Model Compression

Learning To Compose SuperWeights for Neural Parameter Allocation Search WACV 2024 Learning to Compress Prompt in Natural Language Formats NAACL 2024 Learn it or Leave it: Module Composition and Pruning for Continual Learning ACL 2024 Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval AAAI 2024 Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models EMNLP 2024 Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning AAAI 2024 LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication NeurIPS 2024 Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning ACL 2024 Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models NeurIPS 2024 LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning NeurIPS 2024 Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection EMNLP 2024 LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment NeurIPS 2024 LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit EMNLP 2024 LLM in a flash: Efficient Large Language Model Inference with Limited Memory ACL 2024 LLM-QAT: Data-Free Quantization Aware Training for Large Language Models ACL 2024 LLMR: Knowledge Distillation with a Large Language Model-Induced Reward COLING 2024 Look-Up Table Compression for Efficient Image Restoration CVPR 2024 LoRA-GA: Low-Rank Adaptation with Gradient Approximation NeurIPS 2024 LoRAN: Improved Low-Rank Adaptation by a Non-Linear Transformation EMNLP 2024 LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning ACL 2024 LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking CVPR 2024 Low Precision Local Training is Enough for Federated Learning NeurIPS 2024 Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach CVPR 2024 M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning EMNLP 2024 M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy AAAI 2024