I am now a research engineer at MM of Meituan Inc. I was a M.Sc. student at University of Chinese Academy of Sciences (UCAS) (Ranking NO.69 in US.News), and did my research at Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS). I worked in the CUHK@MMLAB in Shenzhen named SIAT-MMLAB, which was founded and directed by Professor Xiaoou Tang, Yu Qiao, and Chao Dong. I received my B.E. degree from Nanjing University (NJU) (Ranking NO.65 in THE, NO.98 in US.News, and NO.121 in QS), Nanjing, China in 2021. My undergraduate and graduate universities are both ranked among the top 100 universities in the world.

My research interests include deep learning, computer vision, and image enhancement. Recently, I have focused on AIGC, low-level tasks, image editing, image generation, video generation, and 3D generation. I have explored AIGC methods such as Diffusion Models for a very long time (from 2022.7 to now). I work on designing new kinds of Diffusion Models and their applications for various fields, aiming to promote the efficiency and flexibility of Diffusion Models used in the real world. I am now an IEEE member, ACM member, IEEE SPS member and CCF member. I have been invited by the PCs and served as a reviewer many times for top conferences or journals such as NeurIPS (2024), ICLR (2025), CVPR (2025), ICCV (2023), ECCV (2024), ACM MM (2024), WACV (2025), ICME (2024), AISTATS (2025), ICMR (2024), Neural Networks (many times), and MMM (2023).

Google scholar citations

image

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข I am looking for more close friends in research. If you would like to discuss AIGC or diffusion models with me, please feel free to contact me. ๐Ÿ˜Š

My first mentor is Shifeng Chen and my second mentor is Chao Dong. Our Lab is directed by Professor Xiaoou Tang and Yu Qiao. I also work with my coauthors such as Donghao Zhou, Chaoqi Chen, Lin Ma, Wei Xiong, He Zhang, Liangliang Cao, Pheng Ann Heng, Zequn Jie, Yizhou Yu, and Jianzhuang Liu. Xiaoou Tang, Chao Dong, Yu Qiao, Liangliang Cao, Pheng Ann Heng, Yizhou Yu, and Jianzhuang Liu are Worldโ€™s Top 2% Scientists of Lifetime Impact Ranking.

๐Ÿ”ฅ News

  • 2024.10: My first-authored paper on diffusion model image editing is accepted by WACV (CAAI-B)!
  • 2024.08: I am now a research engineer at MM of Meituan Inc, focusing on MLLM and AIGC.
  • 2024.07: I won the Invention Venture Award for Innovation from the China Invention Association.
  • 2024.07: My first-authored paper, MagicFight, is accepted by ACM MM (CCF-A)!
  • 2024.06: My first-authored paper, IFAST, is accepted by TIFS (CCF-A and SCI Q1 Top)!
  • 2024.04: I am awarded the Outstanding Graduate Student of Chinese Academy of Sciences, Outstanding Graduate Student of Beijing Universities (ไธญ็ง‘้™ขไผ˜็ง€ๆฏ•ไธš็”Ÿใ€ๅŒ—ไบฌ้ซ˜ๆ ก็ ”็ฉถ็”Ÿไผ˜็ง€ๆฏ•ไธš็”Ÿ)!
  • 2024.03: Our paper GPT4Motion is awarded the Best Paper Runner-Up (ๆœ€ไฝณ่ฎบๆ–‡ไบšๅ†›) in PBDL@CVPR 2024!
  • 2024.03: From 2023 to now, I had 12 articles accepted, 7 of which were regular papers in the CCF/Tsinghua list A/B journal/conference. Most of these papers are my first-authored.
  • 2023.12: I am awarded the SIAT president scholarship (้™ข้•ฟๅฅ–ๅญฆ้‡‘)!
  • 2023.10: I am awarded the Best Paper Candidate in PRICAI (Tsinghua list B in Mathematics)!
  • 2023.10: I get my SSP offers from many top companies. ๐Ÿ”ฌ
  • 2022.07: I work with Noahโ€™s Ark Lab, HUAWEI, and dedicate myself to exploring AIGC algorithm and their applications in low-level and 3D. ๐Ÿ”ฌ
  • 2022.06: ๐Ÿ‘จโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“ I am awarded the outstanding graduate student award of UCAS!
  • 2021.07: ๐Ÿ‘จโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“ I got my bachelorโ€™s degree and got an outstanding graduation thesis award โ€“ Grand prize (Top 0.5% of all bachelors in NJU, only 10+ bachelors got this prize๏ผŒๅณๅ—ไบฌๅคงๅญฆไผ˜็ง€ๆœฌ็ง‘ๆฏ•ไธš่ฎบๆ–‡็‰น็ญ‰ๅฅ–)!
  • 2021.06: ๐Ÿ‘จโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“ I met my close friend Donghao Zhou in SIAT.
  • 2021.04: I join CUHK@MMLAB in Shenzhen (also named SIAT@MMLAB) as a research assistant here.
  • 2021.03: ๐ŸŽ‰๐ŸŽ‰ I am pursuing my masterโ€™s degree at UCAS!
  • 2020.06: I was awarded the excellent member of the School of AI for a recommendation for graduate admission.
  • 2020.10: ๐ŸŽ‰๐ŸŽ‰ My three papers are accepted in the Forum of Science NJU 2020. ๐Ÿค–๏ธ
  • 2020.09: ๐ŸŽ‰๐ŸŽ‰ Again, I am awarded the second prize of Nanjing University scholarship!
  • 2019.10: ๐ŸŽ‰๐ŸŽ‰ Again, we won the first prize in the Sort Bank Cup China Robotics Competition 2019. ๐Ÿค–๏ธ
  • 2019.09: ๐ŸŽ‰๐ŸŽ‰ I am awarded the second prize of Nanjing University scholarship!
  • 2018.10: ๐ŸŽ‰๐ŸŽ‰ We won the first prize in the Sort Bank Cup China Robotics Competition 2018. ๐Ÿค–๏ธ
  • 2018.09: ๐ŸŽ‰๐ŸŽ‰ I become a member of the Robotics Lab belonging to the Lamda group at NJU (leading by Zhi-Hua Zhou). ๐Ÿค–๏ธ
  • 2017.07: ๐ŸŽ‰๐ŸŽ‰ I scored 641 points in the 2017 college entrance exam (้ซ˜่€ƒ), ranking in the Top 600 in Guangdong Province (Top 0.1% of all students in Guangdong๏ผŒ้ซ˜่€ƒๅนฟไธœ็œ็†็ง‘ๅ‰600ๅใ€ไฝ›ๅฑฑๅธ‚ๅ‰30ๅ๏ผŒๆ›พ่Žทไฝ›ๅฑฑๅธ‚่ฏญๆ–‡ๅ•็ง‘็Šถๅ…ƒ๏ผŒๅ‡บๅˆ†ๅฝ“ๅคฉๆŽฅๅˆฐไธญ็ง‘ๅคงใ€ๅ—ไบฌๅคงๅญฆ็ญ‰ๅŽไธœไบ”ๆ กๅ’Œไบบๆฐ‘ๅคงๅญฆๆ‹›็”ŸๅŠž็š„ๅคšๆฌก็”ต่ฏ).

๐Ÿ“ Publications

image

๐ŸŽ‰ I am a student member of MMLab (MM for multimedia), and most of my work is also focused on multimedia as well as multimodal generative research, so I frequently contribute papers to journals and conferences in the field of computer graphics and multimedia.

๐ŸŽ‰

  • Diffusion Model-Based Image Editing: A Survey (GitHub 400+ stars) (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Yi Huang*, Jiancheng Huang*, Yifan Liu, Mingfu Yan, Jiaxi Lv, Jianzhuang Liu, Wei Xiong, He Zhang, Shifeng Chen, Liangliang Cao (* indicates equal contribution)

    arXiv Preprint 2024 (Major Revision of TPAMI)

-[้‡ๅญไฝ] [ๆœบๅ™จไน‹ๅฟƒ] [ๆ–ฐๆ™บๅ…ƒ] [ๆˆ‘็ˆฑ่ฎก็ฎ—ๆœบ่ง†่ง‰] [ไธ“็Ÿฅ] [AI็”Ÿๆˆๆœชๆฅ]

๐ŸŽ‰

  • [MagicFight: Personalized Martial Arts Combat Video Generation] (AIGC๏ผš่ง†้ข‘็”Ÿๆˆ)

    Jiancheng Huang, et. al.

    ACM International Conference on Multimedia (ACM MM) | CCF-A | CAAI-A

    ๐ŸŽ‰

  • [IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images] (AIGC๏ผšๅ›พๅƒ็”Ÿๆˆ)

    Jiancheng Huang, Donghao Zhou, Shifeng Chen

    IEEE Transactions on Information Forensics and Security (TIFS) | SCI Q1 Top | CCF-A | Tsinghua list A | CAAI-A (GitHub 50+ stars)

๐ŸŽ‰

  • [Dual-Schedule Inversion: Tuning-Free Inversion for Real Image Faithful Reconstruction and Editing] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) | CAAI-B

    ๐ŸŽ‰

  • [WaveDM: Wavelet-Based Diffusion Models for Image Restoration] (AIGC๏ผš็”ŸๆˆๅผๅคๅŽŸ)

    Yi Huang*, Jiancheng Huang*, et. al. (* indicates equal contribution)

    IEEE Transaction on Multimedia (TMM) | SCI Q1 Top | Tsinghua list A | CAAI-A

    -[ๅ…ฌไผ—ๅท])

    ๐ŸŽ‰

  • MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models (AIGC๏ผšๅ›พๅƒ็”Ÿๆˆ)

    Donghao Zhou*, Jiancheng Huang*, et. al. (* indicates equal contribution)

    arXiv Preprint 2024 (Under Review of ICLR)

    -[arxiv] [project] [AIGCๅ…ฌไผ—ๅท]

    ๐ŸŽ‰

  • [SBCR: Stochasticity Beats Content Restriction Problem in Training and Tuning Free Image Editing] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    ACM International Conference on Multimedia Retrieval (ICMR) | CCF-B

    ๐ŸŽ‰

  • [Stable Diffusion already has a noisy style latent space] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    IEEE International Conference on Multimedia and Expo (ICME) | CCF-B

    ๐ŸŽ‰

  • [Entwined Inversion: Tune-Free Inversion for Real Image Faithful Reconstruction and Editing] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | CCF-B | Tsinghua list A

    ๐ŸŽ‰

  • [BK-Editer: Body-Keeping Text-Conditioned Real Image Editing] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    Computational Visual Media (CVM) | CCF-C

    ๐ŸŽ‰

  • GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning (GitHub 110+ stars) (AIGC๏ผš่ง†้ข‘็”Ÿๆˆ)

    Jiaxi Lv, Yi Huang, Mingfu Yan, Jiancheng Huang, et. al.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) PDBL (Best Paper Runner-Up)

    [ๆœบๅ™จไน‹ๅฟƒ]

    ๐ŸŽ‰

  • [NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results]

    et. al, Jiancheng Huang, et. al.

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

    ๐ŸŽ‰

  • [Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement] (AIGC๏ผš็”ŸๆˆๅผๅคๅŽŸ)

    Jiancheng Huang, et. al.

    Pacific Rim International Conference on Artificial Intelligence (PRICAI) | Tsinghua list B in Mathematics (Best Paper Candidate)

    ๐ŸŽ‰

  • [DeSeal: Semantic-Aware Seal2Clear Attention for Document Seal Removal] (AIGC๏ผš็”ŸๆˆๅผๅคๅŽŸ)

    Yifan Liu*, Jiancheng Huang*, et. al. (* indicates equal contribution)

    IEEE Signal Processing Letters (SPL) | SCI Q2 | Tsinghua list B

    ๐ŸŽ‰

  • [Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes]

    Donghao Zhou, Jialin Li, Jinpeng Li, Jiancheng Huang, Qiang Nie, Yong liu, Bin-Bin Gao, Qiong Wang, Pheng-Ann Heng, Guangyong Chen

    British Machine Vision Conference (BMVC) | Tsinghua list B

    ๐ŸŽ‰

  • [MambaDW: Semantic-Aware Mamba for Document Watermark Removal] (AIGC๏ผš็”ŸๆˆๅผๅคๅŽŸ)

    Yifan Liu, Mingfu Yan, Jiancheng Huang, et. al.

    Computer Graphics International (CGI) | Tsinghua list B

    ๐ŸŽ‰

  • [Learning Image-Adaptive Lookup Tables With Spatial Awareness for Image Harmonization] (AIGC๏ผš็”ŸๆˆๅผๅคๅŽŸ)

    Yi Huang, Yu Dong, He Zhang, Jiancheng Huang, Shifeng Chen

    IEEE Transactions on Consumer Electronics (TCE) | SCI Q1

    ๐ŸŽ‰

  • [Matten: Video Generation with Mamba-Attention] (AIGC๏ผš่ง†้ข‘็”Ÿๆˆ)

    Jiancheng Huang, et. al.

    arXiv Preprint 2024 (Under Review)

    [AIๅ…ฌไผ—ๅท]

    ๐ŸŽ‰

  • [MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Jiancheng Huang, et. al.

    arXiv Preprint 2024 (Under Review)

    [AIๅ…ฌไผ—ๅท] ๐ŸŽ‰

  • [SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing] (AIGC๏ผšๅ›พๅƒ็ผ–่พ‘)

    Songyan Chen, Jiancheng Huang* (* indicates corresponding author)

    arXiv Preprint 2023 (Under Review) (GitHub 30+ stars)

    ๐ŸŽ‰

  • [Pi-fusion: Physics-informed diffusion model for learning fluid dynamics]

    Jing Qiu*, Jiancheng Huang*, et. al. (* indicates equal contribution)

    arXiv Preprint 2024 (Under Review)

    ๐ŸŽ‰

  • [Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation] (AIGC๏ผšๅ›พๅƒ็”Ÿๆˆ)

    Jiancheng Huang, Yifan Liu, Shifeng Chen

    arXiv Preprint 2023 (Under Review)

    ๐ŸŽ‰

  • [Graph Edit Distance Learning via Different Attention]

    Jiaxi Lv, Liang Zhang, Yi Huang, Jiancheng Huang, Shifeng Chen

    arXiv Preprint 2023 (Under Review)

    ๐ŸŽ‰

๐ŸŽ– Honors and Awards

  • 2023.12: I am awarded the SIAT president scholarship!
  • 2023.12: I am awarded the best paper candidate in PRICAI (Tsinghua list B in Mathematics)!
  • 2022.06: ๐Ÿ‘จโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“ I am awarded the outstanding graduate student award of UCAS!
  • 2021.07: ๐Ÿ‘จโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“ I get an outstanding graduation thesis award โ€“ first prize (Top 0.5% of all bachelors in NJU)!
  • 2020.06: I was awarded the excellent member of School of AI for recommendation for graduate admission.
  • 2020.10: ๐ŸŽ‰๐ŸŽ‰ My three papers are accepted in the Forum of Science NJU 2020. ๐Ÿค–๏ธ
  • 2020.09: ๐ŸŽ‰๐ŸŽ‰ Again, I am awarded the second prize of Nanjing University scholarship!
  • 2019.10: ๐ŸŽ‰๐ŸŽ‰ Again, we win the first prize of the Soft Bank Cup China Robotics Competition 2019. ๐Ÿค–๏ธ
  • 2019.09: ๐ŸŽ‰๐ŸŽ‰ I am awarded the second prize of Nanjing University scholarship!
  • 2018.10: ๐ŸŽ‰๐ŸŽ‰ We win the first prize of the Soft Bank Cup China Robotics Competition 2018. ๐Ÿค–๏ธ

๐Ÿ“– Educations

  • 2021.06 - now, Artificial Intelligence, University of Chinese Academy of Sciences.
  • 2017.06 - 2021.06, Automation, Nanjing University.
  • 2014.09 - 2017.06, Foshan No.1 Middle School.

๐Ÿ’ป Research Fields

  • 2022.07-now โ€‚ Diffusion Models algorithm research.
  • 2022.06 โ€‚ Image low-level vision algorithm research.
  • 2020.01 โ€‚ Robust face algorithm research.
  • 2018.07 โ€‚ Robot motion algorithm research.

๐Ÿ‘จโ€๐Ÿ’ป Internships

  • 2024.07 - Now โ€‚ Research Engineer, MM, Meituan, Shenzhen, China
  • 2022.07 - 2023.01 โ€‚ Research Collaborator, Noahโ€™s Ark Lab, HUAWEI, Shenzhen, China
  • 2021.04 - 2021.08 โ€‚ Research Assistant, SIAT, Shenzhen, China
  • 2018.06 - 2019.10 โ€‚ Team Captain, Robotics Lab of NJU, Nanjing, China