Paper 'LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions' accepted to NeurIPS 2025 Main Conference
Invited as Area Chair for ICLR 2026
Paper 'Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms' accepted to ACL 2025 Main Conference
Selected as Outstanding Reviewer for ICML 2025
Paper 'Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models' accepted as oral presentation (top 1%) at ICML 2025
Two papers accepted to NAACL 2025 (one in Main Conference, one in Findings)
Team's PQN submission ranked among top three finalists in UC Berkeley's Prosocial Ranking Challenge
Paper 'Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts' published in PNAS Nexus
Paper 'Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias' accepted as oral talk at NAACL 2024
Paper 'What Data Benefits My Classifier? Enhancing Model Performance and Interpretability Through Influence-Based Data Selection' accepted as oral talk (top 1.2%) at ICLR 2024
Paper 'Towards Fair Video Summarization' published in Transactions on Machine Learning Research (TMLR)
Paper 'Auditing YouTube’s Recommendation System for Ideologically Congenial, Extreme, and Problematic Recommendations' published in PNAS
Paper 'Robust Fair Clustering: A Novel Fairness Attack and Defense Framework' accepted to ICLR 2023 Main Conference