276 citations · 344 across the 14 of their papers we have counts for
9 papers · 1 filter
Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
Peiyu Yu, Yaxuan Zhu, Sirui Xie +4
Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in the field of generative modeling due to its flexibility in the formulati…
Learning non-Markovian Decision-Making from State-only Sequences
Aoyang Qin, Feng Gao, Qing Li +2
Conventional imitation learning assumes access to the actions of demonstrators, but these motor signals are often non-observable in naturalistic settings. Additionally, sequential…
Latent Diffusion Energy-Based Model for Interpretable Text Modeling
Peiyu Yu, Sirui Xie, Xiaojian Ma +6
Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and st…
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…
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…
SNAS: Stochastic Neural Architecture Search
Sirui Xie, Hehui Zheng, Chunxiao Liu +1
We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architect…