Papers

Filtered to representation autoencoders · clear filter

Browse by term

continual learning 10large language models 6reinforcement learning 6policy optimization 2video generation 2

Matching papers

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

9 upvotes · 15 JUL 2026 · Zhihao Xie, Junfeng Wu, Xinting Hu et al.

This paper develops a method to transform video foundation models' representations into compact, reconstruction-capable, and generation-friendly video latents, which can be used in various generative modeling tasks. Practitioners can use VideoRAE to improve the performance of their models by leveraging the semantic and spatio-temporal structure captured by the frozen video foundation encoder.