Projects - Jin Sun

Computer Vision

Image relighting, image synthesis, 3D reconstruction, scene understanding, human analysis, object detection, context modeling.

View Publications

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

Fukun Liu , Adam T Greer , Gengchen Mai and Jin Sun

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) Datasets and Benchmarks (2025)

Code arXiv
Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Tianze Yang , Yucheng Shi , Mengnan Du , Xuansheng Wu , Qiaoyu Tan , Jin Sun and Ninghao Liu

Forty-second International Conference on Machine Learning (ICML) (2025)
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

Yucheng Shi , Quanzheng Li , Jin Sun , Xiang Li and Ninghao Liu

International Conference on Learning Representations (ICLR) (2025)

Code arXiv
Neural Gaffer: Relighting Any Object via Diffusion

Haian Jin , Yuan Li , Fujun Luan , Yuanbo Xiangli , Sai Bi , Kai Zhang , Zexiang Xu , Jin Sun and Noah Snavely

Conference on Neural Information Processing Systems (NeurIPS) (2024)

Code arXiv
Black-box Backdoor Defense via Zero-shot Image Purification

Yucheng Shi , Mengnan Du , Xuansheng Wu , Zihan Guan , Jin Sun and Ninghao Liu

Conference on Neural Information Processing Systems (NeurIPS) (2023)

Code arXiv
What’s in a Decade? Transforming Faces Through Time

Eric Ming Chen , Jin Sun , Apoorv Khandelwal , Dani Lischinski , Noah Snavely and Hadar Averbuch-Elor

Eurograhics (2023)

arXiv
Towers of babel: Combining images, language, and 3d geometry for learning multimodal vision

Xiaoshi Wu , Hadar Averbuch-Elor , Jin Sun and Noah Snavely

Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)
Visual chirality

Zhiqiu Lin , Jin Sun , Abe Davis and Noah Snavely

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Leveraging vision reconstruction pipelines for satellite imagery

Kai Zhang , Noah Snavely and Jin Sun

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)

Multi-Modal Learning

Cross-modal retrieval and generation, multi-modal representation learning, VLMs and LLMs.

View Publications

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

Fukun Liu , Adam T Greer , Gengchen Mai and Jin Sun

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) Datasets and Benchmarks (2025)

Code arXiv
Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Tianze Yang , Yucheng Shi , Mengnan Du , Xuansheng Wu , Qiaoyu Tan , Jin Sun and Ninghao Liu

Forty-second International Conference on Machine Learning (ICML) (2025)
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

Yucheng Shi , Quanzheng Li , Jin Sun , Xiang Li and Ninghao Liu

International Conference on Learning Representations (ICLR) (2025)

Code arXiv
On the opportunities and challenges of foundation models for geospatial artificial intelligence

Gengchen Mai , Weiming Huang , Jin Sun , Suhang Song , Deepak Mishra , Ninghao Liu , Song Gao , Tianming Liu , Gao Cong , Yingjie Hu and others

ACM Transactions on Spatial Algorithms and Systems (2024)

arXiv

AI for Science, Health, and Society

View Publications

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

Fukun Liu , Adam T Greer , Gengchen Mai and Jin Sun

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) Datasets and Benchmarks (2025)

Code arXiv
On the opportunities and challenges of foundation models for geospatial artificial intelligence

Gengchen Mai , Weiming Huang , Jin Sun , Suhang Song , Deepak Mishra , Ninghao Liu , Song Gao , Tianming Liu , Gao Cong , Yingjie Hu and others

ACM Transactions on Spatial Algorithms and Systems (2024)

arXiv
PeanutNeRF: 3D Radiance Field for Peanuts

Farah Saeed , Jin Sun , Peggy Ozias-Akins , Ye Juliet Chu and Changying Charlie Li

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2023)

Research Topics

Computer Vision

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

Neural Gaffer: Relighting Any Object via Diffusion

Black-box Backdoor Defense via Zero-shot Image Purification

What’s in a Decade? Transforming Faces Through Time

Towers of babel: Combining images, language, and 3d geometry for learning multimodal vision

Visual chirality

Leveraging vision reconstruction pipelines for satellite imagery

Multi-Modal Learning

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

On the opportunities and challenges of foundation models for geospatial artificial intelligence

AI for Science, Health, and Society

ZooplanktonBench: A Geo-Aware Zooplankton Recognition and Classification Dataset from Marine Observations

On the opportunities and challenges of foundation models for geospatial artificial intelligence

PeanutNeRF: 3D Radiance Field for Peanuts