Shutong Jin

Orcid: 0000-0003-0611-4239

According to our database1, Shutong Jin authored at least 16 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution.
CoRR, April, 2026

Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation.
CoRR, March, 2026

RoboLight: A Dataset with Linearly Composable Illumination for Robotic Manipulation.
CoRR, March, 2026

2025
ReLumix: Extending Image Relighting to Video via Video Diffusion Models.
CoRR, September, 2025

Physically-based Lighting Augmentation for Robotic Manipulation.
CoRR, August, 2025

Can Visuo-motor Policies Benefit from Random Exploration Data? A Case Study on Stacking.
CoRR, March, 2025

CuFDFB: Fast and Private Computation on Non-Linear Functions Using FHE.
IACR Cryptol. ePrint Arch., 2025

PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Feature Extractor or Decision Maker: Rethinking the Role of Visual Encoders in Visuomotor Policies.
Proceedings of the IEEE International Conference on Robotics and Automation, 2025

RealCraft: Attention Control as A Tool for Zero-Shot Consistent Video Editing.
Proceedings of the Neural Information Processing - 32nd International Conference, 2025

One-Shot Federated Learning with Classifier-Free Diffusion Models.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2025

2024
Efficient Key-Switching for Word-Type FHE and GPU Acceleration.
IACR Cryptol. ePrint Arch., 2024

How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024

2023
RealCraft: Attention Control as A Solution for Zero-shot Long Video Editing.
CoRR, 2023

Video Transformers under Occlusion: How Physics and Background Attributes Impact Large Models for Robotic Manipulation.
CoRR, 2023

2022
SectionKey: 3-D Semantic Point Cloud Descriptor for Place Recognition.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022


  Loading...