← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization CVPR 2022
It's All in the Teacher: Zero-Shot Quantization Brought Closer to the Teacher CVPR 2022
Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network CVPR 2022
Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization IJCAI 2022
Deeply Tensor Compressed Transformers for End-to-End Object Detection AAAI 2022
Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes IJCAI 2022
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning NIPS 2022
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets ICML 2022
Model Compression Using Optimal Transport WACV 2022
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022
Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks ICML 2022
Scaling Language Model Size in Cross-Device Federated Learning ACL 2022
Robust Binary Models by Pruning Randomly-initialized Networks NIPS 2022
Towards Efficient Post-training Quantization of Pre-trained Language Models NIPS 2022
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models NIPS 2022
AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks NAACL 2022
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks COLING 2022
F-coref: Fast, Accurate and Easy to Use Coreference Resolution AACL 2022
Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERT NAACL 2022
When the Student Becomes the Master: Learning Better and Smaller Monolingual Models from mBERT COLING 2022
Equal Bits: Enforcing Equally Distributed Binary Network Weights AAAI 2022
Supervised Compression for Resource-Constrained Edge Computing Systems WACV 2022
Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLU NAACL 2022
Pruning Adatperfusion with Lottery Ticket Hypothesis NAACL 2022
C3PO: A Lightweight Copying Mechanism for Translating Pseudocode to Code AACL 2022