* equal contribution. † corresponding author.

Preprints

• SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation
  Hongjian Liu, Qingsong Xie†, Zhijie Deng†, Chen Chen, Shixiang Tang, Fueyang Fu, Zheng-jun Zha, and Haonan Lu
• Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks
  Hongcheng Gao, Hao Zhang, Yinpeng Dong†, and Zhijie Deng†
• Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
  Zhijie Deng†, Hongcheng Gao, Yibo Miao, and Hao Zhang†
• Neural Eigenfunctions Are Structured Representation Learners
  Zhijie Deng*, Jiaxin Shi*, Hao Zhang, Peng Cui, Cewu Lu, and Jun Zhu
  
• Accurate and Reliable Forecasting using Stochastic Differential Equations
  Peng Cui, Zhijie Deng, Wenbo Hu, and Jun Zhu
  
• Deep Ensemble as a Gaussian Process Approximate Posterior
  Zhijie Deng, Feng Zhou, Jianfei Chen, Guoqiang Wu, and Jun Zhu
  

Publications

2024

• SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
  Kang You, Zekai Xu, Chen Nie, Zhijie Deng, Qinghai Guo, Xiang Wang, Zhezhi He
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  
• CLLMs: Consistency Large Language Models
  Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng†, and Hao Zhang
  MLSys Young Professionals Symposium, Santa Clara, USA, 2024
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  
• Improved Operator Learning by Orthogonal Attention
  Zipeng Xiao, Zhongkai Hao, Bokai Lin, Zhijie Deng†, and Hang Su†
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  
• Online Speculative Decoding
  Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Ion Stoica, Zhijie Deng†, Alvin Cheung, and Hao Zhang†
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  
• LOVECon: Text-driven Training-Free Long Video Editing with ControlNet
  Zhenyi Liao and Zhijie Deng†
  AI for Content Creation Workshop @ CVPR 2024, Seattle, USA, 2024
  
• Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
  Yibo Miao, Yu Lei, Feng Zhou†, and Zhijie Deng†
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024
• BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
  Siqi Kou, Lei Gan, Dequan Wang, Chongxuan Li†, and Zhijie Deng†
  International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
  

2023

• Towards Accelerated Model Training via Bayesian Data Selection
  Zhijie Deng*, Peng Cui*, and Jun Zhu
  Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
  
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
  Peng Cui, Dan Zhang, Zhijie Deng†, Yinpeng Dong, and Jun Zhu†
  Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
  
• On Calibrating Diffusion Probabilistic Models
  Tianyu Pang†, Cheng Lu, Chao Du, Min Lin, Shuicheng Yan, and Zhijie Deng†
  Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023
  
• Heterogeneous Multi-Task Gaussian Cox Processes
  Feng Zhou, Quyu Kong, Zhijie Deng, Fengxiang He, Peng Cui, and Jun Zhu
  Machine Learning, 2023
  [ArXiv]
• Batch Virtual Adversarial Training for Graph Convolutional Networks
  Zhijie Deng, Yinpeng Dong, and Jun Zhu
  AI Open, 2023
  ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Representation, Long Beach, USA, 2019
  [ArXiv] [code]
• Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
  Zhijie Deng and Yucen Luo
  International Conference on Computer Vision (ICCV), Paris, France, 2023
  [ArXiv] [code]

2022

• BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning
  Zhijie Deng and Jun Zhu
  Asian Conference on Machine Learning (ACML), Hyderabad, India, 2022
  [ArXiv] [code]
• Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
  Zhijie Deng, Feng Zhou, and Jun Zhu
  Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2022 (Spotlight)
  [ArXiv] [code] [slides]
• Confidence-based Reliable Learning under Dual Noises
  Peng Cui, Yang Yue, Zhijie Deng†, and Jun Zhu†
  Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2022
  
• Efficient Inference for Dynamic Flexible Interactions of Neural Populations
  Feng Zhou, Quyu Kong, Zhijie Deng, Jichao Kan, Yixuan Zhang, Cheng Feng, and Jun Zhu
  Journal of Machine Learning Research (JMLR), 2022
  
• NeuralEF: Deconstructing Kernels by Deep Neural Networks
  Zhijie Deng, Jiaxin Shi, and Jun Zhu
  International Conference on Machine Learning (ICML), Baltimore, USA, 2022
  [ArXiv] [code] [slides]
• Exploring Memorization in Adversarial Training
  Yinpeng Dong, Ke Xu, Xiao Yang, Tianyu Pang, Zhijie Deng, Hang Su, and Jun Zhu
  International Conference on Learning Representations (ICLR), Online, 2022
  

2021

• Black-box Detection of Backdoor Attacks with Limited Information and Data
  Yinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang, Zihao Xiao, Hang Su, and Jun Zhu
  International Conference on Computer Vision (ICCV), VIRTUAL, 2021
  
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
  Zhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, and Jun Zhu
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), VIRTUAL, 2021 (Valse 2021 Spotlight, 2021.10)
  [code] [slides]
• Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure
  Zhijie Deng, Yucen Luo, and Jun Zhu
  2nd Workshop on Neural Architecture Search at ICLR 2021
  

2020

• Adversarial Distributional Training for Robust Deep Learning
  Yinpeng Dong*, Zhijie Deng*, Tianyu Pang, Hang Su, and Jun Zhu
  Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
  [ArXiv] [code] [appendix]
• Understanding and Exploring the Network with Stochastic Architectures
  Zhijie Deng, Yinpeng Dong, Shifeng Zhang, and Jun Zhu
  Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
  [code] [slides] [appendix]
• AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning
  Hao Zhang*, Yuan Li*, Zhijie Deng, Xiaodan Liang, Lawrence Carin, Eric P. Xing
  Advances in Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2020
  [code] [appendix]

Before 2020

• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
  Zhijie Deng, Yucen Luo, and Jun Zhu
  International Conference on Computer Vision (ICCV), Seoul, Korea, 2019
  [ArXiv] [code] [appendix]
• Cavs: An Efficient Runtime System for Dynamic Neural Networks
  Shizhen Xu, Hao Zhang, Graham Neubig, Wei Dai, Jin Kyu Kim, Zhijie Deng, Qirong Ho, Guangwen Yang, and Eric P Xing
  USENIX Annual Technical Conference (USENIX ATC), Boston, USA, 2018
  
• Structured Generative Adversarial Networks
  Zhijie Deng*, Hao Zhang*, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu, and Eric P Xing
  Advances in Neural Information Processing Systems (NeurIPS), Long Beach, USA, 2017 (NVAIL Pioneering Research Award, 2017.12)
  [ArXiv] [code]

© 2024.01 Zhijie Deng