【2026.05】论文 Balancing Understanding and Generation in Discrete Diffusion Models (XDLM) 被 ICML 2026 接收 (Spotlight, 2.2%)

【2026.01】论文 RebRL: Reinforcing Discrete Visual Diffusion Models with Rebalanced Timestep Credits 被 CVPR 2026 接收

   

2019-09--2023-06   中国科学院大学   工学博士
2015-08--2017-04   美国密歇根大学   理学硕士
2011-08--2015-07   清华大学   工学学士

2026-03--现在 中国科学院大学 长聘教轨助理教授

2023-08--2025-10 中国科学院大学 博士后 / 特别研究助理

2017-07--2019-07 中国科学院自动化研究所 工程师

   

（ 1 ） 一种基于多模态信息引导的遥感图像可控生成方法, 发明专利, 2025, 第 2 作者, 专利号: ZL 2024 1 1792206.2

（ 2 ） 人脸年龄变化图像对抗生成方法及系统, 发明专利, 2024, 第 2 作者, 专利号: ZL 2020 1 0441089.0

   

（1） CC-Diff++: Spatially Controllable Text-to-Image Synthesis for Remote Sensing with Enhanced Contextual Coherence, IEEE Transactions on Geoscience and Remote Sensing, 2025, 第 2 作者  通讯作者
（2） Expandable Residual Approximation for Knowledge Distillation, IEEE Transactions on Neural Networks and Learning Systems, 2025, 第 3 作者  通讯作者
（3） Revealing key details to see differences: A novel prototypical perspective for skeleton-based action recognition, Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, 第 2 作者  通讯作者
（4） Building vision models upon heat conduction, Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, 第 4 作者
（5） Cross-scenario unknown-aware face anti-spoofing with evidential semantic consistency learning, IEEE Transactions on Information Forensics and Security, 2024, 第 2 作者
（6） Vmamba: Visual state space model, Advances in neural information processing systems 37, 2024, 第 9 作者  通讯作者
（7） One-shot Face Reenactment with Dense Correspondence Estimation, Machine Intelligence Research, 2024, 第 1 作者  通讯作者
（8） r-FACE: Reference guided face component editing, Pattern Recognition, 2024, 第 3 作者
（9） Spatial transform decoupling for oriented object detection, Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 第 4 作者  通讯作者
（10） AnyFace++: A unified framework for free-style text-to-face synthesis and manipulation, IEEE transactions on pattern analysis and machine intelligence, 2024, 第 5 作者
（11） Gan-based facial attribute manipulation, IEEE transactions on pattern analysis and machine intelligence, 2023, 第 1 作者
（12） 3D-aware adversarial makeup generation for facial privacy protection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 第 5 作者
（13） Towards spatially disentangled manipulation of face images with pre-trained StyleGANs, IEEE Transactions on Circuits and Systems for Video Technology, 2022, 第 1 作者
（14） A3GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging, IEEE Transactions on Information Forensics and Security, 2021, 第 1 作者
（15） Age progression and regression with spatial attention modules, Proceedings of the AAAI conference on artificial intelligence, 2020, 第 2 作者
（16） Attribute-aware face aging with wavelet-based generative adversarial networks, Proceedings of the Computer Vision and Pattern Recognition Conference, 2019, 第 1 作者