vix.ing · top · new · best · stats · spec

Sun, Xiaolin

  1. Enhancing LLM Safety via Constrained Direct Preference Optimization
    2024/03/04 by Liu, Zixuan, Sun, Xiaolin, Zheng, Zizhan · 7 citations
    #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
  2. Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
    2024/03/06 by Xiaolin Sun, Zizhan Zheng, Sun, Xiaolin +1 · 1 citation
    Computer Science · #Adversarial Robustness in Machine Learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM