ElasticTok: Adaptive Tokenization for Image and Video

submited by

Style Pass

2024-10-15 06:00:04

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where too few tokens will result in overly lossy encodings, and too many tokens will result in prohibitively long sequence lengths. In this work, we introduce ElasticTok, a method that conditions on prior frames to adaptively encode a frame into a variable number of tokens. To enable this in a computationally scalable way, we propose a masking technique that drops a random number of tokens at the end of each frames’s token encoding. During inference, ElasticTok can dynamically allocate tokens when needed – more complex data can leverage more tokens, while simpler data only needs a few tokens. Our empirical evaluations on images and video demonstrate the effectiveness of our approach in efficient token usage, paving the way for future development of more powerful multimodal models, world models, and agents.

Figure 2. ElasticTok adaptively encodes image and video to variable length outputs based on the complexity of the input data. Single block uses an Encoder-Decoder pipeline with a sampled latent mask. Multi-block extends this with a Block Causal Mask to handle longer video sequences.