publications
Please see Google Scholar for more recent works and arXiv papers.
2025
-
Preprint Restoration Score Distillation: From Corrupted Diffusion Pretraining to One-Step High-Quality Generation2025 -
Preprint Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation2025 -
Preprint Learning Difference-of-Convex Regularizers for Inverse Problems: A Flexible Framework with Theoretical Guarantees2025 -
AISTATS Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayesian TheoryIn International Conference on Artificial Intelligence and Statistics 2025
Book Chapter 
Preprint 2024
-
arXiv -
arXiv Latent Energy-Based Odyssey: Black-Box Optimization via Expanded Exploration in the Energy-Based Latent Space2024 -
NeurIPS Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory MatchingIn Neural Information Processing Systems 2024 -
ECCV Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion ModelsIn European Conference on Computer Vision 2024 -
ECCV Skews in the Phenomenon Space Hinder Generalization in Text-to-Image GenerationIn European Conference on Computer Vision 2024 -
SynData4CV Object-Conditioned Energy-Based Model for Attention Map Alignment in Text-to-Image Diffusion ModelsIn Synthetic Data for Computer Vision Workshop @ CVPR 2024
2023
-
ICASSP Transductive Matrix Completion with Calibration for Multi-Task LearningIn International Conference on Acoustics, Speech, and Signal Processing 2023