Techniques

MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for speech recognition Interspeech 2023 mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations EMNLP 2023 Mnemonist: Locating Model Parameters that Memorize Training Examples UAI 2023 MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models ICLR 2023 MobileOne: An Improved One Millisecond Mobile Backbone CVPR 2023 Model-Based Control with Sparse Neural Dynamics NeurIPS 2023 Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers ACL 2023 ModelGiF: Gradient Fields for Model Functional Distance ICCV 2023 ModelKeeper: Accelerating DNN Training via Automated Training Warmup NSDI 2023 Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN ICLR 2023 Modelling Political Aggression on Social Media Platforms ACL 2023 Modelling Temporal Document Sequences for Clinical ICD Coding EACL 2023 Model-tuning Via Prompts Makes NLP Models Adversarially Robust EMNLP 2023 Module-wise Training of Neural Networks via the Minimizing Movement Scheme NeurIPS 2023 MoEC: Mixture of Expert Clusters AAAI 2023 Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules ICLR 2023 Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching ICLR 2023 Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture NeurIPS 2023 Monaural Speech Separation Method Based on Recurrent Attention with Parallel Branches Interspeech 2023 MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos ICCV 2023 MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope ICCV 2023 More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity ICLR 2023 More Than Just Attention: Improving Cross-Modal Attentions With Contrastive Constraints for Image-Text Matching WACV 2023 MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining NeurIPS 2023 mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video ICML 2023