# MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

arXiv: https://arxiv.org/abs/2410.10798 · HTML: https://mlsanity.com/paper/2410.10798/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 56 of its 71 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 30 of 56)

- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)

## Built on by (most cited first, 19 of 19)

- [Show-o2: Improved Native Unified Multimodal Models](https://mlsanity.com/paper/2506.15564/) (2025)
- [Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation](https://mlsanity.com/paper/2505.05472/) (2025)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [Reconstruction Alignment Improves Unified Multimodal Models](https://mlsanity.com/paper/2509.07295/) (2025)
- [Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads](https://mlsanity.com/paper/2412.00127/) (2024)
- [UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.14682/) (2025)
- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation](https://mlsanity.com/paper/2412.04432/) (2024)
- [Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss](https://mlsanity.com/paper/2602.07022/) (2026)
- [WeGen: A Unified Model for Interactive Multimodal Generation as We Chat](https://mlsanity.com/paper/2503.01115/) (2025)
- [UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2511.16917/) (2025)
- [Transferability Between Understanding and Generation in Unified Multimodal Models](https://mlsanity.com/paper/2607.04423/) (2026)
- [MARRS: Masked Autoregressive Unit-based Reaction Synthesis](https://mlsanity.com/paper/2505.11334/) (2025)
- [MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization](https://mlsanity.com/paper/2503.14040/) (2025)
- [WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens](https://mlsanity.com/paper/2512.02536/) (2025)
- [Semantic Generative Tuning for Unified Multimodal Models](https://mlsanity.com/paper/2605.18714/) (2026)
- [EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement](https://mlsanity.com/paper/2606.02739/) (2026)
- [Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model](https://mlsanity.com/paper/2606.14792/) (2026)

## Abstract (arXiv)

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of image information during understanding task, due to either image discretization or diffusion denoising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way. Differing from diffusion-based approaches, we disentangle the diffusion process from auto-regressive backbone model by employing a light-weight diffusion head on top each auto-regressed image patch embedding. In this way, when the model transits from image generation to understanding through text generation, the backbone model's hidden representation of the image is not limited to the last denoising step. To successfully train our method, we also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals. Extensive evaluations on 18 image understanding benchmarks show that MMAR significantly outperforms most of the existing joint multi-modal models, surpassing the method that employs pre-trained CLIP vision encoder. Meanwhile, MMAR is able to generate high quality images. We also show that our method is scalable with larger data and model size.