"au:"Seokhun Ju"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Seokhun Ju"" — arXiv2 Search

Showing 1–4 of 4 results

/ Date/ Name

Feb 3, 2026MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction May 6, 2025Policy-labeled Preference Learning: Is Preference Enough for RLHF?Oct 31, 2025Learning Generalizable Visuomotor Policy through Dynamics-Alignment Jul 31, 2024Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation