mlsanityData to 14 Oct 2026

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

arXiv 2504.11455 ↗First posted 15 Apr 2025cs.CVcited by 86

Not on the map. Why?

Abstract (arXiv)

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B parameters, our model can generate 1024x1024 resolution images with high fidelity, and achieve competitive results on challenging text-to-image benchmarks, e.g., 0.59 on GenEval and 79.66 on DPG; 2) both supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) training could lead to significant improvements on generation aesthectics and prompt alignment; and 3) when optimized with inference acceleraton techniques like vLLM, the time for SimpleAR to generate an 1024x1024 image could be reduced to around 14 seconds. By sharing these findings and open-sourcing the code, we hope to reveal the potential of autoregressive visual generation and encourage more participation in this research field. Code is available at https://github.com/wdrink/SimpleAR.

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). Builds on 64 of its 74 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

64 of 74 references.

References · 64

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2020Denoising Diffusion Implicit Modelscited by 9,781
  8. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  10. 2023Segment Anythingcited by 8,234
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  12. 2022Scalable Diffusion Models with Transformerscited by 6,054
38 more
  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  11. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  13. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  14. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  15. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  16. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  17. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  18. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  19. 2023Training Diffusion Models with Reinforcement Learningcited by 982
  20. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  21. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  22. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  23. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  24. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  25. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  26. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  27. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  28. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  29. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  30. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  31. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  32. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  33. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  34. 2022Efficiently Scaling Transformer Inferencecited by 539
  35. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  36. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  37. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  38. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 58; 2026: 28.

86 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  3. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 109
  4. 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationcited by 86
  5. 2025Visual Planning: Let's Think Only with Imagescited by 85
  6. 2025PixNerd: Pixel Neural Field Diffusioncited by 82
  7. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57
  8. 2025OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generationcited by 46
  9. 2025SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Rewardcited by 45
  10. 2025Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learningcited by 44
  11. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generationcited by 32
  12. 2025Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOcited by 31
38 more
  1. 2025MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPOcited by 30
  2. 2026JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generationcited by 25
  3. 2025RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learningcited by 23
  4. 2025Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspectivecited by 22
  5. 2025WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generationcited by 20
  6. 2025Follow-Your-Preference: Towards Preference-Aligned Image Inpaintingcited by 18
  7. 2025Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Samplingcited by 18
  8. 2025FARMER: Flow AutoRegressive Transformer over Pixelscited by 18
  9. 2025Group Critical-token Policy Optimization for Autoregressive Image Generationcited by 17
  10. 2025MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoningcited by 16
  11. 2025Co-Reinforcement Learning for Unified Multimodal Understanding and Generationcited by 15
  12. 2025STAGE: Stable and Generalizable GRPO for Autoregressive Image Generationcited by 15
  13. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 14
  14. 2025Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generationcited by 14
  15. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 14
  16. 2025ReCode: Updating Code API Knowledge with Reinforcement Learningcited by 12
  17. 2025Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advancescited by 12
  18. 2025UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generationcited by 11
  19. 2025Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Controlcited by 10
  20. 2025TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuningcited by 10
  21. 2025VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstructioncited by 10
  22. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  23. 2025SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewardscited by 8
  24. 2025HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generationcited by 8
  25. 2025UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learningcited by 8
  26. 2025RubricRL: Simple Generalizable Rewards for Text-to-Image Generationcited by 7
  27. 2025VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generationcited by 7
  28. 2026From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generationcited by 7
  29. 2025The Promise of RL for Autoregressive Image Editingcited by 6
  30. 2025DeRA: Decoupled Representation Alignment for Video Tokenizationcited by 6
  31. 2025Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Modelscited by 6
  32. 2025Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Modelcited by 6
  33. 2026Improving Flexible Image Tokenizers for Autoregressive Image Generationcited by 6
  34. 2026SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Modelscited by 6
  35. 2025Context-Aware Autoregressive Models for Multi-Conditional Image Generationcited by 5
  36. 2025Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generationcited by 5
  37. 2026CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenizationcited by 5
  38. 2025StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generationcited by 4

50 most cited of 86 All 86 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation
  2. 2026VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction
  3. 2025Autoregressive Image Generation with Randomized Parallel Decoding
  4. 2024RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
  5. 2025Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling
  6. 2025FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
  7. 2026VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation
  8. 2025Distilling Specialized Orders for Visual Generation