Efficient Computing

Selecting Large Language Model to Fine-tune via Rectified Scaling Law ICML 2024 Selective Perception: Learning Concise State Descriptions for Language Model Actors NAACL 2024 Selective Prefix Tuning for Pre-trained Language Models ACL 2024 SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching ICML 2024 Separable Self and Mixed Attention Transformers for Efficient Object Tracking WACV 2024 SEQ-former: A context-enhanced and efficient automatic speech recognition framework Interspeech 2024 Sequoia: Scalable and Robust Speculative Decoding NeurIPS 2024 ServiceLab: Preventing Tiny Performance Regressions at Hyperscale through Pre-Production Testing OSDI 2024 SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic ICML 2024 ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models EMNLP 2024 Sharing Key Semantics in Transformer Makes Efficient Image Restoration NeurIPS 2024 Sharpness-Aware Data Generation for Zero-shot Quantization ICML 2024 Sheared Backpropagation for Fine-tuning Foundation Models CVPR 2024 Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning ICLR 2024 ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization NeurIPS 2024 Shimo Lab at “Discharge Me!”: Discharge Summarization by Prompt-Driven Concatenation of Electronic Health Record Sections ACL 2024 Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences ICML 2024 Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networks AAAI 2024 SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design CVPR 2024 SICAR at RRG2024: GPU Poor’s Guide to Radiology Report Generation ACL 2024 Sieve: Multimodal Dataset Pruning using Image Captioning Models CVPR 2024 Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network ICML 2024 SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding ICML 2024 SILVER: Single-loop variance reduction and application to federated learning ICML 2024 SimA: Simple Softmax-Free Attention for Vision Transformers WACV 2024