DEFAR: Mitigating Exposure Bias in Flow Matching

Researchers propose DEFAR, a method to mitigate exposure bias in Flow Matching by dynamically simulating inference during training, using directional and frequency rectification without external heuristics.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. BenchmarkJun 26, 2026, 04:14 PM 84%

   DEFAR framework introduced to dynamically rectify exposure bias in Flow Matching via directional and frequency adaptation.

   Researchers propose DEFAR, a method to mitigate exposure bias in Flow Matching by dynamically simulating inference during training, using directional and frequency rectification without external heuristics.

   Read the full story →