← Core AI
Artificial Intelligence › Core AI ›

Efficient Computing

596 directly classified papers

Papers per year

Papers

MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer EMNLP 2023
Learning To Zoom and Unzoom CVPR 2023
RWKV: Reinventing RNNs for the Transformer Era EMNLP 2023
Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification EMNLP 2023
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning EMNLP 2023
NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks NIPS 2023
Efficient Encoders for Streaming Sequence Tagging EACL 2023
A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates ICML 2023
A Length-Extrapolatable Transformer ACL 2023
Revisiting Token Dropping Strategy in Efficient BERT Pretraining ACL 2023
CQNV: A Combination of Coarsely Quantized Bitstream and Neural Vocoder for Low Rate Speech Coding INTERSPEECH 2023
HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023
Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023
Oscillation-free Quantization for Low-bit Vision Transformers ICML 2023
Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics ICML 2023
ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy WACV 2023
Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules EMNLP 2023
TIPS: Topologically Important Path Sampling for Anytime Neural Networks ICML 2023
Energy-Efficient Adaptive 3D Sensing CVPR 2023
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer AAAI 2023
Fast Fluid Simulation via Dynamic Multi-Scale Gridding AAAI 2023
Reducing ANN-SNN Conversion Error through Residual Membrane Potential AAAI 2023
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023
Motion Information Propagation for Neural Video Compression CVPR 2023
Dynamic Transformers Provide a False Sense of Efficiency ACL 2023