mlsanityData to 14 Oct 2026

Direction-Aware Diagonal Autoregressive Image Generation

arXiv 2503.11129 ↗First posted 14 Mar 2025cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation. To address this issue, this paper proposes Direction-Aware Diagonal Autoregressive Image Generation (DAR) method, which generates image tokens following a diagonal scanning order. The proposed diagonal scanning order ensures that tokens with adjacent indices remain in close proximity while enabling causal attention to gather information from a broader range of directions. Additionally, two direction-aware modules: 4D-RoPE and direction embeddings are introduced, enhancing the model's capability to handle frequent changes in generation direction. To leverage the representational capacity of the image tokenizer, we use its codebook as the image token embeddings. We propose models of varying scales, ranging from 485M to 2.0B. On the 256×256 ImageNet benchmark, our DAR-XL (2.0B) outperforms all previous autoregressive image generators, achieving a state-of-the-art FID score of 1.37.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 59 of its 68 references that are in the map. First posted on arXiv 14 Mar 2025.

Builds on

59 of 68 references.

References · 59

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  10. 2020Denoising Diffusion Implicit Modelscited by 9,781
  11. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  12. 2023Visual Instruction Tuningcited by 7,869
38 more
  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2022Classifier-Free Diffusion Guidancecited by 5,847
  4. 2017Neural Discrete Representation Learningcited by 4,712
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  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. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  11. 2016Improved Techniques for Training GANscited by 2,970
  12. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  13. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  14. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  15. 2020GLU Variants Improve Transformercited by 1,804
  16. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  17. 2018Self-Attention with Relative Position Representationscited by 1,120
  18. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  19. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  20. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  21. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  22. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  23. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  24. 2018Image Transformercited by 772
  25. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  26. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  27. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  28. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  29. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  30. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  31. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 421
  32. 2023EVA-02: A Visual Representation for Neon Genesiscited by 381
  33. 2022MAGVIT: Masked Generative Video Transformercited by 346
  34. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  35. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 302
  36. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizercited by 262
  37. 2024Rotary Position Embedding for Vision Transformercited by 236
  38. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Exploiting Discriminative Codebook Prior for Autoregressive Image Generationcited by 2
  2. 2025SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Modelcited by 2
  3. 2025Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Samplingcited by 2
  4. 2025Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Imagescited by 1
  5. 2026Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modelingcited by 0