Chanyeok Choi

Hanyang University

Seoul, South Korea

angledsugar@gmail.com

I’m a graduate researcher at Hanyang University advised by Prof. Youngmoon Lee, finishing my MS in Applied Artificial Intelligence (BS in Robotics, 2022).

My current work is on critical-phase detection for vision-language-action policies — figuring out, on a per-step basis, whether a robot rollout is heading toward failure and intervening before it does. The focus is making this work zero-shot on top of frozen π₀ / π₀.₅ backbones on LIBERO manipulation benchmarks (CoRL 2026 submission).

Before this, my research moved through safety-RL and adversarial reward poisoning on multi-agent control (including taxi ride-sharing systems), human pose and segmentation for crowded scenes, and human-robot interaction for real-time computational photography (Snapbot). Earlier still I built field-deployed service robots — an auto-climbing mopping platform (ACMR) and an autonomous delivery platform (DATP) — which is where most of my intuition about real-world control and edge cases comes from.

See my publications for paper details, projects for hardware work, or my CV for the full timeline.

Publications

Preprint
Critical-Phase Detection for Vision-Language-Action Policies

Chanyeok Choi and Youngmoon Lee

Preprint, 2026

Under review at CoRL 2026

paper page code DOI BIB

We introduce a zero-shot critical-phase detector (CPD) for frozen vision-language-action policies. CPD couples a temporal-distance latent representation (TLDR) encoder with a self-supervised goal-reachability (G2) labeler, then scores each rollout step by a kernel-density log-ratio between the success and failure latent buffers. On LIBERO-Long with frozen π₀ and π₀.₅ backbones, CPD attains a leave-one-out F1 of 0.86–0.89 for trajectory-level failure detection without any task-specific reward or success label, and we prove a consistency bound between the G2 self-label and the ground-truth success predicate under mild assumptions on the latent geometry.
@article{choi2026cpd, title = {Critical-Phase Detection for Vision-Language-Action Policies}, author = {Choi, Chanyeok and Lee, Youngmoon}, journal = {Preprint}, year = {2026}, note = {Under review at CoRL 2026}, keywords = {vision-language-action, manipulation, failure detection, self-supervised learning, LIBERO} }
Humanoids
Poisoning Attacks on Multi-Agent Reinforcement Learning Systems

Chanyeok Choi, Jaehwan Cho, and Youngmoon Lee

In IEEE-RAS International Conference on Humanoid Robots (Humanoids), Late-Breaking Report, 2025

paper page code DOI BIB

We study reward-poisoning adversarial attacks on cooperative multi-agent reinforcement learning, including controllers for taxi ride-sharing fleets, and characterize the attack budgets under which policy degradation becomes observable.
@inproceedings{choi2025poisoning, title = {Poisoning Attacks on Multi-Agent Reinforcement Learning Systems}, author = {Choi, Chanyeok and Cho, Jaehwan and Lee, Youngmoon}, booktitle = {IEEE-RAS International Conference on Humanoid Robots (Humanoids), Late-Breaking Report}, year = {2025}, keywords = {multi-agent reinforcement learning, adversarial attacks, reward poisoning} }

ICPR

HAPtics: Human Action Prediction in Real-time via Pose Kinematics

Niaz Ahmad, Saif Ullah, Jawad Khan, Chanyeok Choi, and Youngmoon Lee

In International Conference on Pattern Recognition (ICPR), 2024

paper page code DOI BIB

@inproceedings{ahmad2024haptics,
  title = {{HAPtics}: Human Action Prediction in Real-time via Pose Kinematics},
  author = {Ahmad, Niaz and Ullah, Saif and Khan, Jawad and Choi, Chanyeok and Lee, Youngmoon},
  booktitle = {International Conference on Pattern Recognition (ICPR)},
  address = {Kolkata, India},
  year = {2024},
  doi = {10.1007/978-3-031-78354-8_10},
  keywords = {human pose, action prediction, vision}
}

ISLPED

Causes and Fixes of Unexpected Drone Shutoffs

Hojun Choi, Chanyeok Choi, and Youngmoon Lee

In ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2024

paper page code DOI BIB

@inproceedings{choi2024drone,
  title = {Causes and Fixes of Unexpected Drone Shutoffs},
  author = {Choi, Hojun and Choi, Chanyeok and Lee, Youngmoon},
  booktitle = {ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED)},
  year = {2024},
  doi = {10.1145/3665314.3670847},
  keywords = {drones, reliability, field robotics}
}

HRI
Snapbot: Enabling Dynamic Human-Robot Interactions for Real-Time Computational Photography

Chanyeok Choi and Youngmoon Lee

In ACM/IEEE International Conference on Human-Robot Interaction (HRI), Late-Breaking Report, 2024

paper page code DOI BIB

Snapbot is a manipulator-based photography system that frames, composes, and captures stylized portraits in real time, treating the human subject as a dynamic interaction partner rather than a static target.
@inproceedings{choi2024snapbot, title = {{Snapbot}: Enabling Dynamic Human-Robot Interactions for Real-Time Computational Photography}, author = {Choi, Chanyeok and Lee, Youngmoon}, booktitle = {ACM/IEEE International Conference on Human-Robot Interaction (HRI), Late-Breaking Report}, year = {2024}, keywords = {human-robot interaction, manipulation, computational photography} }

ICDM-W

SSK-DNN: Semantic and Sentiment Knowledge for Incremental Text Sentiment Classification

Jawad Khan, Niaz Ahmad, Chanyeok Choi, Saif Ullah, Gyu Rin Kim, and Youngmoon Lee

In IEEE ICDM Workshop on Incremental Learning (IncrLearn), 2023

paper page code DOI BIB

@inproceedings{khan2023ssk,
  title = {{SSK-DNN}: Semantic and Sentiment Knowledge for Incremental Text Sentiment Classification},
  author = {Khan, Jawad and Ahmad, Niaz and Choi, Chanyeok and Ullah, Saif and Kim, Gyu Rin and Lee, Youngmoon},
  booktitle = {IEEE ICDM Workshop on Incremental Learning (IncrLearn)},
  address = {Shanghai, China},
  year = {2023},
  keywords = {natural language processing, sentiment classification, incremental learning}
}