# ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer

arXiv: https://arxiv.org/abs/2412.07720 · HTML: https://mlsanity.com/paper/2412.07720/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 84 of its 95 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 84)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)

## Built on by (most cited first, 30 of 45)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [RELIC: Interactive Video World Model with Long-Horizon Memory](https://mlsanity.com/paper/2512.04040/) (2025)
- [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025)
- [MotionStream: Real-Time Video Generation with Interactive Motion Controls](https://mlsanity.com/paper/2511.01266/) (2025)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Long-Context State-Space Video World Models](https://mlsanity.com/paper/2505.20171/) (2025)
- [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://mlsanity.com/paper/2512.15702/) (2025)
- [Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion](https://mlsanity.com/paper/2602.07775/) (2026)
- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling](https://mlsanity.com/paper/2604.07209/) (2026)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)
- [Streaming Autoregressive Video Generation via Diagonal Distillation](https://mlsanity.com/paper/2603.09488/) (2026)
- [Generative Pre-trained Autoregressive Diffusion Transformer](https://mlsanity.com/paper/2505.07344/) (2025)
- [VideoMAR: Autoregressive Video Generatio with Continuous Tokens](https://mlsanity.com/paper/2506.14168/) (2025)
- [BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2512.12080/) (2025)
- [LIVE: Long-horizon Interactive Video World Modeling](https://mlsanity.com/paper/2602.03747/) (2026)
- [MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines](https://mlsanity.com/paper/2603.06679/) (2026)
- [Towards One-step Causal Video Generation via Adversarial Self-Distillation](https://mlsanity.com/paper/2511.01419/) (2025)
- [HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising](https://mlsanity.com/paper/2603.08703/) (2026)
- [Wonder: Video World Model Done Better](https://mlsanity.com/paper/2607.26037/) (2026)
- [Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention](https://mlsanity.com/paper/2602.04789/) (2026)
- [Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation](https://mlsanity.com/paper/2507.01957/) (2025)
- [Real-Time Motion-Controllable Autoregressive Video Diffusion](https://mlsanity.com/paper/2510.08131/) (2025)
- [Video-GPT via Next Clip Diffusion](https://mlsanity.com/paper/2505.12489/) (2025)
- [TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment](https://mlsanity.com/paper/2606.13035/) (2026)
- [Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis](https://mlsanity.com/paper/2507.01756/) (2025)
- [WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion](https://mlsanity.com/paper/2512.19678/) (2025)
- [SemanticGen: Video Generation in Semantic Space](https://mlsanity.com/paper/2512.20619/) (2025)

## Abstract (arXiv)

Autoregressive and diffusion models have achieved remarkable progress in language models and visual generation, respectively. We present ACDiT, a novel Autoregressive blockwise Conditional Diffusion Transformer, that innovatively combines autoregressive and diffusion paradigms for continuous visual information. By introducing a block-wise autoregressive unit, ACDiT offers a flexible interpolation between token-wise autoregression and full-sequence diffusion, bypassing the limitations of discrete tokenization. The generation of each block is formulated as a conditional diffusion process, conditioned on prior blocks. ACDiT is easy to implement, as simple as applying a specially designed Skip-Causal Attention Mask on the standard diffusion transformer during training. During inference, the process iterates between diffusion denoising and autoregressive decoding that can make full use of KV-Cache. We validate the effectiveness of ACDiT on image, video, and text generation and show that ACDiT performs best among all autoregressive baselines under similar model scales on visual generation tasks. We also demonstrate that, benefiting from autoregressive modeling, pretrained ACDiT can be transferred in visual understanding tasks despite being trained with the generative objective. The analysis of the trade-off between autoregressive and diffusion demonstrates the potential of ACDiT to be used in long-horizon visual generation tasks. We hope that ACDiT offers a novel perspective on visual autoregressive generation and sheds light on new avenues for unified models.