Skip to main content
Search

# Latent Tokenizer

2 related articles

Subscribe to updates
  1. arXiv

    Latent-Foresight jointly learns a latent tokenizer and a flow-based dynamics model end-to-end, consistently outperforming two-stage baselines across future scene understanding tasks

    The work proposes Latent-Foresight, an end-to-end framework that jointly learns a latent tokenizer and a flow-based generative dynamics model, explicitly shaping the representation to support temporal predictability, with key design choices that prevent latent collapse and align reconstruction with generative objectives; experiments report more temporally coherent latent representations and consistent gains over two-stage baselines across multiple future scene understanding tasks and prediction horizons, while eliminating separate training stages, including during high-resolution adaptation.

    Efstathios Karypidis（First author）
    Latent-ForesightLatent TokenizerFlow-based Generative Dynamics ModelLatent World Model
  2. arXiv

    Latent-Foresight jointly trains a tokenizer and a flow-matching predictor, consistently beating two-stage baselines on future scene understanding in Cityscapes and nuScenes

    The work proposes Latent-Foresight, an end-to-end framework that jointly learns a VFM feature tokenizer and a flow-based generative dynamics model, using stop-gradient, latent normalization, a denoised-latent reconstruction loss and a noise schedule to prevent latent collapse, and it consistently outperforms two-stage baselines across multiple future scene understanding tasks and prediction horizons on Cityscapes, nuScenes and Kubric while eliminating separate training stages, including during high-resolution adaptation.

    Efstathios Karypidis（First author）
    Latent-ForesightFlow MatchingWorld ModelLatent TokenizerVision Foundation Models

You’re all caught up