277 citations · 936 across the 59 of their papers we have counts for
62 papers
Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
Chang-Hoon Jeong, Kisung Shin, Hanwool Sul +1
Context-based offline meta-reinforcement learning (COMRL) has advanced almost entirely through better task representations, which separate task identity from artifacts of the behav…
RAIN: Robotic Task Generalization with Region-Aware Interaction Networks
Seunghun Lee, Kyuhwan Shim, Yeogyeong Song +5
Existing vision-language-action (VLA) models benefit from large-scale vision-language pretraining, but tend to memorize training trajectories, limiting their ability to adapt learn…
Reward Inflation: A Healthy Stimulus for Reinforcement Learning
Ganghun Lee, Minji Kim, Minsu Lee +1
Reward serves as the primary learning signal in reinforcement learning (RL). However, while reward magnitudes are typically held fixed throughout training, their temporal modulatio…
On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition
Inwoo Hwang, Yunhyeok Kwak, Yeon-Ji Song +2
Conditional independence provides a way to understand causal relationships among the variables of interest. An underlying system may exhibit more fine-grained causal relationships…
Multimodal Anomaly Detection based on Deep Auto-Encoder for Object Slip Perception of Mobile Manipulation Robots
Youngjae Yoo, Chung-Yeon Lee, Byoung-Tak Zhang
Object slip perception is essential for mobile manipulation robots to perform manipulation tasks reliably in the dynamic real-world. Traditional approaches to robot arms' slip perc…
GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation
Junghyun Kim, Gi-Cheon Kang, Jaein Kim +2
Language-Guided Robotic Manipulation (LGRM) is a challenging task as it requires a robot to understand human instructions to manipulate everyday objects. Recent approaches in LGRM…
EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object
Hyunseo Kim, Hye Jung Yoon, Minji Kim +2
Current robotic hand manipulation narrowly operates with objects in predictable positions in limited environments. Thus, when the location of the target object deviates severely fr…
Background-aware Moment Detection for Video Moment Retrieval
Minjoon Jung, Youwon Jang, Seongho Choi +3
Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query. This task is prone to suffer the weak alignment problem innate i…
L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning
Kibeom Kim, Hyundo Lee, Min Whoo Lee +3
Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are…
Learning Geometry-aware Representations by Sketching
Hyundo Lee, Inwoo Hwang, Hyunsung Go +3
Understanding geometric concepts, such as distance and shape, is essential for understanding the real world and also for many vision tasks. To incorporate such information into a v…
SelecMix: Debiased Learning by Contradicting-pair Sampling
Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak +4
Neural networks trained with ERM (empirical risk minimization) sometimes learn unintended decision rules, in particular when their training data is biased, i.e., when training labe…
DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning
Won-Seok Choi, Dong-Sig Han, Hyundo Lee +2
In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performanc…
Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval
Minjoon Jung, Seongho Choi, Joochan Kim +2
Video corpus moment retrieval (VCMR) is the task to retrieve the most relevant video moment from a large video corpus using a natural language query. For narrative videos, e.g., dr…
SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation
Woo Suk Choi, Yu-Jung Heo, Byoung-Tak Zhang
Scene graph is structured semantic representation that can be modeled as a form of graph from images and texts. Image-based scene graph generation research has been actively conduc…
Robust Imitation via Mirror Descent Inverse Reinforcement Learning
Dong-Sig Han, Hyunseo Kim, Hyundo Lee +2
Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often b…
Learning to Write with Coherence From Negative Examples
Seonil Son, Jaeseo Lim, Youwon Jang +2
Coherence is one of the critical factors that determine the quality of writing. We propose writing relevance (WR) training method for neural encoder-decoder natural language genera…
From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent
Ganghun Lee, Minji Kim, Minsu Lee +1
We present an automated learning framework for a robotic sketching agent that is capable of learning stroke-based rendering and motor control simultaneously. We formulate the robot…
On the Importance of Critical Period in Multi-stage Reinforcement Learning
Junseok Park, Inwoo Hwang, Min Whoo Lee +4
The initial years of an infant's life are known as the critical period, during which the overall development of learning performance is significantly impacted due to neural plastic…
Cross-Modal Alignment Learning of Vision-Language Conceptual Systems
Taehyeong Kim, Hyeonseop Song, Byoung-Tak Zhang
Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-langua…
The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
Gi-Cheon Kang, Sungdong Kim, Jin-Hwa Kim +2
Visual dialog (VisDial) is a task of answering a sequence of questions grounded in an image, using the dialog history as context. Prior work has trained the dialog agents solely on…
Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering
Yu-Jung Heo, Eun-Sol Kim, Woo Suk Choi +1
Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex question…
Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
Junseok Park, Kwanyoung Park, Hyunseok Oh +4
Critical periods are phases during which a toddler's brain develops in spurts. To promote children's cognitive development, proper guidance is critical in this stage. However, it i…
Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness
Jiseob Kim, Jihoon Lee, Byoung-Tak Zhang
Face-swapping models have been drawing attention for their compelling generation quality, but their complex architectures and loss functions often require careful tuning for succes…
Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning
Kibeom Kim, Min Whoo Lee, Yoonsung Kim +3
Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult. To solve this problem, it is…