Techniques

Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization ICLR 2022 DENTRA: Denoising and Translation Pre-training for Multilingual Machine Translation EMNLP 2022 Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators COLT 2022 DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks ICML 2022 DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances Interspeech 2022 DextAIRity: Deformable Manipulation Can be a Breeze RSS 2022 DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning IJCAI 2022 Differentiable Data Augmentation for Contrastive Sentence Representation Learning EMNLP 2022 Differentiable hierarchical and surrogate gradient search for spiking neural networks NeurIPS 2022 Differentiable Stereopsis: Meshes From Multiple Views Using Differentiable Rendering CVPR 2022 DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles CoRL 2022 Dimension Embeddings for Monocular 3D Object Detection CVPR 2022 DisARM: Displacement Aware Relation Module for 3D Detection CVPR 2022 Discourse-Aware Soft Prompting for Text Generation EMNLP 2022 Discrete Representations Strengthen Vision Transformer Robustness ICLR 2022 DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training ICML 2022 DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems AAAI 2022 Distributional properties of political dogwhistle representations in Swedish BERT NAACL 2022 Distribution Consistent Neural Architecture Search CVPR 2022 Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions ICLR 2022 Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model ACL 2022 Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models ACL 2022 Divisive Feature Normalization Improves Image Recognition Performance in AlexNet ICLR 2022 DKM: Differentiable k-Means Clustering Layer for Neural Network Compression ICLR 2022 Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval ACL 2022