# The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation

arXiv: https://arxiv.org/abs/2503.04606 · HTML: https://mlsanity.com/paper/2503.04606/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 4 of its 69 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 4 of 4)

- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [RepCodec: A Speech Representation Codec for Speech Tokenization](https://mlsanity.com/paper/2309.00169/) (2023)

## Abstract (arXiv)

Recent advancements in text-to-video (T2V) generation have been driven by two competing paradigms: autoregressive language models and diffusion models. However, each paradigm has intrinsic limitations: language models struggle with visual quality and error accumulation, while diffusion models lack semantic understanding and causal modeling. In this work, we propose LanDiff, a hybrid framework that synergizes the strengths of both paradigms through coarse-to-fine generation. Our architecture introduces three key innovations: (1) a semantic tokenizer that compresses 3D visual features into compact 1D discrete representations through efficient semantic compression, achieving a ~14,000× compression ratio; (2) a language model that generates semantic tokens with high-level semantic relationships; (3) a streaming diffusion model that refines coarse semantics into high-fidelity videos. Experiments show that LanDiff, a 5B model, achieves a score of 85.43 on the VBench T2V benchmark, surpassing the state-of-the-art open-source models Hunyuan Video (13B) and other commercial models such as Sora, Kling, and Hailuo. Furthermore, our model also achieves state-of-the-art performance in long video generation, surpassing other open-source models in this field. Our demo can be viewed at https://landiff.github.io/.