Kai Mei
3 papers in the PaperMetrix corpus
Papers by this author
-
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
2023 · arXiv (Cornell University)
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by retraining on downstream …
-
LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
2025 · arXiv (Cornell University)
We present AIOS 1.0, a novel platform designed to advance computer-use agent (CUA) capabilities through environmental contextualization. While existing approaches primarily focus on building more powerful agent frameworks or enhancing agent models, we identify a …
-
Semantic Scheduling for LLM Inference
2025 · arXiv (Cornell University)
Conventional operating system scheduling algorithms are largely content-ignorant, making decisions based on factors such as latency or fairness without considering the actual intents or semantics of processes. Consequently, these algorithms often do not prioritize tasks …