2 papers
cs.LG2025
Efficient Low Rank Attention for Long-Context Inference in Large Language Models
Tenghui Li, Guoxu Zhou, Xuyang Zhao +2
As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Exis…
cs.AI2025
Scaling Capability in Token Space: An Analysis of Large Vision Language Model
Tenghui Li, Guoxu Zhou, Xuyang Zhao +1
Large language models have demonstrated predictable scaling behaviors with respect to model parameters and training data. This study investigates whether a similar scaling relation…