Xiaoliang Dai

TL;DR: This work proposes a differentiable neural architecture search (DNAS) framework that uses gradient-based methods to optimize ConvNet architectures, avoiding enumerating and training individual architectures separately as in previous methods.

TL;DR: This work represents images as a set of visual tokens and applies visual transformers to find relationships between visual semantic concepts to densely model relationships between them, and finds that this paradigm of token-based image representation and processing drastically outperforms its convolutional counterparts on image classification and semantic segmentation.

TL;DR: The results show that adapting computation resources to building blocks is critical to model performance, and a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors is proposed.

TL;DR: DMaskingNAS as mentioned in this paper proposes a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands, and employs effective shape propagation to maximize per-FLOP or per-parameter accuracy.

TL;DR: Chameleon as mentioned in this paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, instead of exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints.