FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PoseFM is the first method to reformulate monocular frame-to-frame visual odometry as a flow-matching generative model that predicts camera pose distributions for built-in uncertainty.
citing papers explorer
-
FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
-
PoseFM: Relative Camera Pose Estimation Through Flow Matching
PoseFM is the first method to reformulate monocular frame-to-frame visual odometry as a flow-matching generative model that predicts camera pose distributions for built-in uncertainty.