Skip to yearly menu bar Skip to main content


Poster

PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding

Xuesong Nie · Haoyuan Jin · Yunfeng Yan · Xi Chen · Zhihang Zhu · Donglian Qi

Arch 4A-E Poster #343
[ ] [ Paper PDF ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract:

Predictive learning models, which aim to predict future frames based on past observations, are crucial to constructing world models. These models need to maintain low-level consistency and capture high-level dynamics in unannotated spatiotemporal data. Transitioning from frame-wise to token-wise prediction presents a viable strategy for addressing these needs. How to improve token representation and optimize token decoding presents significant challenges. This paper introduces PredToken, a novel predictive framework that addresses these issues by decoupling space-time tokens into distinct components for iterative cascaded decoding. Concretely, we first design a "decomposition, quantization, and reconstruction" schema based on VQGAN to improve the token representation. This scheme disentangles low- and high-frequency representations and employs a dimension-aware quantization model, allowing more low-level details to be preserved. Building on this, we present a "coarse-to-fine iterative decoding" method. It leverages dynamic soft decoding to refine coarse tokens and static soft decoding for fine tokens, enabling more high-level dynamics to be captured. These designs make PredToken produce high-quality predictions. Extensive experiments demonstrate the superiority of our method on various real-world spatiotemporal predictive benchmarks. Furthermore, PredToken can also be extended to other visual generative tasks to yield realistic outcomes.

Chat is not available.