English

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Machine Learning 2025-12-15 v2 Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition

Abstract

Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new class of omni video-text models that integrate ideas from recent LM reasoning advances to address this challenge. More specifically, we present TV2TV, a unified generative modeling framework which decomposes video generation into an interleaved text and video generation process. TV2TV jointly learns language modeling (next-token prediction) and video flow matching (next-frame prediction) using a Mixture-of-Transformers (MoT) architecture. At inference time, TV2TV decides when to alternate between generating text and video frames, allowing the model to "think in words" about subsequent content before ``acting in pixels'' to produce frames. This design offloads much of the responsibility for deciding what should happen next to the language modeling tower, enabling improved visual quality and prompt alignment of generated videos. It also enables fine-grained controllability, allowing users to modify the video generation trajectory through text interventions at any point in the process. In controlled experiments on video game data, TV2TV demonstrates substantial improvements in both visual quality and controllability. TV2TV also scales to natural videos, as we show by augmenting sports videos with interleaved natural language action descriptions using vision-language models (VLMs). Training TV2TV on this corpus yields strong visual quality and prompt alignment, showcasing the model's ability to reason about and generate complex real-world action sequences. Together, these results highlight TV2TV as a promising step toward video generation with open-ended textual reasoning and control.

Keywords

Cite

@article{arxiv.2512.05103,
  title  = {TV2TV: A Unified Framework for Interleaved Language and Video Generation},
  author = {Xiaochuang Han and Youssef Emad and Melissa Hall and John Nguyen and Karthik Padthe and Liam Robbins and Amir Bar and Delong Chen and Michal Drozdzal and Maha Elbayad and Yushi Hu and Shang-Wen Li and Sreya Dutta Roy and Jakob Verbeek and XuDong Wang and Marjan Ghazvininejad and Luke Zettlemoyer and Emily Dinan},
  journal= {arXiv preprint arXiv:2512.05103},
  year   = {2025}
}
R2 v1 2026-07-01T08:10:04.989Z