Jingxi Chen

Bio

Welcome! I am a Ph.D. student in the Computer Science Department at the University of Maryland, College Park, where I work with Prof. Yiannis Aloimonos and Dr. Cornelia Fermüller in the Perception and Robotics Group. I also work closely with Prof. Christopher Metzler.

During my Ph.D., I have been a Student Researcher at Google Research, an Applied Scientist Intern at Amazon, and a Ph.D. Research Intern at Dolby Laboratories.

Selected Publications

For a complete publication list, please see Google Scholar.

	First Frame Is the Place to Go for Video Content Customization Jingxi Chen*, Zongxia Li*, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermüller, Brandon Y. Feng, Yiannis Aloimonos. CVPR 2026. This work studies controlled video generation by composing content from multiple reference images. We propose a novel and efficient formulation that leverages the in-context capabilities of pre-trained video generation models. Website Paper
	From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition Jingxi Chen, Yixiao Zhang, Xiaoye Qian, Zongxia Li, Cornelia Fermüller, Caren Chen, Yiannis Aloimonos. CVPR 2026. Diffusion-based Image Layer Decomposition with a unified token-to-token model. Work done during my summer internship at Amazon Prime Video team. Website Paper
	Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation Jingxi Chen, Brandon Y. Feng, Haoming Cai, Tianfu Wang, Levi Burner, Dehao Yuan, Cornelia Fermüller, Christopher A. Metzler, Yiannis Aloimonos. CVPR 2025. In this work, we adapt pre-trained video diffusion models trained on internet-scale datasets to solve the specialized real-world video task of event-based video interpolation. Website
	Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations Haoming Cai*, Jingxi Chen*, Brandon Y. Feng, Weiyun Jiang, Mingyang Xie, Kevin W. Zhang, Cornelia Fermüller, Yiannis Aloimonos, Ashok Veeraraghavan, Christopher A. Metzler. NeurIPS 2024. ConVRT is an efficient INR framework for video-based turbulence mitigation that operates in test-time optimization manner. Website
	Active Human Pose Estimation via an Autonomous UAV Agent Jingxi Chen, Botao He, Chahat D. Singh, Cornelia Fermüller, Yiannis Aloimonos. IROS 2024. We leverage radiance fields to imagine different human views to find the best drone pose for aerial cinematography. Website
	Microsaccade-inspired Event Camera for Robotics Botao He, Ze Wang, Yuan Zhou, Jingxi Chen, Chahat D. Singh, Haojia Li, Yuman Gao, Shaojie Shen, Kaiwei Wang, Yanjun Cao, Chao Xu, Yiannis Aloimonos, Fei Gao, Cornelia Fermüller. Science Robotics, 2024. Inspired by microsaccades, we designed an event-based perception system capable of simultaneously maintaining low reaction time and stable texture. Website Paper
	CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras Sachin Shah, Matthew Chan, Haoming Cai, Jingxi Chen, Sakshum Kulshrestha, Chahat D. Singh, Christopher A. Metzler, Yiannis Aloimonos. CVPR 2024. CodedEvents is a novel method for optimal point-spread-function engineering for 3D-tracking with event cameras. Paper
	ProxMaP: Proximal Occupancy Map Prediction for Efficient Indoor Robot Navigation Vishnu D. Sharma, Jingxi Chen, Pratap Tokekar. IROS 2023. We present a self-supervised occupancy prediction technique, ProxMaP, to predict the occupancy within the proximity of the robot to enable faster navigation. Website
	Multi-Agent Reinforcement Learning for Visibility-based Persistent Monitoring Jingxi Chen*, Amrish Baskaran*, Zhongshun Zhang, Pratap Tokekar. IROS 2021. We present a Multi-Agent Reinforcement Learning (MARL) algorithm for the Visibility-based Persistent Monitoring (VPM) problem. Paper

* Equal contribution.

Experiences

• Google Research Summer 2026

  Student Researcher
  Conducted fundamental research on frontier video and world generation models, focusing on 3D geometry, motion dynamics, and long-term world consistency, with large-scale distributed training using JAX and TPUs.
• Amazon Summer 2025

  Applied Scientist Intern
  Diffusion-based image layer decomposition (CVPR 2026).
  Strongly Inclined (Top 1% of all interns).
• Dolby Laboratories Summer 2024

  Ph.D. Research Intern
  Neural event data compression and neural video codecs; two patents submitted.
• University of Maryland Fall 2022 – Present

  Ph.D. in Computer Science
  Perception and Robotics Group.
• Brain Corp Jun – Aug 2022

  Robotics Software Engineer Intern
• University of Maryland 2020 – 2022

  M.S. in Computer Science
• University of Maryland 2017 – 2020

  B.S. in Computer Science

Honors & Service

Fellowships & Awards

• NeuroPAC Fellowship 2024
  Supported by the NSF grant "AccelNet: Accelerating Research on Neuromorphic Perception, Action, and Cognition."
• Ph.D. Dean Fellowship 2022 – 2023
  University of Maryland, College Park.
• John D. Gannon Endowed Scholarship
• Capital One Bank Dean's Scholarship Fund in Computer Science

Service

• Conference Reviewer
  CVPR 2025, ICCV 2025, ICRA 2021, 2023, 2024, IROS 2021, 2022, 2024.
• Journal Reviewer
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).