Efficient Computing

Simple linear attention language models balance the recall-throughput tradeoff ICML 2024 Simple Post-Training Robustness Using Test Time Augmentations and Random Forest WACV 2024 SIRIUS : Contexual Sparisty with Correction for Efficient LLMs NeurIPS 2024 Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation ICLR 2024 Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information NeurIPS 2024 Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels AISTATS 2024 Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning NeurIPS 2024 Skip-Attention: Improving Vision Transformers by Paying Less Attention ICLR 2024 SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization ICML 2024 SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks ICML 2024 SliceGPT: Compress Large Language Models by Deleting Rows and Columns ICLR 2024 Slicing Vision Transformer for Flexible Inference NeurIPS 2024 SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics NAACL 2024 SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow ECCV 2024 SLiM: Speculative Decoding with Hypothesis Reduction NAACL 2024 SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter ICML 2024 SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers CVPR 2024 Small Language Models Are Good Too: An Empirical Study of Zero-Shot Classification COLING 2024 SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction CVPR 2024 SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models COLING 2024 SnapKV: LLM Knows What You are Looking for Before Generation NeurIPS 2024 SNP: Structured Neuron-level Pruning to Preserve Attention Scores ECCV 2024 Soft Prompt Recovers Compressed LLMs, Transferably ICML 2024 SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model NeurIPS 2024 Solar Power Generation Forecasting via Multimodal Feature Fusion (Student Abstract) AAAI 2024