Publications
(*) denotes equal contribution.
Selected Publications (* indicates equal contribution or corresponding author):
- Diff-Instruct*: Towards Human-Preferred One-step Text-to-image Generative Models
Weijian Luo, Colin zhang, Debing Zhang, Zhengyang Geng
preprint, 2024 - Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
Weijian Luo
preprint, 2024 - One-Step Diffusion Distillation through Score Implicit Matching
Weijian Luo, Zemin Huang, Zhengyang Geng, J Zico Kolter, Guo-Jun Qi
Advances in Neural Information Processing Systems 37, 2024 - One-step Flow Matching Generators
Zemin Huang, Zhengyang Geng, Weijian Luo*, Guo-Jun Qi
preprint, 2024 - Diff-instruct: A Universal Approach for Transferring Knowledge from Pre-trained Diffusion Models
Weijian Luo, Tianyang Hu, Shifeng Zhang, Jiacheng Sun, Zhengguo Li, Zhihua Zhang
Advances in Neural Information Processing Systems 36, 45, 2023 - Denoising Fisher Training For Neural Implicit Samplers
Weijian Luo, Wei Deng
preprint, 2024 - Consistency Models Made Easy
Zhengyang Geng, Ashwini Pokle, Weijian Luo, Justin Lin, J Zico Kolter
arXiv preprint, arXiv:2406.14548, 2024 - Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images
Yifei Wang, Weimin Bai, Weijian Luo, Wenzheng Chen, He Sun
arXiv preprint, arXiv:2407.11162, 2024 - Variational Schrödinger Diffusion Models
Wei Deng*, Weijian Luo*, Yixin Tan*, Marin Biloš, Yu Chen, Yuriy Nevmyvaka, Ricky TQ Chen
Forty-first International Conference on Machine Learning. 2024 - SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
Shuchen Xue, Mingyang Yi, Weijian Luo, Shifeng Zhang, Jiacheng Sun, Zhengguo Li, Zhiming Ma
Advances in Neural Information Processing Systems 36, 11, 2023 - Entropy-based Training Methods for Scalable Neural Implicit Samplers
Weijian Luo, Boya Zhang, Zhihua Zhang
Advances in Neural Information Processing Systems 36, 1, 2023 - Enhancing Adversarial Robustness via Score-based Optimization
Boya Zhang, Weijian Luo, Zhihua Zhang
Advances in Neural Information Processing Systems 36, 51810-51829, 2023 - Training Energy-Based Models with Diffusion Contrastive Divergences
Weijian Luo, Hao Jiang, Tianyang Hu, Jiacheng Sun, Zhengguo Li, Zhihua Zhang
arXiv preprint, arXiv:2307.01668, 2023 - A Comprehensive Survey on Knowledge Distillation of Diffusion Models
Weijian Luo
arXiv preprint, arXiv:2304.04262, 2023 - A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization
Yasong Feng, Weijian Luo, Yiming Huang, Tianyu Wang
arXiv preprint, arXiv:2302.01539, 2023 - Data Prediction Denoising Models: The Pupil Outdoes the Master
Weijian Luo, Zhihua Zhang