Model Architecture

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion CVPR 2023 Long Document Summarization with Top-down and Bottom-up Inference EACL 2023 Lookaround Optimizer: k steps around, 1 step average NeurIPS 2023 LookupFFN: Making Transformers Compute-lite for CPU inference ICML 2023 Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit ICML 2023 Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single ICML 2023 MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions ICLR 2023 Machines of Finite Depth: Towards a Formalization of Neural Networks AAAI 2023 MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models ICCV 2023 Making Vision Transformers Efficient From a Token Sparsification View CVPR 2023 Manifold-Preserving Transformers are Effective for Short-Long Range Encoding EMNLP 2023 MARS: Masked Automatic Ranks Selection in Tensor Decompositions AISTATS 2023 Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers CVPR 2023 Massively Scaling Heteroscedastic Classifiers ICLR 2023 MathNAS: If Blocks Have a Role in Mathematical Architecture Design NeurIPS 2023 MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory NeurIPS 2023 Mechanistic Mode Connectivity ICML 2023 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion ICCV 2023 Memorization Capacity of Neural Networks with Conditional Computation ICLR 2023 MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation CVPR 2023 M-FUSE: Multi-Frame Fusion for Scene Flow Estimation WACV 2023 MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods ICML 2023 MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers NeurIPS 2023 Mimetic Initialization of Self-Attention Layers ICML 2023