2025: Three papers accepted to NeurIPS 2025 on generalization of label noise gradient descent, generalization bounds of gradient flow, and MLLM annotation
2025: Four papers accepted to ICML 2025 and one to COLT 2025
2025: Four papers accepted to ICLR 2025 on diffusion model feature learning, Transformer optimization, DMD for GNN, and GNN hyperparameter tuning with diffusion models
2024: One paper on protein sequence generation accepted to IEEE BIBM 2024
2024: Four papers accepted to NeurIPS 2024 on Riemannian bilevel optimization, parameter and memory efficient pretraining, theoretical comparisons between single and multi-modal contrastive learning, and in-context learning with multi-concept word semantics
2024: Organizing a workshop titled 'Deep Generative Models in Machine Learning: Theory, Principle and Efficacy' at ICLR 2025
2024: Created a GitHub repository on Riemannian optimization compiling key papers, books, and resources