ConicFlow: constrained Inference-time optimal control for flow matching models
arXiv:2610.14307v1 Announce Type: new Abstract: We propose ConicFlow, which frames constrained sampling from a flow matching model at inference time as an optimal control problem that balances deviation from the pretrained trajectory against reward, subject to hard terminal constraints. We discretize this problem and adapt receding-horizon control, optimizing only a short window of the trajectory…
Read original article on cs.AI updates on arXiv.org →More in Research