Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks NIPS 2023

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models NIPS 2023

EffConv: Efficient Learning of Kernel Sizes for Convolution Layers of CNNs AAAI 2023

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation ICCV 2023

Overcoming Forgetting Catastrophe in Quantization-Aware Training ICCV 2023

QuIP: 2-Bit Quantization of Large Language Models With Guarantees NIPS 2023

LLM-Pruner: On the Structural Pruning of Large Language Models NIPS 2023

Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers NIPS 2023

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time NIPS 2023

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer NIPS 2023

Binarized Neural Machine Translation NIPS 2023

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NIPS 2023

ZipLM: Inference-Aware Structured Pruning of Language Models NIPS 2023

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning NIPS 2023

Bagging is an Optimal PAC Learner COLT 2023

Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective EACL 2023

Task-specific Compression for Multi-task Language Models using Attribution-based Pruning EACL 2023

Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression ICCV 2023

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NIPS 2023

Boost Transformer-based Language Models with GPU-Friendly Sparsity and Quantization ACL 2023

Quantifying lottery tickets under label noise: accuracy, calibration, and complexity UAI 2023

Math Word Problem Solving by Generating Linguistic Variants of Problem Statements ACL 2023

Client-Customized Adaptation for Parameter-Efficient Federated Learning ACL 2023

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting ACL 2023

Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment AAAI 2023