2 papers
cs.LG2026
Efficient Generative Modeling with Unitary Matrix Product States Using Riemannian Optimization
Haotong Duan, Zhongming Chen, Ngai Wong
Tensor networks, which are originally developed for characterizing complex quantum many-body systems, have recently emerged as a powerful framework for capturing high-dimensional p…
cs.LG2025
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models
Jiajun Zhou, Yifan Yang, Kai Zhen +6
Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-…