxiv.org/abs/2305.17866
Hoist scheduling has become a bottleneck in electroplating industry applications with the development of autonomous devices. Although there are a few approaches proposed to target at the challenging problem, they generally cannot scale to large-scale
Externí odkaz:
http://arxiv.org/abs/2212.05412
There has been increasing attention on planning model learning in classical planning. Most existing approaches, however, focus on learning planning models from structured data in symbolic representations. It is often difficult to obtain such structur
Externí odkaz:
http://arxiv.org/abs/2211.15666
Autor:
Jin, Kebing, Zhuo, Hankz Hankui
Natural language processing (NLP) aims at investigating the interactions between agents and humans, processing and analyzing large amounts of natural language data. Large-scale language models play an important role in current natural language proces
Externí odkaz:
http://arxiv.org/abs/2202.07138
Although there have been approaches that are capable of learning action models from plan traces, there is no work on learning action models from textual observations, which is pervasive and much easier to collect from real-world applications compared
Externí odkaz:
http://arxiv.org/abs/2202.08373
Despite of achieving great success in real-world applications, Deep Reinforcement Learning (DRL) is still suffering from three critical issues, i.e., data efficiency, lack of the interpretability and transferability. Recent research shows that embedd
Externí odkaz:
http://arxiv.org/abs/2112.09836
In retrosynthetic planning, the huge number of possible routes to synthesize a complex molecule using simple building blocks leads to a combinatorial explosion of possibilities. Even experienced chemists often have difficulty to select the most promi
Externí odkaz:
http://arxiv.org/abs/2112.06028
Dealing with planning problems with both logical relations and numeric changes in real-world dynamic environments is challenging. Existing numeric planning systems for the problem often discretize numeric variables or impose convex constraints on num
Externí odkaz:
http://arxiv.org/abs/2110.10007
Publikováno v:
In Artificial Intelligence December 2022 313
