Distribution Recovery in Compact Diffusion World Models via Conditioned Frame Interpolation
Keywords: Diffusion Models, World Models, Distribution Recovery, Frame Interpolation, Out-of-Distribution Detection, Neural Game Engines, Generative Models
TL;DR: We extend compact diffusion world models with frame interpolation capabilities to enable distribution recovery during generation, providing an alternative to massive model scaling for achieving long-horizon world exploration.
Abstract: This early proof-of-concept explores addressing distribution drift in diffusion-based world models without requiring massive model scale or constrained environments. We explore a dual-purpose training approach where models learn both autoregressive world generation and frame interpolation capabilities. This is combined with an out-of-distribution detection mechanism that, upon detecting drift or degradation, samples appropriate target frames and conditions the model to interpolate toward them, effectively pulling generation back into the learned distribution. We demonstrate this approach's potential through initial experiments and discuss practical considerations for target frame sampling and interpolation training. This early work presents an alternative path toward enabling longer world exploration with smaller models.
Submission Number: 65
Loading