MS student, Korea Advanced Institute of Science & Technology
2 papers at NeurIPS 2025
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.
