Scholar
Dong Ki Kim
Google Scholar ID: Yl_3akYAAAAJ
Field AI (previously: MIT, LG AI Research)
Citations & Impact
Citations
927
H-index
16
i10-index
18
Publications
20
Co-authors
51
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Recipient of the Kwanjeong Educational Foundation Fellowship.
- Published 'AutoGuide: Automated Generation and Selection of State-Aware Guidelines for Large Language Model Agents' at NeurIPS 2024.
- Published 'Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Agents' at EMNLP 2024.
- Published 'Reasoning about Action Preconditions with Programs' at NAACL 2024.
- Published 'SkillAct: Using Skill Abstractions Improves LLM Agents' at ICML 2024 Workshop.
- Published 'MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning' at NeurIPS 2023 Workshop (spotlight).
- Published 'TOD-Flow: Modeling the Structure of Task-Oriented Dialogues' at EMNLP 2023.
- Published 'Learning Higher Order Skills that Efficiently Compose' at ICML 2023 Workshop.
- Published 'Game-Theoretical Perspectives on Active Equilibria' at CoRL 2022 Workshop (oral presentation).
- Published 'Influencing Long-Term Behavior in Multiagent Reinforcement Learning' at NeurIPS 2022.
- Published 'ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation' at ICRA 2022.
- Presented an earlier version of work at ICLR 2022 Workshop (spotlight).
Research Experience
- Currently Staff Research Scientist at Field AI, collaborating with Dr. Shayegan Omidshafiei and Dr. Ali Agha on field foundation models.
- Formerly Research Scientist at LG AI Research, working with Prof. Honglak Lee on LLM agents for web navigation.
- Conducted multiagent reinforcement learning research during Ph.D. at MIT.
- Worked on computer vision research as an undergraduate at Cornell.
- Completed research visits at CMU-RI and TTIC.
