Donghoon Kim
4 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(12)
Conferences
ACL (1)
EMNLP (1)
ICLR (1)
IJCAI (1)
Top co-authors
Keywords
representation learning
(1)
offline reinforcement learning
(1)
vision language model
(1)
skill abstraction
(1)
long-horizon planning
(1)
generative agent
(1)
prefix tuning
(1)
parameter efficient fine tuning
(1)
social simulation
(1)
hierarchical policy
(1)
multimodal safety
(1)
goal-conditioned policy learning
(1)
plan revision
(1)
visual overtrust
(1)
Papers
Multimodal Safety Evaluation in Generative Agent Social Simulations
ACL 2026
Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models
ICLR 2025
Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
EMNLP 2024
Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
IJCAI 2024