Zinan Lin

Senior Researcher

Publications

View by:

- Emergent Social Intelligence Risks in Generative Multi-Agent Systems
  
  Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yucheng Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V. Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang
  
  March 2026
  
  Publication
- CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
  
  Kaiyi Huang, Yukun Huang, Yu Li, Jianhong Bai, Xintao Wang, Zinan Lin, Xuefei Ning, Jiwen Yu, Pengfei Wan, Yu Wang, Xihui Liu
  
  CVPR 2026 | March 2026
  
  Publication
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  
  Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, Xihui Liu
  
  ICLR 2026 | February 2026
  
  Publication
- From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  Usenix Security 2026 | February 2026
  
  Publication Project
- NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2026 | February 2026
  
  Publication
- PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
  
  Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
  
  ICLR 2026 | February 2026
  
  Publication Project
- GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
  
  Kaiyi Huang, Yukun Huang, Xuefei Ning, Zinan Lin, Yu Wang, Xihui Liu
  
  AAAI 2026 | February 2026
  
  Publication
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
  
  Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song, Bo Li
  
  ICLR 2026 | February 2026
  
  Publication
- Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
  
  Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang
  
  NeurIPS 2025 | December 2025
  
  Publication
- Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
  
  Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin
  
  NeurIPS 2025 | December 2025
  
  Publication
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
  
  Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
  
  Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
  
  Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li
  
  October 2025
  
  Publication
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  CCS 2025 | July 2025
  
  Publication Project
- Scaling Textual Gradients via Sampling-Based Momentum
  
  Zixin Ding, Junyuan Hong, Jiachen T. Wang, Zinan Lin, Zhangyang Wang, Yuxin Chen
  
  ICML 2025 Workshop on Test-Time Adaptation | June 2025
  
  Publication
- Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
  
  Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
  
  February 2025
  
  Publication Project
- Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2025 | February 2025
  
  Publication Github
- Inferentially-Private Private Information
  
  Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
  
  WWW 2025 | February 2025
  
  Publication Project
- Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  ICLR 2025 | February 2025
  
  Publication
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  
  Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
  
  ICLR 2025 | February 2025
  
  Publication Project
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  
  Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
  
  ICLR 2025 | February 2025
  
  Publication
- RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  
  Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
  
  NeurIPS 2024 | October 2024
  
  Publication
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
  
  Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
  
  ECCV 2024 | July 2024
  
  Publication
- Statistic Maximal Leakage
  
  Shuaiqi Wang, Zinan Lin, Giulia Fanti
  
  IEEE International Symposium on Information Theory 2024 | July 2024
  
  Publication Project
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  June 2024
  
  DOI Publication Publication
- Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  
  Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
  
  NeurIPS 2024 | June 2024
  
  Publication
- FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
  
  Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
  
  CVPR 2024 | June 2024
  
  Publication
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
  
  Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
  
  Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
  
  ICLR 2024 | May 2024
  
  Publication Publication Publication
- Mixture-of-Linear-Experts for Long-term Time Series Forecasting
  
  Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
  
  AISTATS 2024 | May 2024
  
  Publication
- Efficiently Computing Similarities to Private Datasets
  
  Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
  
  ICLR 2024 | May 2024
  
  Publication Project
- Improving the Training of Rectified Flows
  
  Sangyun Lee, Zinan Lin, Giulia Fanti
  
  NeurIPS 2024 | May 2024
  
  Publication
- Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
  
  Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
  
  ICLR (TinyPapers) 2024 | May 2024
  
  Publication
- Selective Pre-training for Private Fine-tuning
  
  Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
  
  TMLR | May 2024
  
  Publication Publication Project
- Summary Statistic Privacy in Data Sharing
  
  Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
  
  IEEE Journal on Selected Areas in Information Theory | March 2024
  
  Publication Project
- Training Private and Efficient Language Models with Synthetic Data from LLMs
  
  Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
  
  NeurIPS 2023 SoLaR Workshop | December 2023
  
  Publication Project
- OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
  
  Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
  
  ICML 2023 | July 2023
  
  Publication
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
  
  Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
  
  NeurIPS 2023 | June 2023
  
  Outstanding Paper Award
  
  Publication Project

- Emergent Social Intelligence Risks in Generative Multi-Agent Systems
  
  Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yucheng Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V. Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang
  
  March 2026
  
  Publication
- CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
  
  Kaiyi Huang, Yukun Huang, Yu Li, Jianhong Bai, Xintao Wang, Zinan Lin, Xuefei Ning, Jiwen Yu, Pengfei Wan, Yu Wang, Xihui Liu
  
  CVPR 2026 | March 2026
  
  Publication
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  
  Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, Xihui Liu
  
  ICLR 2026 | February 2026
  
  Publication
- PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
  
  Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
  
  ICLR 2026 | February 2026
  
  Publication Project
- NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2026 | February 2026
  
  Publication
- GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
  
  Kaiyi Huang, Yukun Huang, Xuefei Ning, Zinan Lin, Yu Wang, Xihui Liu
  
  AAAI 2026 | February 2026
  
  Publication
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
  
  Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song, Bo Li
  
  ICLR 2026 | February 2026
  
  Publication
- Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
  
  Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang
  
  NeurIPS 2025 | December 2025
  
  Publication
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
  
  Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
  
  Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
  
  Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin
  
  NeurIPS 2025 | December 2025
  
  Publication
- BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
  
  Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li
  
  October 2025
  
  Publication
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  CCS 2025 | July 2025
  
  Publication Project
- Scaling Textual Gradients via Sampling-Based Momentum
  
  Zixin Ding, Junyuan Hong, Jiachen T. Wang, Zinan Lin, Zhangyang Wang, Yuxin Chen
  
  ICML 2025 Workshop on Test-Time Adaptation | June 2025
  
  Publication
- Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
  
  Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
  
  February 2025
  
  Publication Project
- Inferentially-Private Private Information
  
  Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
  
  WWW 2025 | February 2025
  
  Publication Project
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  
  Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
  
  ICLR 2025 | February 2025
  
  Publication
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  
  Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
  
  ICLR 2025 | February 2025
  
  Publication Project
- Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  ICLR 2025 | February 2025
  
  Publication
- Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2025 | February 2025
  
  Publication Github
- RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  
  Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
  
  NeurIPS 2024 | October 2024
  
  Publication
- MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
  
  Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
  
  ECCV 2024 | July 2024
  
  Publication
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- Statistic Maximal Leakage
  
  Shuaiqi Wang, Zinan Lin, Giulia Fanti
  
  IEEE International Symposium on Information Theory 2024 | July 2024
  
  Publication Project
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  June 2024
  
  DOI Publication Publication
- Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  
  Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
  
  NeurIPS 2024 | June 2024
  
  Publication
- FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
  
  Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
  
  CVPR 2024 | June 2024
  
  Publication
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
  
  Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
  
  Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
  
  ICLR 2024 | May 2024
  
  Publication Publication Publication
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Mixture-of-Linear-Experts for Long-term Time Series Forecasting
  
  Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
  
  AISTATS 2024 | May 2024
  
  Publication
- Improving the Training of Rectified Flows
  
  Sangyun Lee, Zinan Lin, Giulia Fanti
  
  NeurIPS 2024 | May 2024
  
  Publication
- Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
  
  Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
  
  ICLR (TinyPapers) 2024 | May 2024
  
  Publication
- Summary Statistic Privacy in Data Sharing
  
  Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
  
  IEEE Journal on Selected Areas in Information Theory | March 2024
  
  Publication Project
- Training Private and Efficient Language Models with Synthetic Data from LLMs
  
  Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
  
  NeurIPS 2023 SoLaR Workshop | December 2023
  
  Publication Project
- OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
  
  Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
  
  ICML 2023 | July 2023
  
  Publication
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
  
  Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
  
  NeurIPS 2023 | June 2023
  
  Outstanding Paper Award
  
  Publication Project
- CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
  
  Kaiyi Huang, Yukun Huang, Yu Li, Jianhong Bai, Xintao Wang, Zinan Lin, Xuefei Ning, Jiwen Yu, Pengfei Wan, Yu Wang, Xihui Liu
  
  CVPR 2026 | March 2026
  
  Publication
- From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  Usenix Security 2026 | February 2026
  
  Publication Project
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  
  Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, Xihui Liu
  
  ICLR 2026 | February 2026
  
  Publication
- GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
  
  Kaiyi Huang, Yukun Huang, Xuefei Ning, Zinan Lin, Yu Wang, Xihui Liu
  
  AAAI 2026 | February 2026
  
  Publication
- Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
  
  Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang
  
  NeurIPS 2025 | December 2025
  
  Publication
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
  
  Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
  
  Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin
  
  NeurIPS 2025 | December 2025
  
  Publication
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  
  Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
  
  ICLR 2025 | February 2025
  
  Publication
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  
  Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
  
  ICLR 2025 | February 2025
  
  Publication Project
- Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  ICLR 2025 | February 2025
  
  Publication
- Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2025 | February 2025
  
  Publication Github
- MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
  
  Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
  
  ECCV 2024 | July 2024
  
  Publication
- FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
  
  Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
  
  CVPR 2024 | June 2024
  
  Publication
- Improving the Training of Rectified Flows
  
  Sangyun Lee, Zinan Lin, Giulia Fanti
  
  NeurIPS 2024 | May 2024
  
  Publication
- Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
  
  Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
  
  ICLR (TinyPapers) 2024 | May 2024
  
  Publication
- OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
  
  Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
  
  ICML 2023 | July 2023
  
  Publication
- From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  Usenix Security 2026 | February 2026
  
  Publication Project
- PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
  
  Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
  
  ICLR 2026 | February 2026
  
  Publication Project
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
  
  Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song, Bo Li
  
  ICLR 2026 | February 2026
  
  Publication
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
  
  Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
  
  Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li
  
  October 2025
  
  Publication
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  CCS 2025 | July 2025
  
  Publication Project
- Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
  
  Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
  
  February 2025
  
  Publication Project
- Inferentially-Private Private Information
  
  Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
  
  WWW 2025 | February 2025
  
  Publication Project
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  
  Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
  
  ICLR 2025 | February 2025
  
  Publication Project
- RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  
  Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
  
  NeurIPS 2024 | October 2024
  
  Publication
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- Statistic Maximal Leakage
  
  Shuaiqi Wang, Zinan Lin, Giulia Fanti
  
  IEEE International Symposium on Information Theory 2024 | July 2024
  
  Publication Project
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
  
  Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Efficiently Computing Similarities to Private Datasets
  
  Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
  
  ICLR 2024 | May 2024
  
  Publication Project
- Selective Pre-training for Private Fine-tuning
  
  Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
  
  TMLR | May 2024
  
  Publication Publication Project
- Summary Statistic Privacy in Data Sharing
  
  Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
  
  IEEE Journal on Selected Areas in Information Theory | March 2024
  
  Publication Project
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
  
  Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
  
  NeurIPS 2023 | June 2023
  
  Outstanding Paper Award
  
  Publication Project
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  
  Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, Xihui Liu
  
  ICLR 2026 | February 2026
  
  Publication
- PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
  
  Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
  
  ICLR 2026 | February 2026
  
  Publication Project
- NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2026 | February 2026
  
  Publication
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
  
  Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
  
  ICLR 2024 | May 2024
  
  Publication Publication Publication
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Efficiently Computing Similarities to Private Datasets
  
  Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
  
  ICLR 2024 | May 2024
  
  Publication Project
- Selective Pre-training for Private Fine-tuning
  
  Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
  
  TMLR | May 2024
  
  Publication Publication Project
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project

- Emergent Social Intelligence Risks in Generative Multi-Agent Systems
  
  Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yucheng Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V. Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang
  
  March 2026
  
  Publication
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  June 2024
  
  DOI Publication Publication
- CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
  
  Kaiyi Huang, Yukun Huang, Yu Li, Jianhong Bai, Xintao Wang, Zinan Lin, Xuefei Ning, Jiwen Yu, Pengfei Wan, Yu Wang, Xihui Liu
  
  CVPR 2026 | March 2026
  
  Publication
- From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  Usenix Security 2026 | February 2026
  
  Publication Project
- FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  
  Kaiyi Huang, Yukun Huang, Xintao Wang, Zinan Lin, Xuefei Ning, Pengfei Wan, Di Zhang, Yu Wang, Xihui Liu
  
  ICLR 2026 | February 2026
  
  Publication
- PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text
  
  Tianyuan Zou, Zinan Lin, Sivakanth Gopi, Yang Liu, Ya-Qin Zhang, Robert Sim, Xin Deng, Sergey Yekhanin
  
  ICLR 2026 | February 2026
  
  Publication Project
- NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2026 | February 2026
  
  Publication
- GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
  
  Kaiyi Huang, Yukun Huang, Xuefei Ning, Zinan Lin, Yu Wang, Xihui Liu
  
  AAAI 2026 | February 2026
  
  Publication
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
  
  Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song, Bo Li
  
  ICLR 2026 | February 2026
  
  Publication
- Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
  
  Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang
  
  NeurIPS 2025 | December 2025
  
  Publication
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
  
  Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
  
  Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
  
  NeurIPS 2025 | December 2025
  
  Publication Project
- Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
  
  Zinan Lin, Enshu Liu, Xuefei Ning, Junyi Zhu, Wenyu Wang, Sergey Yekhanin
  
  NeurIPS 2025 | December 2025
  
  Publication
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
  
  Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang
  
  CCS 2025 | July 2025
  
  Publication Project
- Scaling Textual Gradients via Sampling-Based Momentum
  
  Zixin Ding, Junyuan Hong, Jiachen T. Wang, Zinan Lin, Zhangyang Wang, Yuxin Chen
  
  ICML 2025 Workshop on Test-Time Adaptation | June 2025
  
  Publication
- Inferentially-Private Private Information
  
  Shuaiqi Wang, Shuran Zheng, Zinan Lin, Giulia Fanti, Zhiwei Steven Wu
  
  WWW 2025 | February 2025
  
  Publication Project
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  
  Tianchen Zhao, Tongcheng Fang, Enshu Liu, Wan Rui, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning
  
  ICLR 2025 | February 2025
  
  Publication
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  
  Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, Zidi Xiong, Chenhui Zhang, Lingzhi Yuan, Yi Zeng, Peiyang Xu, Chengquan Guo, Andy Zhou, Jeffrey Ziwei Tan, Zhun Wang, Alexander Xiong, Xuandong Zhao, Yu Gai, Francesco Pinto, Yujin Potter, Zhen Xiang, Zinan Lin, Dan Hendrycks, Dawn Song, Bo Li
  
  ICLR 2025 | February 2025
  
  Publication Project
- Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
  
  Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
  
  ICLR 2025 | February 2025
  
  Publication
- Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
  
  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin
  
  ICLR 2025 | February 2025
  
  Publication Github
- RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  
  Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, Bo Li
  
  NeurIPS 2024 | October 2024
  
  Publication
- MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
  
  Tianchen Zhao, Xuefei Ning, Tongcheng Fang, Enshu Liu, Guyue Huang, Zinan Lin, Shengen Yan, Guohao Dai, Yu Wang
  
  ECCV 2024 | July 2024
  
  Publication
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
  
  ICML 2024 | July 2024
  
  Spotlight
  
  Publication Project
- Statistic Maximal Leakage
  
  Shuaiqi Wang, Zinan Lin, Giulia Fanti
  
  IEEE International Symposium on Information Theory 2024 | July 2024
  
  Publication Project
- Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  
  Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
  
  NeurIPS 2024 | June 2024
  
  Publication
- FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
  
  Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang
  
  CVPR 2024 | June 2024
  
  Publication
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
  
  Xinyu Tang, Richard Shin, Huseyin Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Robert Sim
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
  
  Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang
  
  ICLR 2024 | May 2024
  
  Publication Publication Publication
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
  
  Zinan Lin, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Harsha Nori, Sergey Yekhanin
  
  ICLR 2024 | May 2024
  
  Publication Publication Github Project
- Mixture-of-Linear-Experts for Long-term Time Series Forecasting
  
  Ronghao Ni, Zinan Lin, Shuaiqi Wang, Giulia Fanti
  
  AISTATS 2024 | May 2024
  
  Publication
- Improving the Training of Rectified Flows
  
  Sangyun Lee, Zinan Lin, Giulia Fanti
  
  NeurIPS 2024 | May 2024
  
  Publication
- Efficiently Computing Similarities to Private Datasets
  
  Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
  
  ICLR 2024 | May 2024
  
  Publication Project
- Rescaling Intermediate Features Makes Trained Consistency Models Perform Better
  
  Junyi Zhu, Zinan Lin, Enshu Liu, Xuefei Ning, Matthew B. Blaschko
  
  ICLR (TinyPapers) 2024 | May 2024
  
  Publication
- Training Private and Efficient Language Models with Synthetic Data from LLMs
  
  Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan (Jana) Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
  
  NeurIPS 2023 SoLaR Workshop | December 2023
  
  Publication Project
- OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
  
  Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang
  
  ICML 2023 | July 2023
  
  Publication
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
  
  Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
  
  NeurIPS 2023 | June 2023
  
  Outstanding Paper Award
  
  Publication Project
- BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
  
  Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li
  
  October 2025
  
  Publication
- Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models
  
  Zinan Lin, Tadas Baltrusaitis, Sergey Yekhanin
  
  February 2025
  
  Publication Project
- Selective Pre-training for Private Fine-tuning
  
  Da Yu, Sivakanth Gopi, Janardhan (Jana) Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
  
  TMLR | May 2024
  
  Publication Publication Project
- Summary Statistic Privacy in Data Sharing
  
  Zinan Lin, Shuaiqi Wang, Vyas Sekar, Giulia Fanti
  
  IEEE Journal on Selected Areas in Information Theory | March 2024
  
  Publication Project

Zinan Lin

Publications

Emergent Social Intelligence Risks in Generative Multi-Agent Systems

CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation

From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text

GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

Struct-Bench: A Benchmark for Differentially Private Structured Text Generation

Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis

Scaling Textual Gradients via Sampling-Based Momentum

Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Inferentially-Private Private Information

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

Statistic Maximal Leakage

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Mixture-of-Linear-Experts for Long-term Time Series Forecasting

Efficiently Computing Similarities to Private Datasets

Improving the Training of Rectified Flows

Rescaling Intermediate Features Makes Trained Consistency Models Perform Better

Selective Pre-training for Private Fine-tuning

Summary Statistic Privacy in Data Sharing

Training Private and Efficient Language Models with Synthetic Data from LLMs

OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Emergent Social Intelligence Risks in Generative Multi-Agent Systems

CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation

PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries

Struct-Bench: A Benchmark for Differentially Private Structured Text Generation

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis

Scaling Textual Gradients via Sampling-Based Momentum

Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Models

Inferentially-Private Private Information

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Statistic Maximal Leakage

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Mixture-of-Linear-Experts for Long-term Time Series Forecasting

Improving the Training of Rectified Flows

Rescaling Intermediate Features Makes Trained Consistency Models Perform Better

Summary Statistic Privacy in Data Sharing

Training Private and Efficient Language Models with Synthetic Data from LLMs

OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation