I am a Senior Researcher at Tencent. I earned my PhD degree from NUS National University of Singapore (NUS), Department of Electrical and Computer Engineering (ECE), supervised by Prof. Robby T. Tan. I had my research internship in Adobe Adobe, mentored by Prof. Connelly Barnes.

Previously, I completed my M.Sc. degree at the NUS National University of Singapore (NUS); received my B.Eng. degree from the UESTC University of Electronic Science and Technology of China (UESTC).

My primary research interests include computer vision and deep learning, mainly focusing on AIGC and Multimodal. I’m looking for self-motivated interns and full-time researchers.

📜 Research Area

  1. AIGC (e.g., GAN, Diffusion, LoRA training, FLUX, SDXL Lighting, SDXL Turbo, Hyper SD, SDXL, SD1.5, LCM, Midjourney)
  2. Talking Face Generation
  3. Multimodal, Direct Preference Optimization (DPO)
  4. Image/Video Enhancement, Restoration and Decomposition (e.g., Intrinsic Image Decomposition)
  5. Deep Learning and its Applications (e.g., Medical Images)

📝 Publications

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
Songtao Jiang, Yan Zhang, Ruizhe Chen, Yeying Jin, Zuozhu Liu
arXiv, 2024
arXiv | bibtex

Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models
Songtao Jiang, Yan Zhang, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, Zuozhu Liu
arXiv, 2024
arXiv | | bibtex

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Zuozhu Liu
EMNLP finding, 2024, Miami, Florida
arXiv | | bibtex

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal
Yeying Jin, Xin Li, Jiadong Wang, Yan Zhang, Malu Zhang
European Conference on Computer Vision (ECCV), 2024, Milan, Italy
arXiv | | bibtex | poster | slides | video

Dual-Rain: Video Rain Removal using Assertive and Gentle Teachers
Tingting Chen*, Beibei Lin*, Yeying Jin*, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan (Equal-first author)
European Conference on Computer Vision (ECCV), 2024, Milan, Italy
arXiv | bibtex

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt
Xin Li, Bingchen Li, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren, Zhibo Chen
European Conference on Computer Vision (ECCV), 2024, Milan, Italy
arXiv | | bibtex

NightHaze: Nighttime Image Dehazing via Self-Prior Learning
Beibei Lin*, Yeying Jin*, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan (Equal-first author)
In review, 2024
arXiv | bibtex

SeD: Semantic-Aware Discriminator for Image Super-Resolution
Bingchen Li, Xin Li, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen
Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Seattle, USA
arXiv | | bibtex

DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
Yeying Jin, Yuan Yuan, Wenhan Yang, Wei Ye, Robby T. Tan
Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada
arXiv | | bibtex | paper | poster | slides

First diffusion-based shadow removal performs robustly on hard, soft and self shadows.

NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction
Beibei Lin*, Yeying Jin*, Wending Yan, Wei Ye, Yuan Yuan, Sunli Zhang, Robby T. Tan
Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada
arXiv | bibtex | poster

Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression
Yeying Jin, Wenhan Yang, Robby T. Tan
European Conference on Computer Vision (ECCV), 2022, Tel Aviv, Israel
arXiv | | bibtex | paper | supp | poster | slides | video | data | link

Night image enhancement by enhancing low-light regions and suppressing light-effects regions.

DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network
Yeying Jin, Aashish Sharma, Robby T. Tan
International Conference on Computer Vision (ICCV), 2021, Montreal, Canada
arXiv | | bibtex | paper | supp | poster | slides | video

First unsupervised hard and soft shadow removal.

Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution
Yeying Jin*, Beibei Lin*, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan
ACM Multimedia (ACM'MM), 2023, Ottawa, Canada
arXiv | | bibtex | paper | poster | slides | data

First learning-based network handling nighttime haze and glow using APSF.

Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning
Yeying Jin, Ruoteng Li, Wenhan Yang, Robby T. Tan
Association for the Advancement of Artificial Intelligence (AAAI), 2023, Washington DC, USA
arXiv | | bibtex | paper | poster | slides

First reflectance layer estimation that performs robustly even in the presence of shadows and specularities.

Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal
Yeying Jin, Wending Yan, Wenhan Yang, Robby T. Tan
Asian Conference on Computer Vision (ACCV), 2022, Macau, China
arXiv | | bibtex | paper | supp | poster | slides | data

Dense and/or non-uniform fog removal.

🏫 Educations

  • 01.2020-01.2024: Ph.D. (Computer Vision and Deep Learning), NUS NUS, Singapore (CAP: 4.75/5.00)
  • 08.2017-08.2018: M.S. (Electrical and Computer Engineering), NUS NUS, Singapore
  • 09.2013-07.2017: B.Eng (Electrical and Computer Engineering), UESTC UESTC, China (GPA: 3.93/4.00)

👔 Internship and Work Experience

🎖 Honors and Awards

💻 Academic Services

  • Reviewer: ICLR’25, NeurIPS’23-24, ECCV’22-24, CVPR’22-25, ICCV’23, TPAMI’23, IJCV’24, AAAI’23-25, TIP’23, CVIU’23, TCSVT’23, TVCJ’23, NEUCOM’23, ACCV’22-24, IJCAI’22, IJCNN’21, etc.
  • Teaching Assistant: EE5731 Visual Computing, EE5904 Neural Network (NUS ECE)

💬 Invited Talks

TopicHostDate
Raindrop Clarity: Dual-Focused, Day & NightAITIME AI TIME09.2024
Shadow Removal using Diffusion ModelAITIME AI TIME01.2024
Visibility Enhancement using Generative ModelHuawei Huawei Shanghai HiSilicon07.2023
NextCam Reading Group: Light-effects SuppressionAdobe Adobe, USA07.2023
Image/Video Restoration and GenerationHuawei Huawei Shanghai HiSilicon03.2023
Intrinsic Image DecompositionAITIME AI TIME02.2023
Diffusion Model in Image ProcessingByteDance (invited by Hanshu Yan)01.2023
Visibility Enhancement in NighttimeHuawei Huawei, Singapore12.2022
Unsupervised Image Restoration and GenerationAITIME AI TIME11.2022
PosterVenueDate
Poster Present at VALSEVALSE Chongqing, China05.2024
Poster Present at Singapore Vision DayNUS NUS, Singapore05.2023
Poster Present at AI Research SymposiumAISG AISG, Singapore01.2023