Byeonghwi Kim (김병휘)

I'm a Ph.D. student at SNU Machine Perception and Reasoning Lab. at Seoul National University advised by Prof. Jonghyun Choi. My research focus is on Embodied AI, Robotics, and Physical AI.

I was fortunate to work as a research intern at the Physical AI team at Krafton AI (2025) and the PRIOR team at Allen Institute of Artificial Intelligence (AI2) (2021-2022). Currently, I am looking for a research internship position for physical AI research.

I completed a Ph.D. course at Yonsei University and received a M.S. degree from Gwangju Institute of Science and Technology under the supervision of Prof. Jonghyun Choi. I received a B.S. degree with first-class honors from Kwangwoon University under the supervision of Prof. Cheolsoo Park.

CV  /  Email  /  Google Scholar  /  Semantic Scholar  /  DBLP  /  LinkedIn  /  Github

profile photo

    Work Experience
Krafton AI
Research Intern at Physical AI Team (Jun. 2025 ~ Dec. 2025)
Mentor: Dr. Kangwook Lee
Allen Institute for AI (AI2)
Research Intern at PRIOR Team (Sept. 2021 ~ Mar. 2022)
Mentor: Dr. Roobzeh Mottaghi
    Selected Publications
Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples
Taewoong Kim, Byeonghwi Kim, Jonghyun Choi
AAAI 2025 (Oral)
[pdf] [bibtex] [code]
Pre-emptive Action Revision by Environmental Feedback for Embodied Instruction Following Agents
Jinyeon Kim*, Cheolhong Min*, Byeonghwi Kim, Jonghyun Choi
CoRL 2024
[pdf] [bibtex] [code]
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
Taewoong Kim*, Cheolhong Min*, Byeonghwi Kim, Jinyeon Kim, Wonje Jeung, Jonghyun Choi
ECCV 2024
[pdf] [bibtex] [code]
Online Continual Learning for Interactive Instruction Following Agents
Byeonghwi Kim*, Minhyuk Seo*, Jonghyun Choi
ICLR 2024
[pdf] [bibtex] [code]
Context-Aware Planning and Environment-Aware Memory for Instruction Following
Embodied Agents
Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim, Cheolhong Mim, Jonghyun Choi
ICCV 2023
🏆 1st Place in Generalist Language Grounding Agents Challenge (CVPRW'23) 🏆
[pdf] [bibtex] [code]
Multi-Level Compositional Reasoning for Interactive Instruction Following
Suvaansh Bhambri*, Byeonghwi Kim*, Jonghyun Choi
AAAI 2023 (Oral)
[pdf] [bibtex] [code]
Factorizing Perception and Policy for Interactive Instruction Following
(Prev: MOCA: A Modular Object-Centric Approach for Interactive Instruction Following)
Kunal Pratap Singh*, Suvaansh Bhambri*, Byeonghwi Kim*, Roozbeh Mottaghi, Jonghyun Choi
ICCV 2021
🏆 2nd Place in ALFRED Challenge (ECCVW'20) 🏆
[pdf] [bibtex] [code]
Agent with the Big Picture: Perceiving Surroundings for Interactive Instruction Following
Byeonghwi Kim, Suvaansh Bhambri, Kunal Pratap Singh, Roozbeh Mottaghi, Jonghyun Choi
Embodied AI Workshop @ CVPR 2021
🏆 2nd Place in ALFRED Challenge (CVPRW'21) 🏆
[pdf] [bibtex] [code]
    Selected Honors and Awards
Youlchon AI Star Scholarship (2025)
Nongshim Youlchon Foundation & SNU AI Institute
1st Place in Generalist Language Grounding Agents Challenge
Embodied AI Workshop @ CVPR 2023
ECLAIR: Event-Cognizant Language Interaction Robots
2st Place in ALFRED Challenge
Embodied AI Workshop @ CVPR 2021
Agent with the Big Picture: Perceiving Surroundings for Interactive Instruction Following
2st Place in ALFRED Challenge
Embodied Vision, Actions & Language Workshop @ ECCV 2020
Improving Mask Prediction for Long Horizon Instruction Following
    Academic Services
  • Reviewer / Program Committee Member
      • - Machine Learning: ICLR (2024-2026), ICML (2024-2026), ICML Position Paper Track (2025), NeurIPS (2023-2024), NeurIPS Datasets & Benchmarks Track (2025), NeurIPS Position Paper Track (2025), AISTATS (2025-2026), AAAI (2024-2026)
      - Computer Vision: IEEE TPAMI (2024-2025), IEEE TCSVT (2025), CVPR (2023-2026), ICCV (2025), ECCV (2024-2026), WACV (2023-2026), BMVC (2025), ACM MM (2025), ACM MM Datasets Track (2025), ACM MMAsia (2025)
      - Robotics: IEEE RA-L (2025), ICRA (2022, 2025), IROS (2025), CoRL (2025), RO-MAN (2024-2025)

This template is from Jon Barron.