Efficient Computing

Separable Physics-Informed Neural Networks NeurIPS 2023 Sequence Parallelism: Long Sequence Training from System Perspective ACL 2023 SHARCS: Efficient Transformers Through Routing with Dynamic Width Sub-networks EMNLP 2023 ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer NeurIPS 2023 Simple Hardware-Efficient Long Convolutions for Sequence Modeling ICML 2023 Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer IJCAI 2023 Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention CVPR 2023 SlowBERT: Slow-down Attacks on Input-adaptive Multi-exit BERT ACL 2023 SMPConv: Self-Moving Point Representations for Continuous Convolution CVPR 2023 Sparse Universal Transformer EMNLP 2023 Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers CVPR 2023 Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation EMNLP 2023 Speculative Decoding with Big Little Decoder NeurIPS 2023 SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference ICML 2023 SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking ICCV 2023 StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller NeurIPS 2023 Strong and Efficient Baselines for Open Domain Conversational Question Answering EMNLP 2023 SUBP: Soft Uniform Block Pruning for 1×N Sparse CNNs Multithreading Acceleration NeurIPS 2023 TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction EMNLP 2023 Temporal Dynamic Quantization for Diffusion Models NeurIPS 2023 The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment EMNLP 2023 The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers ICLR 2023 Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning CVPR 2023 TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models EMNLP 2023 Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity EMNLP 2023