efficient inference

GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints EMNLP 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023 HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition Interspeech 2023 I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference ICCV 2023 Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference ICLR 2023 Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation ACL 2023 MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition NeurIPS 2023 MixFormerV2: Efficient Fully Transformer Tracking NeurIPS 2023 Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference ACL 2023 MUX-PLMs: Pre-training Language Models with Data Multiplexing ACL 2023 Progressive Ensemble Distillation: Building Ensembles for Efficient Inference NeurIPS 2023 QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution NeurIPS 2023 Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution ICCV 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 SpeedDETR: Speed-aware Transformers for End-to-end Object Detection ICML 2023 Stop or Forward: Dynamic Layer Skipping for Efficient Action Recognition WACV 2023 TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting ICCV 2023 AdaViT: Adaptive Vision Transformers for Efficient Image Recognition CVPR 2022 AEGNN: Asynchronous Event-Based Graph Neural Networks CVPR 2022 A Theoretical View on Sparsely Activated Networks NeurIPS 2022 Block-Skim: Efficient Question Answering for Transformer AAAI 2022 ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences NeurIPS 2022 Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking ACL 2022