Efficient Computing

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks NeurIPS 2023 Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models ACL 2023 On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023 Oscillation-free Quantization for Low-bit Vision Transformers ICML 2023 Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023 Reducing ANN-SNN Conversion Error through Residual Membrane Potential AAAI 2023 Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline NeurIPS 2023 Revisiting Token Dropping Strategy in Efficient BERT Pretraining ACL 2023 Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch ICML 2023 ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy WACV 2023 Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture IJCAI 2023 RWKV: Reinventing RNNs for the Transformer Era EMNLP 2023 SHARCS: Efficient Transformers Through Routing with Dynamic Width Sub-networks EMNLP 2023 SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models ICML 2023 Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen Estimator IJCAI 2023 SpeedyZero: Mastering Atari with Limited Data and Time ICLR 2023 SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking ICCV 2023 Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning EMNLP 2023 The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment EMNLP 2023 TIPS: Topologically Important Path Sampling for Anytime Neural Networks ICML 2023 Toeplitz Neural Network for Sequence Modeling ICLR 2023 Treepiece: Faster Semantic Parsing via Tree Tokenization EMNLP 2023 Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules EMNLP 2023 Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic ICLR 2023 You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023