Efficient Computing

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference EACL 2024 SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead NeurIPS 2024 SparQ Attention: Bandwidth-Efficient LLM Inference ICML 2024 Sparse Binarization for Fast Keyword Spotting Interspeech 2024 Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once ICML 2024 Sparse Dimensionality Reduction Revisited ICML 2024 SparseFlow: Accelerating Transformers by Sparsifying Information Flows ACL 2024 Sparse High Rank Adapters NeurIPS 2024 Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency ICML 2024 Sparse maximal update parameterization: A holistic approach to sparse training dynamics NeurIPS 2024 Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications ICML 2024 Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization ICML 2024 Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities ICML 2024 SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters ICML 2024 SparseWAV: Fast and Accurate One-Shot Unstructured Pruning for Large Speech Foundation Models Interspeech 2024 SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities CVPR 2024 Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers ICLR 2024 Speaker Personalization for Automatic Speech Recognition using Weight-Decomposed Low-Rank Adaptation Interspeech 2024 SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices NeurIPS 2024 SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding EMNLP 2024 Spectral Adapter: Fine-Tuning in Spectral Space NeurIPS 2024 Spectroformer: Multi-Domain Query Cascaded Transformer Network for Underwater Image Enhancement WACV 2024 Speculative Contrastive Decoding ACL 2024 Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism ACL 2024 Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NeurIPS 2024