Jie An

Jie An [安捷]

Hi! I am an Applied Scientist at Amazon AGI, where I work on image and video generation models as well as omni understanding and generation models. Previously, I was a Research Scientist at Meta Reality Labs, where I worked on 3D generation and world modeling. I received my Ph.D. in Computer Science from University of Rochester, advised by Prof. Jiebo Luo, where I received the ACM SIGMM Outstanding Ph.D. Thesis Award. Earlier, I earned my bachelor's and master's (with honor) degrees in Applied Mathematics from Peking University, advised by Prof. Jinwen Ma.

I was a research intern at Apple (Seattle, 2024–2025), working with Prof. Alexander Schwing. Before that, I interned at Microsoft Cloud & AI (Redmond, 2023–2024, now part of Microsoft AI) and Meta FAIR (New York City, 2022), hosted by Dr. Zhengyuan Yang and Prof. Harry Yang.

My research primarily focuses on visual content generation. I am particularly interested in foundational generative models, text-to-video generation, physics AI/world modeling, and artistic generation/style transfer. My research is driven by a long-term vision: from developing a fundamental understanding of generative models, to building increasingly capable foundation models, and ultimately advancing toward visual artificial general intelligence (VisualAGI).

Contact: pkuanjie [at] gmail [dot] com

Email / Google Scholar / Github / LinkedIn / Name Pronounce

News

[2025/10] Honored to receive the SIGMM Award for Outstanding PhD Thesis in Multimedia Computing, Communications, and Applications! Many thanks to my advisor and all collaborators during my PhD study.
[2025/09] Our paper On Inductive Biases That Enable Generalization of Diffusion Transformers is accepted by NeurIPS 2025.
[2025/06] Our paper Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training is accepted by ICCV 2025.
[2025/05] Excited to be selected for the CVPR 2025 Doctoral Consortium!
[2025/04] Our paper Video Understanding with Large Language Models: A Survey is accepted by TCSVT.
[2024/12] Our paper Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion is accepted to AAAI 2025.
[2024/06] Our paper Learning to Evaluate the Artness of AI-generated Images is accepted by TMM.
[2024/06] Our paper OpenLEAF: Open-Domain Interleaved Image-Text Generation and Evaluation is accepted to ACM MM 2024 BNI track.
[2024/05] Our paper Bring Metric Functions into Diffusion Models is accepted to IJCAI 2024.
[2024/03] We will organize the first workshop on Visual-Language Alignment in Text-Guided Multi-Modal Generation (T2MM) in conjunction with #ICME2024. Welcome to submit your workshop papers!
[2024/03] I will join Apple as a research intern this summer.
[2023/02] I will join Microsoft Cloud & AI as a research intern.

Thesis

Text-to-Video Generation Based on Diffusion Model by Jie An, advised by Jiebo Luo, University of Rochester

Publications & Preprints

	On Inductive Biases That Enable Generalization of Diffusion Transformers Jie An, De Wang, Pengsheng Guo, Jiebo Luo, Alexander Schwing NeurIPS 2025 \| Project Page \| Code \| Featured at Apple MLR \| BibTex We find that the generalization ability of DiTs is linked to an attention locality bias: despite access to global tokens, DiTs naturally develop locality patterns in certain attention layers.
	Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training Zhenghong Zhou^, Jie An^, Jiebo Luo ICCV 2025 \| Project Page \| BibTex We incorporate a 3D point cloud model based on MonST3R into a video diffusion model, which enables arbitrary camera trajectory control in video generation, without training.
	Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion Jingyuan Chen, Fuchen Long, Jie An, Zhaofan Qiu, Ting Yao, Jiebo Luo, Tao Mei AAAI 2025 \| BibTex We introduce a FIFO-style training-free approach that can enable a video diffusion model to generate infinite long videos in sampling stage.
	Video Understanding with Large Language Models: A Survey Y. Tang, J. Bi, S. Xu, L. Song, S. Liang, T. Wang, D. Zhang, Jie An and others TCSVT \| GitHub \| BibTex We present a comprehensive survey about using LLMs/LMMs for video understanding.
	OpenLEAF: Open-Domain Interleaved Image-Text Generation and Evaluation Jie An^, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Lijuan Wang, Jiebo Luo ACM MM (BNI Track)* 2024 \| BibTex We introduce a benchmark dataset, an evaluation pipeline, and a set of baseline models for interleaved image-text generation task.
	Bring Metric Functions into Diffusion Models Jie An, Zhengyuan Yang, Jianfeng Wang, Linjie Li, Zicheng Liu, Lijuan Wang, Jiebo Luo IJCAI 2024 \| BibTex We study how to ultilize LPIPS loss in diffusion model training to improve the image generation quality.
	Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation Jie An^, Songyang Zhang^, Harry Yang, Sonal Gupta, Jia-Bin Huang, Jiebo Luo and Xi Yin Arxiv 2023 \| Project Page \| BibTex We propose an efficient text-to-video generation method based on latent diffusion model and temporal shift.
	Learning to Evaluate the Artness of AI-generated Images Junyu Chen, Jie An, Hanjia Lyu, Jiebo Luo TMM 2024 \| BibTex We propose a rank-based method to evaluate the artness level of AI-generated artworks.
	Holistic Visual-Textual Sentiment Analysis with Prior Models Junyu Chen, Jie An, Hanjia Lyu and Jiebo Luo MIPR 2024 \| BibTex We ultilize multi-modal expert features to assist the sentiment analysis task.
	QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity Siyu Huang^, Jie An^, Donglai Wei, Jiebo Luo and Hanspeter Pfister CVPR 2023 \| Code \| BibTex QuantArt allows the style transfer model take the reference from the whole artistic picture dataset, leading to improved visual fidelity.
	Make-A-Video: Text-to-video Generation Without Text-video Data. Uriel Singer^, Adam Polyak^, Thomas Hayes^, Xi Yin^, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta and Yaniv Taigman ICLR 2023 \| BibTex We propose a text-to-video generation method based on diffusion model.
	Domain-Scalable Unpaired Image Translation via Latent Space Anchoring Siyu Huang^, Jie An^ , Donglai Wei, Zudi Lin, Jiebo Luo and Hanspeter Pfister TPAMI \| Code \| BibTex We propose a GAN-based multi-domain image translation method that can extend to any unseen domain without the need to train the core backbone.
	Is Bigger Always Better? An Empirical Study on Efficient Architectures for Style Transfer and Beyond Jie An, Tao Li, Haozhi Huang, Jinwen Ma and Jiebo Luo WACV 2023 \| BibTex We study whether the big VGG19 architecture is the best backbone for image style transfer and explore its efficient alternatives.
	Facial Attribute Transformers for Precise and Robust Makeup Transfer Zhaoyi Wan, Haoran Chen, Jie An, Wentao Jiang, Cong Yao and Jiebo Luo WACV 2022 \| BibTex We propose an new transformer-based method for makeup transfer and removal.
	ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows Jie An^, Siyu Huang^, Yibing Song, Dejing Dou, Wei Liu and Jiebo Luo CVPR 2021 \| Code \| BibTex We propose an unbiased style transfer method based on neural flows to address the content leak issue in style transfer.
	Global Image Sentiment Transfer Jie An, Tianlang Chen, Songyang Zhang and Jiebo Luo ICPR 2020 \| BibTex We propose a method to transfer the global sentiment of images.
	Ultrafast photorealistic style transfer via neural architecture search Jie An^, Haoyi Xiong^, kun Huan and Jiebo Luo AAAI 2020 (Oral Presentation) \| Code \| BibTex We propose a neural architecture search framework to discover efficient architectures for photo-realistic style transfer.
	Pyramid attention network for semantic segmentation Hanchao Li, Pengfei Xiong, Jie An, and Lingxue Wang BMVC 2018 \| BibTex We propose a new network architecture for semantic image segmentation.

Invited Talks

[2026/01] "On Diffusion-Based Visual Content Generation: From Base Model to Methodology and Evaluation" @ Apple, MLR
[2025/03] "On Diffusion-Based Visual Content Generation: From Base Model to Methodology and Evaluation" @ Meta, Reality Labs
[2025/02] "On Diffusion-Based Visual Content Generation: From Base Model to Methodology and Evaluation" @ Clemson University, Computer Science

Work & Internships

	Amazon AGI [2025/07 - Current] Applied Scientist Video Generation Architecture, Parallelism, and Pre-training. Omni Understanding and Generation Models. Reinforcement Learning for Image Generation.
	Meta Reality Lab [2025/05 - 2025/07] AI Research Scientist 3D Generation and World Modeling.
	Apple [2024/05 - 2025/04] Research Intern Advisors: Alexander Schwing, Andy (De) Wang, Pengsheng Guo Project: Diffusion Model Analysis
	Microsoft Cloud & AI [2023/02 - 2024/4] Research Intern Advisors: Zhengyuan Yang, Jianfeng Wang, Linjie Li, Lijuan Wang, Zicheng Liu Project: Diffusion Model and Visual-Language Generation.
	Meta FAIR [2022/05 - 2022/12] Research Intern Advisors: Harry Yang, Xi Yin, Sonal Gupta Project: Text-to-Video Generation.

Collaborators

I am fortunate to collaborate with, and more importantly learn from, the following talented collaborators:

[2025] Zhenghong Zhou, Ph.D., University of Rochester.
[2025] Jingyuan (Patrick) Chen, B.S., University of Rochester, now M.S. at University of Pennsylvania.
[2024] Yunlong Tang, Ph.D., University of Rochester.
[2023-2024] Junyu Chen, M.S., University of Rochester, now Ph.D. at University of Rochester.
[2023] Alexander Martin, B.S., University of Rochester, now Ph.D. at Johns Hopkins University.
[2023] Songyang Zhang, Ph.D., University of Rochester, now researcher at Utopic Studio.
[2023] Tao Li, Ph.D., Peking University.
[2022] Zhaoyi Wan, researcher, Megvii, now researcher at JQ Investments.
[2021-2023] Siyu Huang, researcher, Baidu, now professor at Clemson University.
[2018] Hanchao Li, intern, Megvii, now engineer at Microsoft (Redmond).

Academic Services

Conference Reviewer

CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, WACV, EMNLP, ACL, MM, AAAI, ICASSP, ICME

Journal Reviewer

TPAMI, TMM, TNNLS, APSIPA

Honors & Awards

[2025/10] SIGMM Award for Outstanding PhD Thesis
[2025/06] Selection for Doctoral Consortium, CVPR 2025
[2019/06] Outstanding Graduate of Beijing
[2018/10] Graduate student scholarship, Peking University
[2016/10] Graduate student scholarship, Peking University
[2015/06] “Guang Hua” scholarship, Peking University

Template