Efficient Computing

TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models EMNLP 2023 Token Merging: Your ViT But Faster ICLR 2023 Too Large; Data Reduction for Vision-Language Pre-Training ICCV 2023 TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images CVPR 2023 TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition CVPR 2023 torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP EMNLP 2023 Toward Accurate Post-Training Quantization for Image Super Resolution CVPR 2023 Toward Edge-Efficient Dense Predictions With Synergistic Multi-Task Neural Architecture Search WACV 2023 Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning ACL 2023 Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity NeurIPS 2023 Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model EMNLP 2023 Towards Better Dynamic Graph Learning: New Architecture and Unified Library NeurIPS 2023 Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask? NeurIPS 2023 Towards Efficient and Accurate Winograd Convolution via Full Quantization NeurIPS 2023 Towards Efficient Dialogue Processing in the Emergency Response Domain ACL 2023 Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors CVPR 2023 Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation EACL 2023 Towards Fully Quantized Neural Networks For Speech Enhancement Interspeech 2023 Towards Higher Ranks via Adversarial Weight Pruning NeurIPS 2023 Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting CVPR 2023 Towards Inference Efficient Deep Ensemble Learning AAAI 2023 Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models IJCAI 2023 Towards Optimal Caching and Model Selection for Large Model Inference NeurIPS 2023 Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint ICCV 2023 Towards Real-Time Segmentation on the Edge AAAI 2023