- 暂无内容
- 暂无内容
- 暂无内容
- Just-in-time: Training-free spatial acceleration for diffusion Transformers.IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2026
- Outlier-robust diffusion solvers for inverse problem.to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2026
- Diffusion model based signal recovery under 1-bit quantization.AAAI Conference on Artificial Intelligence (AAAI).2026
- Learnable sampler distillation for discrete diffusion models.Conference on Neural Information Processing Systems (NeurIPS spotlight presentation).2025
- Integrating intermediate layer optimization and projected gradient descent for solving inverse problems with diffusion models.International Conference on Machine Learning (ICML).2025
- Learning single index models with diffusion priors.International Conference on Machine Learning (ICML).2025
- AlgoFormer: An efficient Transformer framework with algorithmic structures.Transactions on Machine Learning Research.2025
- Solving quadratic systems with full-rank matrices using sparse or generative priors.IEEE Transactions on Signal Processing.2025
- Generalized eigenvalue problems with generative priors.Conference on Neural Information Processing Systems (NeurIPS).2024
- Uniform recovery guarantees for quantized corrupted sensing with structured or generative priors.SIAM Journal on Imaging Sciences.2024
- The surprising effectiveness of skip-tuning in diffusion sampling.International Conference on Machine Learning (ICML).2024
- Accelerating diffusion sampling with optimized time steps.IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2024
- Efficient algorithms for non-Gaussian single index models with generative priors.AAAI Conference on Artificial Intelligence (AAAI).2024
- A unified framework for uniform signal recovery in nonlinear generative compressed sensing.Conference on Neural Information Processing Systems (NeurIPS).2023
- DiffFit: Unlocking transferability of large diffusion models via simple parameter-efficient fine-tuning.International Conference on Computer Vision (ICCV oral presentation).2023
-
聚焦机器学习与人工智能领域，主要从事扩散模型、高维逆问题、大语言模型等相关的理论分析与应用研究。