AI RESEARCH
Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
arXiv CS.LG
•
ArXi:2605.16863v1 Announce Type: cross Compositional diffusion models offer a promising route to long-horizon planning by denoising multiple overlapping sub-trajectories while ensuring that together they constitute a global solution. However, enforcing local behavior over long chains is often insufficient for a coherent global structure to emerge. Recent works tackle this limitation through intrinsic search, which explores multiple paths during the denoising process.