8 citations · 10 across the 3 of their papers we have counts for
7 papers
HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
Sirui Xie, Xiaojian Ma, Peiyu Yu +3
Humans learn compositional and causal abstraction, \ie, knowledge, in response to the structure of naturalistic tasks. When presented with a problem-solving task involving some obj…
Generalized Inverse Planning: Learning Lifted non-Markovian Utility for Generalizable Task Representation
Sirui Xie, Feng Gao, Song-Chun Zhu
In searching for a generalizable representation of temporally extended tasks, we spot two necessary constituents: the utility needs to be non-Markovian to transfer temporal relatio…
Understanding the wiring evolution in differentiable neural architecture search
Sirui Xie, Shoukang Hu, Xinjiang Wang +4
Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underl…
DSNAS: Direct Neural Architecture Search without Parameter Retraining
Shoukang Hu, Sirui Xie, Hehui Zheng +4
If NAS methods are solutions, what is the problem? Most existing NAS methods require two-stage parameter optimization. However, performance of the same architecture in the two stag…
Graph-guided Architecture Search for Real-time Semantic Segmentation
Peiwen Lin, Peng Sun, Guangliang Cheng +3
Designing a lightweight semantic segmentation network often requires researchers to find a trade-off between performance and speed, which is always empirical due to the limited int…
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
Sirui Xie, Junning Huang, Lanxin Lei +4
Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent ex…