AI RESEARCH
Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning
arXiv CS.LG
•
ArXi:2602.10420v2 Announce Type: replace Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this paradigm to binary manifolds, a fundamental setting for generative modeling of discrete data.