AIConfPaper
← Search

SeungJae Lee

19 accepted papers

2026

LVI-Q: Robust LiDAR-Visual-Inertial-Kinematic Odometry for Quadruped Robots Using Tightly-Coupled and Efficient Alternating Optimization

Kevin Christiansen Marsim, Minho Oh, Byeongho Yu, Seungjae Lee, I Made Aswin Nahrendra, Hyungtae Lim +1
ICRA 2026poster

Autonomous navigation for legged robots in complex and dynamic environments relies on robust simultaneous localization and mapping (SLAM) systems to accurately map surroundings and localize the robot, ensuring safe and efficient operation. While prior sensor fusion-based SLAM approaches have integra…

Cited by 0Source ↗PDF ↗Scholar ↗
2026

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning

Yuanchen Ju, Yongyuan Liang, Yen-Jen Wang, Gireesh Nandiraju, Yuanliang Ju, Seungjae Lee +4
ICLR 2026oral

Mobile manipulators in households must both navigate and manipulate. This requires a compact, semantically rich scene representation that captures where objects are, how they function, and which parts are actionable. Scene graphs are a natural choice, yet prior work often separates spatial and funct…

Cited by 0Source ↗code ↗Scholar ↗
2026

SE(3)-LIO: Smooth IMU Propagation with Jointly Distributed Poses on SE(3) Manifold for Accurate and Robust LiDAR-Inertial Odometry

Gunhee Shin, Seungjae Lee, Jei Kong, Young-Woo Seo, Hyun Myung
ICRA 2026poster

In estimating odometry accurately, an inertial measurement unit (IMU) is widely used owing to its high-rate measurements, which can be utilized to obtain motion information through IMU propagation. In this paper, we address the limitations of existing IMU propagation methods in terms of motion predi…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2026

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control

Priyansh Bhatnagar, Ashkan Moradifirouzabadi, Se-Hyun Yang, SeungJae Lee, Jungwook Choi, Mingu Kang
ICML 2026spotlight

Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy. However, prior methods rely on fixed or heuristic rank selection and struggle to achieve aggressive compression with minimal accuracy degradation. We propose STAR-KV, an ad…

Cited by 0Source ↗Scholar ↗
2026

Tailored ViT Slimming: Budget-Aware Multi-Dimensional Sparsity Regularization for Vision Transformers Pruning (Student Abstract)

Suwoong Lee, Seungjae Lee, Yunho Jeon, Junmo Kim
AAAI 2026technical

We propose Tailored ViT Slimming (TVS), a budget-aware multi-dimensional pruning framework for Vision Transformers. TVS injects learnable masks into MHSA and MLP modules and applies adaptive non-convex sparsity regularization to achieve maximal utilization of parameters under strict module-wise budg

Cited by 0Source ↗PDF ↗Scholar ↗
2026

TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos

Seungjae Lee, Yoonkyo Jung, Inkook Chun, Yao-Chih Lee, Zikui Cai, Hongjia Huang +5
CVPR 2026

Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments---humans and different robots---are abundant, differences in embodiment, camera, and environment hinder their direct use. We address the small-data

Cited by 0Source ↗code ↗Scholar ↗
2025

Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy

Inkook Chun, Seungjae Lee, Michael Samuel Albergo, Saining Xie, Eric Vanden-Eijnden
NeurIPS 2025poster

Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation-learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task complexity, leading to computational inefficiency for simple…

Cited by 0Source ↗Scholar ↗
2025

Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models

Seungjae Lee, Daniel Ekpo, Haowen Liu, Furong Huang, Abhinav Shrivastava, Jia-Bin Huang
CoRL 2025poster

Exploration is key for general-purpose robotic learning, particularly in open-ended environments where explicit guidance or task-specific feedback is limited. Vision-language models (VLMs), which can reason about object semantics, spatial relations, and potential outcomes, offer a promising foundati…

Cited by 0Source ↗Scholar ↗
2025

LVI-Q: Robust LiDAR-Visual-Inertial-Kinematic Odometry for Quadruped Robots Using Tightly-Coupled and Efficient Alternating Optimization

Kevin Christiansen Marsim, Minho Oh, Byeongho Yu, Seungjae Lee, I Made Aswin Nahrendra, Hyungtae Lim +1
RA-L 2025

Autonomous navigation for legged robots in complex and dynamic environments relies on robust simultaneous localization and mapping (SLAM) systems to accurately map surroundings and localize the robot, ensuring safe and efficient operation. While prior sensor fusion-based SLAM approaches have integra

Cited by 3Source ↗Scholar ↗
2025

Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments

Haritheja Etukuru, Norihito Naka, Zijin Hu, Seungjae Lee, Julian Mehu, Aaron Edsinger +4
ICRA 2025

Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given sufficient training data in an environment, robot policies can generalize to demonstrated vari

Cited by 49Source ↗code ↗Scholar ↗
2024

Behavior Generation with Latent Actions

Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto
ICML 2024spotlight

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision-making. Unlike language or image generation, decision-making requires modeling actions – continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated so…

Cited by 57Source ↗PDF ↗code ↗Scholar ↗
2023

CQM: Curriculum Reinforcement Learning with a Quantized World Model

Seungjae Lee, Daesol Cho, Jonghae Park, H. Jin Kim
NeurIPS 2023poster

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a high-dimensional space. Thus, they usually rely on manually spe…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement

Daesol Cho, Seungjae Lee, H. Jin Kim
NeurIPS 2023poster

Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards. To tackle these challenges, this work proposes a new approach for curriculum RL c…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation

Daesol Cho, Seungjae Lee, H. Jin Kim
ICLR 2023top-25%

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a sequence of surrogate tasks, shows reasonable results, most…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator

Nakkwan Choi, Seungjae Lee, Yongsik Lee, Seungjoon Yang
CVPR 2023poster

This work presents the restoration of drawings of wooden built heritage. Hand-drawn drawings contain the most important original information but are often severely degraded over time. A novel restoration method based on the vector quantized variational autoencoders is presented. Latent space represe…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning

Seungjae Lee, Jigang Kim, Inkyu Jang, H. Jin Kim
NeurIPS 2022accept

Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction. However, previous HRL algorithms often suffer from serious data inefficiency as environments get large. The extended components, $i.e.$, goal space and length of episodes,…

Cited by 20Source ↗PDF ↗Scholar ↗
2022

Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud

Seungjae Lee, Hyungtae Lim, Hyun Myung
IROS 2022poster

In the field of 3D perception using 3D LiDAR sensors, ground segmentation is an essential task for various purposes, such as traversable area detection and object recognition. Under these circumstances, several ground segmentation methods have been proposed. However, some limitations are still encou…

Cited by 155Source ↗code ↗Scholar ↗
2021

Robust and Recursively Feasible Real-Time Trajectory Planning in Unknown Environments

Inkyu Jang, Dongjae Lee, Seungjae Lee, H. Jin Kim
IROS 2021poster

Motion planners for mobile robots in unknown environments face the challenge of simultaneously maintaining both robustness against unmodeled uncertainties and persistent feasibility of the trajectory-finding problem. That is, while dealing with uncertainties, a motion planner must update its traject…

Cited by 3Source ↗Scholar ↗