Model Compression

DepGraph: Towards Any Structural Pruning CVPR 2023 DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models EMNLP 2023 Detecting and Repairing Deviated Outputs of Compressed Models ACML 2023 DETRDistill: A Universal Knowledge Distillation Framework for DETR-families ICCV 2023 DFPC: Data flow driven pruning of coupled channels without data. ICLR 2023 Differentiable Transportation Pruning ICCV 2023 Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes ACL 2023 DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023 Don’t just prune by magnitude! Your mask topology is a secret weapon NeurIPS 2023 DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration CVPR 2023 DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization ACL 2023 Dual Student Networks for Data-Free Model Stealing ICLR 2023 DUnE: Dataset for Unified Editing EMNLP 2023 Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NeurIPS 2023 Dynamic Sparsity Is Channel-Level Sparsity Learner NeurIPS 2023 Dynamic Structure Pruning for Compressing CNNs AAAI 2023 EA-HAS-Bench: Energy-aware Hyperparameter and Architecture Search Benchmark ICLR 2023 EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs EMNLP 2023 EELBERT: Tiny Models through Dynamic Embeddings EMNLP 2023 EffConv: Efficient Learning of Kernel Sizes for Convolution Layers of CNNs AAAI 2023 Efficient Distributed Inference of Deep Neural Networks via Restructuring and Pruning AAAI 2023 Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming ICML 2023 Efficient Transformer Knowledge Distillation: A Performance Review EMNLP 2023 Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization EMNLP 2023 EQ-Net: Elastic Quantization Neural Networks ICCV 2023