← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP 2021
Block Pruning For Faster Transformers EMNLP 2021
Layer-wise Model Pruning based on Mutual Information EMNLP 2021
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade EMNLP 2021
KSM: Fast Multiple Task Adaption via Kernel-Wise Soft Mask Learning CVPR 2021
QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks CVPR 2021
Dynamic Slimmable Network CVPR 2021
Bi-GCN: Binary Graph Convolutional Network CVPR 2021
Binary Neural Network for Speaker Verification INTERSPEECH 2021
Amortized Neural Networks for Low-Latency Speech Recognition INTERSPEECH 2021
CSECU-DSG at SemEval-2021 Task 1: Fusion of Transformer Models for Lexical Complexity Prediction ACL 2021
BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation EMNLP 2021
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression EMNLP 2021
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution NIPS 2021
Demystifying and Generalizing BinaryConnect NIPS 2021
Class-Disentanglement and Applications in Adversarial Detection and Defense NIPS 2021
Scaling Up Exact Neural Network Compression by ReLU Stability NIPS 2021
Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme NIPS 2021
Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory NIPS 2021
A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness NIPS 2021
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices NIPS 2021
Pruning Randomly Initialized Neural Networks with Iterative Randomization NIPS 2021
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition NIPS 2021
AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks NIPS 2021