Donghu Kim

14 papers A* 5Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff.
CoRR
Isaac Han, Sangyeon Park, Seungwon Oh, Donghu Kim, Hojoon Lee, Kyung-Joong Kim
2025 — conf
Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information.
EMNLP (Industry Track)
Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo
2025 J jnl
Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information.
CoRR
Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo
2025 J jnl
Dynamic Mixture of Experts Against Severe Distribution Shifts.
CoRR
Donghu Kim
2025 A* conf
Hyperspherical Normalization for Scalable Deep Reinforcement Learning.
ICML
Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo
2025 J jnl
Hyperspherical Normalization for Scalable Deep Reinforcement Learning.
CoRR
Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo
2025 A* conf
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning.
ICLR
Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone, Takuma Seno
2024 A* conf
Do's and Don'ts: Learning Desirable Skills with Instruction Videos.
NeurIPS
Hyunseung Kim, Byungkun Lee, Hojoon Lee, Dongyoon Hwang, Donghu Kim, Jaegul Choo
2024 J jnl
Do's and Don'ts: Learning Desirable Skills with Instruction Videos.
CoRR
Hyunseung Kim, Byungkun Lee, Hojoon Lee, Dongyoon Hwang, Donghu Kim, Jaegul Choo
2024 A* conf
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning.
ICML
Donghu Kim, Hojoon Lee, Kyungmin Lee, Dongyoon Hwang, Jaegul Choo
2024 J jnl
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning.
CoRR
Donghu Kim, Hojoon Lee, Kyungmin Lee, Dongyoon Hwang, Jaegul Choo
2024 J jnl
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning.
CoRR
Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone, Takuma Seno
2024 A* conf
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks.
ICML
Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Donghu Kim, Dugki Min, Jaegul Choo, Clare Lyle
2024 J jnl
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks.
CoRR
Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Donghu Kim, Dugki Min, Jaegul Choo, Clare Lyle