vector quantization
Vector quantization is a technique for approximating a large set of vectors by a smaller set of representative vectors (centroids). In AI, this is commonly employed in signal processing and neural network compression to reduce model size and improve efficiency.
- BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
- NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
- RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
- Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
- VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation