5 papers
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
Kanghua Mo, Li Hu, Yucheng Long +1
Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradi…
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
Yaxin Xiao, Qingqing Ye, Li Hu +5
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to…
Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline
Lifan Hu
Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The l…
dots.llm1 Technical Report
Bi Huo, Bin Tu, Cheng Qin +24
Mixture of Experts (MoE) models have emerged as a promising paradigm for scaling language models efficiently by activating only a subset of parameters for each input token. In this…
Learning Lie Group Generators from Trajectories
Lifan Hu
This work investigates the inverse problem of generator recovery in matrix Lie groups from discretized trajectories. Let be a real matrix Lie group and $\mathfrak{g} = \text{Li…