Efficient Computing

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models ACL 2024 Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation MIDL 2024 Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads ICML 2024 MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter ACL 2024 MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs NSDI 2024 Membership Inference Attacks against Large Vision-Language Models NeurIPS 2024 Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk EMNLP 2024 Memory Consolidation Enables Long-Context Video Understanding ICML 2024 Memory-Efficient Fine-Tuning of Transformers via Token Selection EMNLP 2024 Memory-Efficient LLM Training with Online Subspace Descent NeurIPS 2024 Memory Efficient Neural Processes via Constant Memory Attention Block ICML 2024 Memory-Efficient Reversible Spiking Neural Networks AAAI 2024 MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers NeurIPS 2024 MemoryPrompt: A Light Wrapper to Improve Context Tracking in Pre-trained Language Models COLING 2024 Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning ICML 2024 Mercury: A Code Efficiency Benchmark for Code Large Language Models NeurIPS 2024 MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks ECCV 2024 MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters IJCAI 2024 MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration EMNLP 2024 MGit: A Model Versioning and Management System ICML 2024 MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence NeurIPS 2024 Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary ICML 2024 MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention NeurIPS 2024 MiniCache: KV Cache Compression in Depth Dimension for Large Language Models NeurIPS 2024 Minimal Distillation Schedule for Extreme Language Model Compression EACL 2024