Feb 2025: Paper 'Training-Free Bayesianization for Low-Rank Adapters of Large Language Models' accepted to ICLR 2025 “QUESTION” Workshop.
Oct 2024: Paper 'BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models' accepted to NeurIPS 2024.
May 2023: First paper on certified robustness in NLP, 'Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions', accepted to Findings of ACL 2023.
Apr 2024: Contributed to a survey on Continual Learning of LLMs.
2025: Co-authored 'Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay', accepted to NeurIPS 2025.