Jaekyeom Kim
Jaekyeom Kim
LG AI Research
Verified email at - Homepage
Cited by
Cited by
Emi: Exploration with mutual information
H Kim, J Kim, Y Jeong, S Levine, HO Song
arXiv preprint arXiv:1810.01176, 2018
Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning
J Kim, H Kim, G Kim
Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020
Lipschitz-constrained unsupervised skill discovery
S Park, J Choi, J Kim, H Lee, G Kim
International Conference on Learning Representations, 2022
Unsupervised skill discovery with bottleneck option learning
J Kim, S Park, G Kim
arXiv preprint arXiv:2106.14305, 2021
Time discretization-invariant safe action repetition for policy gradient methods
S Park, J Kim, G Kim
Advances in Neural Information Processing Systems 34, 267-279, 2021
Drop-bottleneck: Learning discrete compressed representation for noise-robust exploration
J Kim, M Kim, D Woo, G Kim
arXiv preprint arXiv:2103.12300, 2021
Constrained gpi for zero-shot transfer in reinforcement learning
J Kim, S Park, G Kim
Advances in Neural Information Processing Systems 35, 4585-4597, 2022
Autoguide: Automated generation and selection of state-aware guidelines for large language model agents
Y Fu, DK Kim, J Kim, S Sohn, L Logeswaran, K Bae, H Lee
arXiv preprint arXiv:2403.08978, 2024
Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Y Zhang, M Khalifa, L Logeswaran, J Kim, M Lee, H Lee, L Wang
arXiv preprint arXiv:2404.17140, 2024
Apparatus and method with compressed neural network computation
SM Rhee, KIM Jaekyeom, G Kim, M Kim, WOO Dongyeon, HAN SeungJu
US Patent 11,868,428, 2024
Device and method with state transition linearization
M Ko, KIM Jaekyeom, P Seohong, G Kim, S Suh
US Patent App. 17/989,320, 2023
The system can't perform the operation now. Try again later.
Articles 1–11