Donghu Kim
6 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (6) π Renaissance Researcher (5) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(14)
Conferences
ICML (3)
EMNLP (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
unsupervised learning
(1)
reinforcement learning
(1)
domain adaptation
(1)
knowledge distillation
(1)
dialogue generation
(1)
behavior cloning
(1)
continuous control
(1)
skill discovery
(1)
reward function
(1)
unsupervised skill discovery
(1)
reward shaping
(1)
instruction learning
(1)
hierarchical search
(1)
dialogue system
(1)
language agent
(1)
large language model
(1)
token consumption
(1)
instruction video
(1)
Papers
Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information
EMNLP 2025
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
ICLR 2025
Hyperspherical Normalization for Scalable Deep Reinforcement Learning
ICML 2025
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
NIPS 2024
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
ICML 2024
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
ICML 2024