Model Compression

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models EMNLP 2024 Dodo: Dynamic Contextual Compression for Decoder-only LMs ACL 2024 DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging EMNLP 2024 Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning CVPR 2024 DSD²: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free? AAAI 2024 DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs NeurIPS 2024 Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis CVPR 2024 Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs ICLR 2024 EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees EMNLP 2024 Efficient Low-Dimensional Compression of Overparameterized Models AISTATS 2024 Efficient Multitask Dense Predictor via Binarization CVPR 2024 Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters NeurIPS 2024 Efficient Reinforcement Learning by Discovering Neural Pathways NeurIPS 2024 Efficient Stitchable Task Adaptation CVPR 2024 ELAD: Explanation-Guided Large Language Models Active Distillation ACL 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective NeurIPS 2024 Entropy Induced Pruning Framework for Convolutional Neural Networks AAAI 2024 EPSD: Early Pruning with Self-Distillation for Efficient Model Compression AAAI 2024 ESPACE: Dimensionality Reduction of Activations for Model Compression NeurIPS 2024 Expanding Sparse Tuning for Low Memory Usage NeurIPS 2024 Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion NeurIPS 2024 Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models IJCAI 2024 Exploring Quantization for Efficient Pre-Training of Transformer Language Models EMNLP 2024 Exploring Space Efficiency in a Tree-based Linear Model for Extreme Multi-label Classification EMNLP 2024