Kinam Kim

Ph.D. Student · KAIST AI

I am a Ph.D. student at KAIST AI, advised by Prof. Jaegul Choo. I am currently a research intern at NVIDIA, previously at Microsoft Research Asia.

My research is on robot foundation models: Vision-Language-Action (VLA) models and world models built on video generative priors. I work on what it takes to make them run on real robots, from reinforcement learning and zero-shot sim-to-real transfer to generating dexterous manipulation data at scale without teleoperation.

If you have any questions or suggestions, please feel free to contact me via email (kinamplify@kaist.ac.kr)!

kinamplify@kaist.ac.kr Scholar GitHub CV

News

• Sep 2026 🎉 Object-Centric Residual RL accepted to CoRL 2026. New
• Jul 2026 🏆 FlashSAC received the Outstanding Paper Award at RSS 2026. New
• Feb 2026 🎉 EgoX accepted to CVPR 2026.
• Jan 2026 🎉 ACG accepted to ICRA 2026.
• Sep 2025 🎉 TIC-FT accepted to NeurIPS 2025.
• Feb 2025 🎉 STG accepted to CVPR 2025.

Experience

• 
  NVIDIA

  Research Intern

  2026.07 – Now
• 
  Microsoft Research Asia

  Research Intern

  2026.02 – 2026.07

Publications

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Jaegul Choo, Yasuyuki Matsushita

CoRL 2026

Work done during an internship at Microsoft Research Asia

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

Donghu Kim*, Youngdo Lee*, Minho Park, Kinam Kim, I Made Aswin Nahendra, Takuma Seno, Sehee Min, Daniel Palenicek, Florian Vogt, Danica Kragic, Jan Peters, Jaegul Choo, Hojoon Lee (* equal contribution)

RSS 2026

Outstanding Paper Award

EgoX: Egocentric Video Generation from a Single Exocentric Video

Taewoong Kang*, Kinam Kim*, Dohyeon Kim*, Minho Park, Junha Hyung, Jaegul Choo (* equal contribution)

CVPR 2026

ACG: Action Coherence Guidance for Flow-based VLA Models

Minho Park*, Kinam Kim*, Junha Hyung, Hyojin Jang, Hoiyeong Jin, Jooyeol Yun, Hojoon Lee, Jaegul Choo (* equal contribution)

ICRA 2026

Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models

Kinam Kim*, Junha Hyung*, Jaegul Choo (* equal contribution)

NeurIPS 2025

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Junha Hyung*, Kinam Kim*, Susung Hong, Min-Jung Kim, Jaegul Choo (* equal contribution)

CVPR 2025

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models

Sungwon Hwang*, Hyojin Jang*, Kinam Kim, Minho Park, Jaegul Choo (* equal contribution)

arXiv 2025

Overcoming Camera-Facing Gaze Bias in EG3D Scene Generation

Kinam Kim, Juhyun Lee, Youngdo Lee

arXiv 2023

Education

• Ph.D. Student @ Korea Advanced Institute of Science & Technology (KAIST)
  • KAIST AI (Advisor: Prof. Jaegul Choo)
  • 2025.02 – Present
• B.S. at Korea Advanced Institute of Science & Technology (KAIST)
  • School of Computing
  • 2019.03 – 2024.02