Shutong JIN's homepage | KTH Royal Institute of Technology

Shutong JIN

Hi there! I'm currently a PhD student at RPL, KTH Royal Institute of Technology under the supervision of Assoc. Prof. Florian Pokorny (main supervisor) and Prof. Erik Elmroth (co-supervisor), funded by Wallenberg AI, Autonomous Systems and Software Program (WASP). My research includes two directions:

Attention as a tool for zero-shot robotic manipulation.
Scaling behaviors for learning-based methods with the large-scale cloud robotics platform CloudGripper we designed at KTH.

Current Research Interest: Attention Mechanism, Zero-shot Robotic Manipulation, Vision/Video Transformers/Diffusion Models, Visuo-motor Control Policies.

[Contact][Github] [Google Scholar]

Publications

	PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement [Video] Shutong Jin, Ruiyu Wang, Kuangyi Chen, Florian T. Pokorny Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
	Feature Extractor or Decision Maker: Rethinking the Role of Visual Encoders in Visuomotor Policies Ruiyu Wang, Zheyu Zhuang, Shutong Jin, Nils Ingelhag, Danica Kragic, Florian T. Pokorny Preprint
	CloudGripper-Push-1K: Understanding the Generalization Gap of Physics and Background Attributes for Robotic Manipulation Shutong Jin, Ruiyu Wang, Zahid Muhammad and Florian T. Pokorny IEEE/RSJ IROS 2024 Workshop on Collecting, Managing, and Utilizing Data through Embodied Robots. Best Poster Award
	CloudGripper-AutoGrasper: A Cloud Robotics Toolkit for Automatic Data Collection Axel Kaliff, Shutong Jin, Zahid Muhammad and Florian T. Pokorny IEEE/RSJ IROS 2024 Workshop on Collecting, Managing, and Utilizing Data through Embodied Robots.
	RealCraft: Attention Control as A Tool for Zero-shot Consistent Video Editing Shutong Jin, Ruiyu Wang and Florian T. Pokorny Preprint.
	How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing [Video] Shutong Jin, Ruiyu Wang, Muhammad Zahid and Florian T. Pokorny 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
	SectionKey: 3-D Semantic Point Cloud Descriptor for Place Recognition Shutong Jin, Zhenyu Wu, Chunyang Zhao, Jun Zhang, Guohao Peng and Danwei Wang 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).