Model Compression

MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer EMNLP 2023 NarrowBERT: Accelerating Masked Language Model Pretraining and Inference ACL 2023 NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models EMNLP 2023 Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models ACL 2023 NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers CVPR 2023 NTK-SAP: Improving neural network pruning by aligning training dynamics ICLR 2023 OMPQ: Orthogonal Mixed Precision Quantization AAAI 2023 On Biased Compression for Distributed Learning JMLR 2023 On Distillation of Guided Diffusion Models CVPR 2023 On Surgical Fine-tuning for Language Encoders EMNLP 2023 Parameter-Efficient Fine-Tuning without Introducing New Latency ACL 2023 Parameter-Efficient Learning for Text-to-Speech Accent Adaptation Interspeech 2023 Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts EMNLP 2023 Parameter-efficient Tuning for Large Language Model without Calculating Its Gradients EMNLP 2023 Partial Network Cloning CVPR 2023 Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023 Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets NeurIPS 2023 Practical Network Acceleration With Tiny Sets CVPR 2023 Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference AAAI 2023 Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models ICML 2023 Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge CVPR 2023 Pruning Pre-trained Language Models with Principled Importance and Self-regularization ACL 2023 Q-DETR: An Efficient Low-Bit Quantized Detection Transformer CVPR 2023 Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation EMNLP 2023 Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization CVPR 2023