2 papers
cs.LG2026
FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management
Nazmul Takbir, Hamidreza Alikhani, Nikil Dutt +1
Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior w…
cs.CL2024
ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination
Navid Ayoobi, Lily Knab, Wen Cheng +5
While large language models (LLMs) exhibit significant utility across various domains, they simultaneously are susceptible to exploitation for unethical purposes, including academi…