About me

I’m a master’s student in Computer Science at the University of Maryland, College Park, where I conduct research under the guidance of Prof. Ruohan Gao.

I earned my B.S. in Computer Science from Yonsei University, graduating summa cum laude and was honored as the department’s valedictorian. During my undergraduate studies, I had the privilege of being advised by Prof. Seon Joo Kim.

My primary interest lies in multisensory machine learning, with the goal of enabling machines to perceive and reason about the physical world and human behavior by integrating diverse signals such as audiovisual, tactile, behavioral, and other nonverbal cues, while generalizing across diverse and dynamic environments for robust and holistic perception.

For more details, please refer to my CV.

---

Publications

(* denotes equal contribution)

• Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024
  Nuria Alina Chandra, Ryan Murtfeldt, Lin Qiu, Arnab Karmakar, Hannah Lee, Emmanuel Tanumihardja, Kevin Farhat, Ben Caffee, Sejin Paik, Changyeon Lee, Jongwook Choi, Aerin Kim, Oren Etzioni
  Under Review
  [Paper]

• Cost-Efficient and Effective Counter Unmanned Aerial System via Visual-Acoustic Sensing
  Changyeon Lee*, Dongju Yu*, Soyeon Cho*, Dane W. Hindsley, Halaevalu F. Patterson, Megan A. Clecak, Eric T. Matson
  IEEE International Conference on Robotic Computing (IRC) 2024
  [Paper]

• DistilDIRE: A Small, Fast, Cheap and Light Diffusion Synthesized Deepfake Detection
  Yewon Lim*, Changyeon Lee*, Aerin Kim, Oren Etzioni
  ICML 2024 Workshop on Foundation Models in the Wild
  [Paper] [Code]

• The Tug-Of-War Between Deepfake Generation and Detection
  Hannah Lee, Changyeon Lee, Kevin Farhat, Lin Qiu, Steve Geluso, Aerin Kim, Oren Etzioni
  ICML 2024 Workshop on Data-centric Machine Learning Research
  [Paper]

• Towards Interpretable Controllability in Object-Centric Learning
  Jinwoo Kim*, Janghyuk Choi*, Jaehyun Kang, Changyeon Lee, Ho-Jin Choi, Seon Joo Kim
  CVPR 2024 Workshop on Causal and Object-Centric Representations for Robotics
  [Paper]