Model Compression

Enhancing Scalability of Pre-trained Language Models via Efficient Parameter Sharing EMNLP 2023 Equivariant Architectures for Learning in Deep Weight Spaces ICML 2023 ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks AAAI 2023 Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting It into MLPs: An Effective GNN-to-MLP Distillation Framework AAAI 2023 FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer AAAI 2023 Facto-CNN: Memory-Efficient CNN Training with Low-rank Tensor Factorization and Lossy Tensor Compression ACML 2023 Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training CVPR 2023 FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices EMNLP 2023 Fast and Accurate Binary Neural Networks Based on Depth-Width Reshaping AAAI 2023 Fast as CHITA: Neural Network Pruning with Combinatorial Optimization ICML 2023 FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER CVPR 2023 Finding the Pillars of Strength for Multi-Head Attention ACL 2023 FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU ICML 2023 FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-Off Between Accuracy and Robustness WACV 2023 ForestPrune: Compact Depth-Pruned Tree Ensembles AISTATS 2023 Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge NSDI 2023 Generic-to-Specific Distillation of Masked Autoencoders CVPR 2023 Genie: Show Me the Data for Quantization CVPR 2023 Global Vision Transformer Pruning With Hessian-Aware Saliency CVPR 2023 GOHSP: A Unified Framework of Graph and Optimization-Based Heterogeneous Structured Pruning for Vision Transformer AAAI 2023 GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints EMNLP 2023 Gradient-based Gradual Pruning for Language-Specific Multilingual Neural Machine Translation EMNLP 2023 GreenKGC: A Lightweight Knowledge Graph Completion Method ACL 2023 GWQ: Group-Wise Quantization Framework for Neural Networks ACML 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023