RobotUse: Allocating Computation, Context, and Decisions
Junhoo Lee, Injun Baek, Seungyeon Kim, Suhyun Jeon, Minkyu Kim, Baekseung Kim, Nojun Kwak
arXiv preprint arXiv:2610.04929, 2026.
Recursive Harness Distillation across Agents for Robot Manipulation
Seungyeon Kim, Junhoo Lee, Minkyu Kim, Baekseung Kim, Nojun Kwak
arXiv preprint arXiv:2609.33378, 2026.
ACRO: Actor–Critic Rollout Orchestration
Junhoo Lee, Seungyeon Kim, Baekseung Kim, Minkyu Kim, Suhyun Jeon, Jimyeong Kim, Nojun Kwak
Preprint, 2026.
Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
Junhoo Lee, Hyeonjin Kim, Sangbum Han, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2026.
Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
Junhoo Lee*, Baekseung Kim*, Seungyeon Kim, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2026.
ManiFusion: Unlocking High-Throughput Generation via Superposition in Manifold Space
Minkyu Kim, Baekseung Kim, Junhoo Lee, Jangho Kim, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2026.
Unlocking the Potential of Diffusion Language Models through Template Infilling
Junhoo Lee, Seungyeon Kim, Nojun Kwak
Annual Meeting of the Association for Computational Linguistics (ACL), 2026. Long Paper · Oral Presentation
CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
Junhoo Lee, Mijin Koo, Nojun Kwak
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability
Wonguen Cho, Junhoo Lee, Nojun Kwak
The 1st Workshop on Physical World AI: Geometry, Characteristics, and Multimodal Sensing at the Conference on Neural Information Processing Systems (NeurIPS), 2026.
Completion Aware Guidance for World Action Models
Seungyeon Kim, Junhoo Lee, Baekseung Kim, Minkyu Kim, Nojun Kwak
Robotics World Modeling Workshop at the Conference on Neural Information Processing Systems (NeurIPS), 2026.
Point-to-Point: Sparse Motion Guidance for Controllable Video Editing
Yeji Song, Jaehyun Lee, Mijin Koo, Junhoo Lee, Nojun Kwak
The 4th AI for Visual Arts Workshop at the European Conference on Computer Vision (AI4VA, ECCV Workshops), 2026.
End-to-End Multi-Entity Customization
Wonhark Park*, Jaehyun Lee*, Wonsik Shin, Junhoo Lee, Nojun Kwak
IET Image Processing, 2026.
Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
Dongkwan Lee*, Junhoo Lee*, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2025.
What's Making That Sound Right Now? Video-centric Audio-Visual Localization
Hahyeon Choi, Junhoo Lee, Nojun Kwak
The IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
The Role of Teacher Calibration in Knowledge Distillation
Suyoung Kim, Seonguk Park, Junhoo Lee, Nojun Kwak
IEEE Access, 2025.
Deep Support Vectors
Junhoo Lee, Hyunho Lee, Kyomin Hwang, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2024.
Any-Way Meta Learning
Junhoo Lee, Yearim Kim, Hyunho Lee, Nojun Kwak
The AAAI Conference on Artificial Intelligence (AAAI), 2024.
Do Not Think About Pink Elephant!
Kyomin Hwang*, Suyoung Kim*, Junhoo Lee*, Nojun Kwak
The IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops, Responsible Generative AI), 2024.
Coreset Selection for Object Detection
Hojun Lee, Suyoung Kim, Junhoo Lee, Jaeyoung Yoo, Nojun Kwak
The IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops, Dataset Distillation), 2024.
Practical Dataset Distillation Based on Deep Support Vectors
Hyunho Lee, Junhoo Lee, Nojun Kwak
The European Conference on Computer Vision Workshops (ECCV Workshops, Dataset Distillation Challenge), 2024.
SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning
Junhoo Lee, Jayeon Yoo, Nojun Kwak
The Conference on Neural Information Processing Systems (NeurIPS), 2023.