3 papers
cs.CR2026
SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri
Haocheng Xia, Yongjoo Park
LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-b…
cs.CL2026
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
Haocheng Xia, Mihir Pamnani, Hanxi Fang +2
Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens. Its importance becomes even greater in long-context…
cs.RO2026
HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments
Shuijing Liu, Haochen Xia, Fatemeh Cheraghi Pouria +5
We study the problem of robot navigation in dense and interactive crowds with static constraints such as corridors and furniture. Previous methods fail to consider all types of spa…