CellFluxRL post-trains the CellFlux model with RL using seven biological reward functions to generate more biologically valid virtual cell images.
The algorithm adapts DiffusionNFT [48] to the source-to-target flow matching setting and replaces the generic reward with our suite of biologically grounded reward functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
CellFluxRL post-trains the CellFlux model with RL using seven biological reward functions to generate more biologically valid virtual cell images.