Techniques

MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound CVPR 2022 Merry Go Round: Rotate a Frame and Fool a DNN CVPR 2022 Meta-Auto-Decoder for Solving Parametric Partial Differential Equations NeurIPS 2022 MetaFormer Is Actually What You Need for Vision CVPR 2022 Meta-Learning Fast Weight Language Models EMNLP 2022 MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding EMNLP 2022 MGNNI: Multiscale Graph Neural Networks with Implicit Layers NeurIPS 2022 MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling ICLR 2022 MiniViT: Compressing Vision Transformers With Weight Multiplexing CVPR 2022 Mitigating Neural Network Overconfidence with Logit Normalization ICML 2022 Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy NAACL 2022 Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA EMNLP 2022 Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech Interspeech 2022 MixFormer: Mixing Features Across Windows and Dimensions CVPR 2022 Mixture of Attention Heads: Selecting Attention Heads Per Token EMNLP 2022 Mixture-of-Experts with Expert Choice Routing NeurIPS 2022 MLP4Rec: A Pure MLP Architecture for Sequential Recommendations IJCAI 2022 MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation IJCAI 2022 Mobile Based Human Identification Using Forehead Creases: Application and Assessment Under COVID-19 Masked Face Scenarios WACV 2022 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer ICLR 2022 Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably) ICML 2022 Modality-specific Learning Rates for Effective Multimodal Additive Late-fusion ACL 2022 Model Preserving Compression for Neural Networks NeurIPS 2022 Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time ICML 2022 Modify Self-Attention via Skeleton Decomposition for Effective Point Cloud Transformer AAAI 2022