AI RESEARCH
WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation
arXiv CS.CV
•
ArXi:2603.15132v1 Announce Type: new While recent Flow Matching models avoid the reconstruction bottlenecks of latent autoencoders by operating directly in pixel space, the lack of semantic continuity in the pixel manifold severely intertwines optimal transport paths. This induces severe trajectory conflicts near intersections, yielding sub-optimal solutions. Rather than bypassing this issue via information-lossy latent representations, we directly untangle the pixel-space trajectories by proposing Waypoint Diffusion Transformers (WiT.