What is recorded here?
Compressed videos with a temporally causal discrete tokenizer and generated tokens with a text-conditioned masked transformer, combining image/text and video/text data for variable-length prompt sequences.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Masked generation, transformers and discrete autoencoders are inherited. Variable-length generation is an architectural capability, not arbitrarily long semantic/visual coherence or unlimited compute. Original2022 snapshot controls.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Ruben Villegas; Mohammad Babaeizadeh; Pieter-Jan Kindermans; Hernan Moraldo; Han Zhang; Mohammad Taghi Saffar; Santiago Castro; Julius Kunze; Dumitru Erhan
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Villegas et al.: causal video tokenization with variable-prompt generation
Compressed videos with a temporally causal discrete tokenizer and generated tokens with a text-conditioned masked transformer, combining image/text and video/text data for variable-length prompt sequences.
Scientific scope
Masked generation, transformers and discrete autoencoders are inherited. Variable-length generation is an architectural capability, not arbitrarily long semantic/visual coherence or unlimited compute. Original2022 snapshot controls.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Ruben Villegas; Mohammad Babaeizadeh; Pieter-Jan Kindermans; Hernan Moraldo; Han Zhang; Mohammad Taghi Saffar; Santiago Castro; Julius Kunze; Dumitru Erhan
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.