Co-occurring keywords · papers mentioning both
Papers
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
ACL 2026
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
NeurIPS 2022
Robust Tucker Tensor Decomposition for Effective Image Representation
ICCV 2013