% Key papers for Next-scale and token autoregressive images (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{cvpr2022_autoregressive_18325, title = {{Autoregressive Image Generation Using Residual Quantization}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, } @inproceedings{neurips2024_visual_73330, title = {{Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94115}, } @inproceedings{neurips2021_imagebart_61122, title = {{ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2021}, url = {https://nips.cc/virtual/2021/poster/26261}, } @inproceedings{cvpr2025_infinity_26625, title = {{Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34414}, } @inproceedings{neurips2024_autoregressive_72453, title = {{Autoregressive Image Generation without Vector Quantization}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94905}, } @inproceedings{cvpr2023_towards_22363, title = {{Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, url = {https://cvpr.thecvf.com/virtual/2023/poster/22990}, } @inproceedings{neurips2022_nuwa_63693, title = {{NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/54352}, } @inproceedings{icml2021_bang_39075, title = {{BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2021}, url = {https://icml.cc/virtual/2021/poster/8523}, } @inproceedings{cvpr2023_not_21720, title = {{Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, url = {https://cvpr.thecvf.com/virtual/2023/poster/22980}, } @inproceedings{cvpr2025_parallelized_27218, title = {{Parallelized Autoregressive Visual Generation}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34410}, } @inproceedings{cvpr2025_randar_27375, title = {{RandAR: Decoder-only Autoregressive Visual Generation in Random Orders}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33854}, } @inproceedings{cvpr2025_collaborative_25738, title = {{Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33605}, } @inproceedings{cvpr2025_editar_26084, title = {{EditAR: Unified Conditional Generation with Autoregressive Models}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/34111}, } @inproceedings{neurips2022_draft_64926, title = {{Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/53954}, } @inproceedings{neurips2025_understand_77916, title = {{Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=Z4hi1a9FsB}, } @inproceedings{iclr2024_sequencematch_34003, title = {{SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/19072}, } @inproceedings{neurips2025_flexvar_74854, title = {{FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=1qKvZX4qnp}, } @inproceedings{neurips2025_freqexit_75908, title = {{FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=DUlZTgLkeh}, } @inproceedings{neurips2025_nfig_79234, title = {{NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=nHNYDM6PVz}, } @inproceedings{iclr2025_hart_83553, title = {{HART: Efficient Visual Generation with Hybrid Autoregressive Transformer}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/32057}, } @inproceedings{iclr2026_mvar_88445, title = {{MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026}, url = {https://openreview.net/forum?id=mkr1ZrwgeJ}, } @inproceedings{aaai2026_next_104245, title = {{Next Patch Prediction for AutoRegressive Visual Generation}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/37774}, } @inproceedings{aaai2026_scalar_105247, title = {{SCALAR: Scale-wise Controllable Visual Autoregressive Learning}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/38119}, } @inproceedings{icml2024_denoising_44902, title = {{Denoising Autoregressive Representation Learning}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024}, url = {https://icml.cc/virtual/2024/poster/33550}, } @inproceedings{icml2025_flowar_46897, title = {{FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/45682}, } @inproceedings{icml2025_continuous_47831, title = {{Continuous Visual Autoregressive Generation via Score Maximization}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/44770}, } @inproceedings{icml2025_tractable_48244, title = {{Tractable Transformers for Flexible Conditional Generation}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/44368}, }