About Me

Jr-Jen Chen (Jacky)

Deep Learning Researcher

Hi, I am Jr-Jen Chen, a research assistant (former MS student) in the Vision and Learning Lab (VLLab) at National Taiwan University's Graduate Institute of Communication Engineering, advised by Prof. Yu-Chiang Frank Wang. I currently work remotely as a research intern with Prof. Ming-Hsuan Yang at UC Merced. During my graduate studies, I collaborated with Yen-Chun Chen at Microsoft on multi-modal large language models and video understanding, and worked with Prof. Yilun Du on compositional generative models for self-improving embodied agents. My research interests lie at the intersection of computer vision, multimodal reasoning, continual learning and robotics. I obtained my BE degree from the Department of Mechanical Engineering at National Taiwan University. I'm actively seeking PhD position in this field starting from 2026 fall. Feel free to reach out to me if you have any opportunities!

Research Interests:

Multi-modal Large Language Models Reasoning-across-time in Videos Video Reasoning and Moment Localization Continual Learning MLLMs in Robotics Compositional Generative Models Diffusion Models

Enabling AI to imagine, reason, and learn continually like humans.

Publications

Reinforcing Compositional Robotic Agents

MoSEL: Modular Self-Reflective Learning for Embodied Decision-Making

Authors: Jr-Jen Chen, Yilun Du, Yu-Chiang Frank Wang

Under review: ICLR 2026

[ Project Page ] [ Open Review ]

Continual Personalization in Diffusion Models

Authors: Yu-Chien Liao*, Jr-Jen Chen*, Chi-Pin Huang, Ci-Siang Lin, Meng-Lin Wu, Yu-Chiang Frank Wang

Conference: ICCV 2025 (Poster)

[ Project Page ] [ arXiv ]

ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos

Authors: Jr-Jen Chen, Yu-Chien Liao, Hsi-Che Lin, Yu-Chu Yu, Yen-Chun Chen, Yu-Chiang Frank Wang

Conference: NeurIPS 2024 Datasets and Benchmarks (Poster)

[ Project Page ] [ arXiv ] [ GitHub ] [ Huggingface ] [ Leaderboard ]

Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models

Authors: Yu-Chu Yu, Chi-Pin Huang, Jr-Jen Chen, Kai-Po Chang, Yung-Hsuan Lai, Fu-En Yang, Yu-Chiang Frank Wang

Conference: ECCV 2024 (Poster)

[ Project Page ] [ arXiv ] [ GitHub ]

Resume

Education

National Taiwan University

2023 - Present

Master of Graduate Institute of Communication Engineering

GPA: 4.30 / 4.30
Award: The Phi Tau Phi Scholastic Honor Society (Top 1%)

National Taiwan University

2019 - 2023

Bachelor of Mechanical Engineering

GPA: 4.08 / 4.30
Rank: 8 / 140
Award: 3 times of Dean's List

Teaching Assistant

Deep Learning for Computer Vision

2022 Fall, 2023 Fall

Instructor: Yu-Chiang Frank Wang

Course Link

Awards

Certificate of Achievement of MOBILEHEROS 2021 CONNECTIVITY INNOVATION AWARDS

awarded by Bureau of Industry, Ministry of Economic Affairs

2nd of NASA 2020, INTERNATIONAL SPACE APP CHALLENGE

awarded by American Institute in Taiwan

Professional Experience

Research Intern

2025 - Present

Vision and Learning Lab, Advisor: Ming-Hsuan Yang

University of California, Merced

Multi-modal Large Langugage Models
Visual Reasoning

Research Assistant

2025 - Present

Vision and Learning Lab, Advisor: Yu-Chiang Frank Wang

Graduate Institute of Communication Engineering, National Taiwan University

Multi-modal Large Langugage Models / Video Understanding
Continual Learning on Vision-Language Models
Diffusion Models Personalization

ADLINK Assistant Engineer

2022.07 - 2022.08

IoT Solutions & Technology Business Unit-Solution Architect & Technical Support

Machine Learning / Anomaly Detection
Edge Computation

Undergraduate Student Researcher

2021.08 - 2022.01

Bio-inspired Robotics Lab, Advisor: Pei-Chun Lin

Department of Mechanical Engineering, National Taiwan University

Publication: EnveRob: Integration of an Intelligent Robotic Arm System for Mail Delivery Applications
Object Dection / Depth Estimatioin
Robot Operation System (ROS).