← Optimization & Theory
Machine Learning › Optimization & Theory ›

Model Compression

10 directly classified papers

Papers per year

Papers

Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? CVPR 2025
Hypernetworks for Perspectivist Adaptation EMNLP 2025
Talking Head Anime 4: Distillation for Real-Time Performance WACV 2025
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation ACL 2025
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts ACL 2025
TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models ACL 2025
JointSQ: Joint Sparsification-Quantization for Distributed Learning CVPR 2024
SAFE: Machine Unlearning With Shard Graphs ICCV 2023
Quantized Training of Gradient Boosting Decision Trees NIPS 2022
WSNet: Compact and Efficient Networks Through Weight Sampling ICML 2018