Hojoon Lee
10 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (17) π Conference Polyglot (4) π Cross-Pollinator (6)
π
Renaissance Researcher
(6)
π
Keyword Champion
π€
Dynamic Duo
(10)
π
Century Club
(10)
Conferences
ICML (5)
NIPS (3)
EMNLP (1)
ICLR (1)
Top co-authors
Keywords
unsupervised skill discovery
(2)
continuous control
(2)
reinforcement learning
(2)
behavior cloning
(1)
skill discovery
(1)
reward function
(1)
unsupervised representation learning
(1)
predictive representation
(1)
latent space
(1)
skill learning
(1)
reward shaping
(1)
instruction learning
(1)
gradient propagation
(1)
feature decorrelation
(1)
llm evaluator
(1)
pairwise evaluation
(1)
temporal prediction
(1)
representational collapse
(1)
adversarial benchmark
(1)
instruction video
(1)
Papers
The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators
EMNLP 2025
Hyperspherical Normalization for Scalable Deep Reinforcement Learning
ICML 2025
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
ICLR 2025
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
ICML 2024
Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
ICML 2024
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
ICML 2024
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
NIPS 2024
On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
ICML 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
NIPS 2023
Learning to Discover Skills through Guidance
NIPS 2023