Skip to content
View cheesss's full-sized avatar
馃幆
Focusing
馃幆
Focusing
3 followers · 11 following

Block or report cheesss

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don鈥檛 include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user鈥檚 behavior. Learn more about reporting abuse.

Report abuse
cheesss/README.md

Hyeonjun Cho

Undergraduate researcher in robot learning at Sungkyunkwan University.

I study learning-based manipulation under distribution shift, with an emphasis on imitation learning, vision-language planning, safety interventions, and recovery on real robot systems.

Research portfolio 路 Academic CV 路 Email

Selected research

Recovery-Aware LPB for RMP-Induced OOD States

Designed a recovery-aware policy bridge and evaluated it in 160 RB10 trials. The proposed method completed 146/160 trials (91.3%) in the reported intervention setting.

Project case study 路 Public research code

Grounded Language-to-Motion Planning with Memory and Gripper Constraints

Integrated visual grounding, execution memory, and gripper-aware grasp selection. Success improved from 9/15 to 12/15 in the defined evaluation.

Project case study 路 Research fork

LLM-Based Zero-Shot Trajectory Generation

Implemented structured waypoint generation, collision-aware validation, simulation experiments, and early RB10 integration.

Project case study 路 Research fork

Research tools

Python 路 PyTorch 路 ROS 2 路 Diffusion Policy 路 Vision-Language Models 路 PyBullet 路 RB10

Current status

  • Recovery-aware LPB manuscript in preparation
  • Open to graduate research opportunities in robot learning and Physical AI

Pinned Loading

  1. ollama ollama Public

    Forked from ollama/ollama

    Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    Go 2

  2. recovery-aware-lpb-rb10 recovery-aware-lpb-rb10 Public

    Recovery-aware policy bridge for RMP-induced OOD states on an RB10 manipulator.

    Python 1

  3. lattice-current lattice-current Public

    Independent research fork for real-time global intelligence, AI-assisted analysis, ontology graphs, historical replay, and backtesting.

    JavaScript 2