Skip to content

Author

Ž. Kereta

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control

This framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control, forming coordination as a stochastic optimal control problem.

Riccardo Barbano, Vincent Pauline, Run-Chang Li et al. · 0 citations

Trajectory Stitching for Solving Inverse Problems with Flow-Based Models

MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code, is proposed, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code and reduces memory consumption while improving reconstruction quality.

Alexander Denker, Moshe Eliasof, Ž. Kereta et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.