Jinwoo Ahn

👋 Hey! I am a third-year undergraduate student at Berkeley EECS with an honors concentration in cognitive science. I will be returning to Berkeley in the fall to continue my studies upon completion of my military service.

🕐 I was previously affiliated twice with Boeing Research & Technology as a research intern. Before this, I worked with Dr. Ruiqi Zhong at Berkeley AI Research on concrete problems of natural language processing.

🔍 I am actively looking for industry internships (South Korea) and academic research opportunities (Anywhere on Earth) for Summer 2026 and beyond.

Email  /  Scholar  /  Twitter  /  Github  /  LinkedIn  /  Medium

profile photo

Research

I envision developing AI systems that imitate the human thought process across different modalities. For this purpose, I work with different types of inputs to reduce the gap between human and machine cognition. Recently, I am shifting my interest towards building AI systems that are safe and reliable.

News

  • [5/24/2026] I officially discharged from the military. It definitely felt longer than it actually was.
  • [6/25/2025] One paper has been accepted to ICCV 2025.
  • [1/2/2025] I will be serving my mandatory military service at the Combined Forces Command.
  • [9/15/2024] I am now a part of AttentionX as a guest member.
  • [1/15/2024] I will be returning to Boeing as a Research Intern.
  • [9/21/2023] One paper has been accepted to NeurIPS 2023.
  • [7/15/2023] I am now a part of the Berkeley EECS Honors Program.
  • [6/26/2023] I will be working at Boeing as a Research Intern.
  • [6/12/2022] I will be working at Dashlabs.ai as a Software Engineering Intern.

Blog

Publications

VAGUE: Visual Contexts Clarify Ambiguous Expressions
Heejeong Nam*, Jinwoo Ahn*, Keummin Ka, Jiwan Chung, Youngjae Yu
International Conference on Computer Vision (ICCV), 2025
[paper] [code] [project]

Goal Driven Discovery of Distributional Differences via Language Descriptions
Ruiqi Zhong, Peter Zhang, Steve Li, Jinwoo Ahn, Dan Klein, Jacob Steinhardt
Advances in Neural Information Processing Systems (NeurIPS), 2023
[paper] [code]

Others

Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation
Jinwoo Ahn, Hyeokjoon Kwon, Hwiyeon Yoo
Technical Report, 2024
[paper]

Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting
Jinwoo Ahn, Kyuseung Shin
Technical Report, 2024
[paper]

Miscellaneous

  • I come from a multicultural background. I was born in Korea, grew up in China, and am now living in the US.
  • I train mixed martial arts. I occasionally go on amateur leagues and want to fight professionally someday.
  • I have my own way of staying disciplined. I either run, train martial arts, and/or lift at the gym regularly.

Collaboration

I am very optimistic towards research collaboration, especially if we plan to submit to top venues or legalize them as patents. I frequently pursue personal projects with external collaborators on ideas that I find worth investigating. If you believe you will benefit from having a collaborator like me, please do not hesitate to reach out.

Below are my fantastic collaborators that I worked or am currently working with:

  • Kyuseung Shin (Everspin; EECS at UC Berkeley)
  • Heejeong Nam (Boeing; MSCS at Brown)
  • Hwiyeon Yoo, PhD (Boeing; now at Naver Labs)
  • Hyeokjoon Kwon (Boeing; MSR at CMU)

Website design from Jon Barron