Optimization & Theory

Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token EMNLP 2022 Massive-scale Decoding for Text Generation using Lattices NAACL 2022 Matryoshka Representation Learning NeurIPS 2022 Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks JMLR 2022 Measures of Information Reflect Memorization Patterns NeurIPS 2022 Measuring Compositional Consistency for Video Question Answering CVPR 2022 Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022 Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization NeurIPS 2022 Memory safe computations with XLA compiler NeurIPS 2022 MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution ICML 2022 Merry Go Round: Rotate a Frame and Fool a DNN CVPR 2022 MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022 Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond ICLR 2022 MINIMAL: Mining Models for Universal Adversarial Triggers AAAI 2022 Minimizing Control for Credit Assignment with Strong Feedback ICML 2022 MISRNet: Lightweight Neural Vocoder Using Multi-Input Single Shared Residual Blocks Interspeech 2022 Mixture of Attention Heads: Selecting Attention Heads Per Token EMNLP 2022 MLink: Linking Black-Box Models for Collaborative Multi-Model Inference AAAI 2022 MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences EMNLP 2022 Mobile-Former: Bridging MobileNet and Transformer CVPR 2022 Modality-specific Learning Rates for Effective Multimodal Additive Late-fusion ACL 2022 Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems EMNLP 2022 Model Criticism for Long-Form Text Generation EMNLP 2022 Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers AAAI 2022 Modeling Context With Linear Attention for Scalable Document-Level Translation EMNLP 2022