no code implementations • 13 Feb 2025 • Junsu Kim, Jaeyeon Kim, Ernest K. Ryu
Low-rank adaptation (LoRA) has become a standard approach for fine-tuning large foundation models.
1 code implementation • 28 Jan 2025 • Yoojin Jang, Junsu Kim, Hayeon Kim, Eun-ki Lee, Eun-Sol Kim, Seungryul Baek, Jaejun Yoo
Human-object interaction (HOI) is an essential problem in artificial intelligence (AI) which aims to understand the visual world that involves complex relationships between humans and objects.
no code implementations • 27 Aug 2024 • Junsu Kim, Seohong Park, Sergey Levine
Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making.
no code implementations • 7 Aug 2024 • Junsu Kim, Junhee Lee, Ukcheol Shin, Jean Oh, Kyungdon Joo
First, in the VPZoomer module, we initially utilize VP in feature extraction to achieve information balanced feature extraction across the scene by generating a zoom-in image based on VP.
no code implementations • 11 Jun 2024 • Huiwon Jang, Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
To tackle this challenge, in this paper, we revisit the idea of stochastic video generation that learns to capture uncertainty in frame prediction and explore its effectiveness for representation learning.
no code implementations • 8 Mar 2024 • Junsu Kim, Yunhoe Ku, Jihyeon Kim, Junuk Cha, Seungryul Baek
This technique uses Vision-Language Model (VLM) to verify the correctness of pseudo ground-truths (GTs) without requiring additional model training.
no code implementations • CVPR 2024 • Junsu Kim, Hoseong Cho, Jihyeon Kim, Yihalem Yimolal Tiruneh, Seungryul Baek
In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models.
no code implementations • 14 Dec 2023 • Junsu Kim, Sumin Hong, Chanwoo Kim, Jihyeon Kim, Yihalem Yimolal Tiruneh, Jeongwan On, Jihyun Song, Sunhwa Choi, Seungryul Baek
In this paper, we introduce an effective buffer training strategy (eBTS) that creates the optimized replay buffer on object detection.
1 code implementation • 20 Mar 2023 • Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin
Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies.
1 code implementation • 5 Feb 2023 • Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel
In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation.
1 code implementation • NeurIPS 2021 • Junsu Kim, Younggyo Seo, Jinwoo Shin
In this paper, we present HIerarchical reinforcement learning Guided by Landmarks (HIGL), a novel framework for training a high-level policy with a reduced action space guided by landmarks, i. e., promising states to explore.
Efficient Exploration
Hierarchical Reinforcement Learning
+3
no code implementations • 29 Sep 2021 • Kyunghwan Son, Junsu Kim, Yung Yi, Jinwoo Shin
Although these two sources are both important factors for learning robust policies of agents, prior works do not separate them or deal with only a single risk source, which could lead to suboptimal equilibria.
Ranked #1 on
SMAC+
on Off_Near_parallel
1 code implementation • 9 Jun 2021 • Junsu Kim, Sungsoo Ahn, Hankook Lee, Jinwoo Shin
Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself.
Ranked #4 on
Multi-step retrosynthesis
on USPTO-190
2 code implementations • NeurIPS 2020 • Sungsoo Ahn, Junsu Kim, Hankook Lee, Jinwoo Shin
De novo molecular design attempts to search over the chemical space for molecules with the desired property.