Model Compression

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER CVPR 2023 FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits CVPR 2023 FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference ACL 2023 Fixed Input Parameterization for Efficient Prompting ACL 2023 Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation ACL 2023 Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification EMNLP 2023 ForestPrune: Compact Depth-Pruned Tree Ensembles AISTATS 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 GPT4All: An Ecosystem of Open Source Compressed Language Models EMNLP 2023 GPU-accelerated Guided Source Separation for Meeting Transcription Interspeech 2023 Gradient-based Gradual Pruning for Language-Specific Multilingual Neural Machine Translation EMNLP 2023 GreenKGC: A Lightweight Knowledge Graph Completion Method ACL 2023 G-SPEED: General SParse Efficient Editing MoDel EMNLP 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023 HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks AAAI 2023 Heavy Sets with Applications to Interpretable Machine Learning Diagnostics AISTATS 2023 How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives ACL 2023 Itri Amigos at ArAIEval Shared Task: Transformer vs. Compression-Based Models for Persuasion Techniques and Disinformation Detection EMNLP 2023 Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers CVPR 2023 Large-Capacity and Flexible Video Steganography via Invertible Neural Network CVPR 2023 Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefix EMNLP 2023 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 Less is More: Task-aware Layer-wise Distillation for Language Model Compression ICML 2023 Lifting the Curse of Capacity Gap in Distilling Language Models ACL 2023