Md Raihan Khan

Md Raihan Khan

Lecturer in EEE (North Western University) & B.Sc. graduate (KUET). Efficient, geometry-aware deep learning: generative modeling, optimal transport, and neural signals.

Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching

Published in Third IEEE International Conference on Computing, Applications and Systems (ICCAS) — under review, 2026, 2026

This work introduces difficulty-calibrated interpolation paths for conditional flow matching, adapting the interpolation/transport schedule to sample difficulty to improve training and sampling behavior in flow-based generative models.

Recommended citation: Airin Akter Tania and Md Raihan Khan, "Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching," IEEE ICCAS 2026 (under review).