HYUNSEUNG KIM
6 papers · 2023–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(16)
Venues
Top co-authors
Research topics
Deep Learning
(4)
Reinforcement Learning
(4)
Methods
(4)
Artificial Intelligence
(3)
Machine Learning
(3)
Architectures
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Applications · Reinforcement Learning
(2)
Computer Vision
(1)
Robotics
(1)
Analysis
(1)
Applications · Robotics
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
sample efficiency
(2)
continuous control
(2)
unsupervised skill discovery
(2)
reinforcement learning
(2)
loss landscape
(1)
behavior cloning
(1)
skill discovery
(1)
reward function
(1)
generalization
(1)
skill learning
(1)
reward shaping
(1)
instruction learning
(1)
simplicity bia
(1)
layer normalization
(1)
gradient propagation
(1)
visuomotor control
(1)
network scaling
(1)
instruction video
(1)
skill guidance
(1)
input plasticity
(1)
Papers
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
ICLR 2025
Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
ICML 2024
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
NeurIPS 2024
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
ICML 2024
Learning to Discover Skills through Guidance
NeurIPS 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
NeurIPS 2023