← Search

Zhihang Zhu

2 accepted papers

2024

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

CVPR 2024poster

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 predi…

Cited by 1SourcePDFScholar
2024

Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations

AAAI 2024technical

Spatiotemporal predictive learning is a paradigm that empowers models to learn spatial and temporal patterns by predicting future frames from past frames in an unsupervised manner. This method typically uses recurrent units to capture long-term dependencies, but these units often come with high comp…