← authors · overview

• Rethinking Machine Unlearning For Large Language Models
  2024 · 253 citations
• Practical Detection Of Trojan Neural Networks: Data-limited And Data-free Cases
  2020 · 94 citations
• PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
  2024 · 1 citations
• WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
  2024 · 1 citations
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
  2024 · 1 citations
• Context-Aware RL for Agentic and Multimodal LLMs
  2026
• Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
  2026
• UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
  2026
• Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
  2025
• Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
  2025
• Generating Adversarial Computer Programs Using Optimized Obfuscations
  2021
• TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
  2020
• On sparse identification of complex dynamical systems: A study on discovering influential reactions in chemical reaction networks
  2020