Optimization & Theory

Regularizing Transformer-based Acoustic Models by Penalizing Attention Weights Interspeech 2022 Relational Surrogate Loss Learning ICLR 2022 ReMoNet: Recurrent Multi-Output Network for Efficient Video Denoising AAAI 2022 Removing Batch Normalization Boosts Adversarial Training ICML 2022 Rep-Net: Efficient On-Device Learning via Feature Reprogramming CVPR 2022 Reproducibility Issues for BERT-based Evaluation Metrics EMNLP 2022 Resource-Adaptive Federated Learning with All-In-One Neural Composition NeurIPS 2022 Restormer: Efficient Transformer for High-Resolution Image Restoration CVPR 2022 Rethinking and Refining the Distinct Metric ACL 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 Rethinking InfoNCE: How Many Negative Samples Do You Need? IJCAI 2022 Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NeurIPS 2022 Rethinking Resolution in the Context of Efficient Video Recognition NeurIPS 2022 Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones Is Enough AAAI 2022 Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters ACL 2022 Reverse Engineering the Neural Tangent Kernel ICML 2022 Reversible Vision Transformers CVPR 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection CVPR 2022 Revisiting Grammatical Error Correction Evaluation and Beyond EMNLP 2022 Revisiting Locality Sensitive Hashing for Vocabulary Selection in Fast Neural Machine Translation EMNLP 2022 Revisiting Over-smoothing in BERT from the Perspective of Graph ICLR 2022 Revisiting Random Channel Pruning for Neural Network Compression CVPR 2022 Revisiting Sparse Convolutional Model for Visual Recognition NeurIPS 2022 Revisiting Transformer-based Models for Long Document Classification EMNLP 2022