2 papers
cs.LG2026
MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
Kuan Wang, Chao Zhang
When a multimodal AI agent is asked to forget a fact, current memory systems usually delete the text entry and report success. We find that the fact can remain recoverable from ret…
cs.LG2024
LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy
Rongzhi Zhang, Kuang Wang, Liyuan Liu +4
The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed K…