Profiles2020-2026
Juho Lee
Kim Jaechul Graduate School of AI, KAIST
51Papers
28Last author
45Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers51
- From Drift to Coherence: Stabilizing Beliefs in LLMsAuthor 5 of 5ICML 2026 · 2 citations
- Stochastic Optimal Control for Continuous-Time fMRI Representation LearningAuthor 7 of 8ICLR 2026 · 2 citations
- ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person DetectionAuthor 8 of 9ICLR 2026 · 1 citation
- Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural NetworksAuthor 2 of 2ICML 2026 · 1 citation
- Soft Equivariance Regularization for Invariant Self-Supervised LearningAuthor 5 of 6ICLR 2026 · 1 citation
- Confidence is Not Universal: Task-Dependent Calibration and Emergent Behavior in LLMsAuthor 5 of 6ICML 2026
- OCNR: Stabilizing Self-Play by Mitigating Iteration-Collapse With One-Class Novelty RewardsAuthor 4 of 4ICML 2026
- Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented GenerationAuthor 5 of 5NeurIPS 2025 · 5 citations
- SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language ModelsAuthor 7 of 12ACL Findings 2025 · 3 citations
- Axial Neural Networks for Dimension-Free Foundation ModelsAuthor 5 of 5NeurIPS 2025 · 1 citation
- Test Time Scaling for Neural ProcessesAuthor 6 of 6NeurIPS 2025 · 1 citation
- Active Learning with Selective Time-Step Acquisition for PDEsAuthor 4 of 4ICML 2025
- Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time SeriesAuthor 3 of 3ICLR 2025
- Ensemble Distribution Distillation via Flow MatchingAuthor 5 of 5ICML 2025
- HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsAuthor 8 of 10ICLR 2025
- PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMsAuthor 5 of 5NeurIPS 2025
- Parameter Expanded Stochastic Gradient Markov Chain Monte CarloAuthor 5 of 5ICLR 2025
- Variational Bayesian Pseudo-CoresetAuthor 3 of 3ICLR 2025
- Stochastic Optimal Control for Diffusion Bridges in Function SpacesAuthor 4 of 4NeurIPS 2024 · 20 citations
- Learning Infinitesimal Generators of Continuous Symmetries from DataAuthor 3 of 3NeurIPS 2024 · 18 citations
- Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text GuidanceAuthor 3 of 4ICLR 2024 · 15 citations
- Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic GraphsAuthor 2 of 3AAAI 2024 · 11 citations
- A Simple Early Exiting Framework for Accelerated Sampling in Diffusion ModelsAuthor 7 of 7ICML 2024 · 10 citations
- Self-Supervised Dataset Distillation for Transfer LearningAuthor 5 of 6ICLR 2024 · 9 citations
- Enhancing Transfer Learning with Flexible Nonparametric Posterior SamplingAuthor 4 of 4ICLR 2024 · 7 citations
- Sparse Weight Averaging with Multiple Particles for Iterative Magnitude PruningAuthor 4 of 6ICLR 2024 · 4 citations
- Ex Uno Pluria: Insights on Ensembling in Low Precision Number SystemsAuthor 2 of 2NeurIPS 2024 · 2 citations
- Fast Ensembling with Diffusion Schrödinger BridgeAuthor 3 of 3ICLR 2024 · 2 citations
- Learning to Explore for Stochastic Gradient MCMCAuthor 4 of 4ICML 2024 · 2 citations
- Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-ShiftsAuthor 4 of 4ICML 2024 · 2 citations
Showing the 30 most recent indexed papers.
