PhD student, Korea Advanced Institute of Science and Technology
3 papers at NeurIPS 2025
We introduce the challenge of adaptive inference-time scaling—dynamically adjusting computational effort during inference—and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework.
C-MCTD enables diffusion planners to generate plans 10× longer than training examples by systematically stitching together shorter plans through tree search.
Fast Monte Carlo Tree Diffusion (Fast-MCTD) achieves up to 100× speedup over MCTD through parallel rollouts and sparse trajectory planning, maintaining strong performance in complex long-horizon tasks while being computationally efficient.
