Elamur Research⌕
☰
home / papers / 2026 / Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Paper · 2026 · Dianyi Wang, Wei Song, Yikun Wang et al.

Summary

Most large vision-language models (LVLMs) such as LLaVA receive training signal only on their text answers. The hundreds of visual tokens they take as input go unsupervised, so fine-grained visual detail can be neglected. The authors propose ASVR (Autoregressive Semantic Visual Reconstruction). It adds a visual prediction head that, under the same next-token objective used for text, predicts the discrete codes a pretrained semantic visual tokenizer assigns to the input image. The model still receives continuous encoder features as input, and the visual and text losses are simply summed. No external modules such as a diffusion transformer are required. Semantic targets proved more useful than appearance (pixel-level) targets. The continuous-input, discrete-target setup also beat both shared discrete input/output tokens and the denoising-based ROSS approach. Across 14 multimodal benchmarks, ASVR typically raises baseline averages by about 2–3%, and the gains hold across data scales, backbones and high-resolution settings. This suggests explicit visual supervision is a cheap, scalable addition to standard LVLM training.

Key points

  • Training data scales tested: LLaVA-1.5-665K, LLaVA-Next-779K, Bunny-v1_1-data-2M and LLaVA-OV-4M. Backbones included the Vicuna family and Mistral.
  • In a controlled comparison (Vicuna-v1.5-7B, LLaVA-Next data), ASVR averaged 55.1 across 14 benchmarks. ROSS scored 53.3 with SigLIP semantic targets and 52.9 with VAE appearance targets.
  • The largest gains in that comparison came on hallucination- and perception-oriented tests: MMVP rose from 30.1 to 36.8 and HallusionBench from 31.2 to 39.2 relative to semantic ROSS.
  • Attention-map analysis shows ASVR models concentrate more on image regions relevant to the question than the LLaVA baseline.
  • Limitations: the current version does not support video or dynamic resolution. Code is released at github.com/AlenjandroWang/ASVR.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of Southern CaliforniaLos Angeles · United States162 works · 35,836 citations🎓Fudan UniversityShanghai · China167 works · 20,987 citations🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations🎓Shanghai Innovation InstituteShanghai · China24 works · 262 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei and Jiaqi Wang. 2026. Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1900

@inproceedings{wang2026autoregressive,
  title = {{Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better}},
  author = {Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei and Jiaqi Wang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1900},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1900}
}

References

71 references, 42 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. AI@Meta. 2024. Llama 3 model card. find
  2. Ibrahim M Alabdulmohsin, Xiaohua Zhai, Alexander Kolesnikov, and Lucas Beyer. 2023. Getting vit in shape: Scaling laws for compute-optimal model design. Advances in Neural Information Processing Systems, 36:16406–16425. find
  3. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023a. Qwen technical report. arXiv preprint arXiv:2309.16609.
  4. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023b. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond.
  5. Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, and 1 others. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954. find
  6. Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaomin Shi, and Wei Zhang. 2025. A survey of inductive reasoning for large language models. ArXiv, abs/2510.10182.
  7. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, and 1 others. 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pa…
  8. Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, Guang Shi, and Haoqi Fan. 2025. Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683. — [arXiv:2505.14683](https://arxiv.org/abs/2505.14683) find
  9. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee. find
  10. Shuai Dong, Siyuan Wang, Xingyu Liu, and Zhongyu Wei. 2025a. Interleaved latent visual reasoning with selective perceptual modeling. ArXiv, abs/2512.05665.
  11. Shuai Dong, Jie Zhang, Guoying Zhao, Shiguang Shan, and Xilin Chen. 2025b. Semantic mismatch and perceptual degradation: A new perspective on image editing immunity. ArXiv, abs/2512.14320. — [arXiv:2512.14320](https://arxiv.org/abs/2512.14320) find
  12. Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Bin Wang, Linke Ouyang, Songyang Zhang, Haodong Duan, Wenwei Zhang, Yining Li, Hang Yan, Yang Gao, Zhe Chen, Xinyue Zhang, Wei Li, Jingwen Li, Wenhai Wang, Kai Chen, Conghui He, and 5 others. 2024. Internlm-xcomposer2-4khd: A pioneering large vision-l…
  13. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. Preprint,…
  14. Alexey Dosovitskiy and Thomas Brox. 2016. Generating images with perceptual similarity metrics based on deep networks. Advances in neural information processing systems, 29. find
  15. Patrick Esser, Robin Rombach, and Bjorn Ommer. 2021. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12873–12883. find
  16. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024. Llava-onevision: Easy visual task transfer. Preprint, arXiv:2408.03326.
  17. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, and Rongrong Ji. 2024a. Mme: A comprehensive evaluation benchmark for multimodal large language models. Preprint, arXiv:2306.13394.
  18. Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, and Ying Shan. 2023a. Seed-bench: Benchmarking multimodal llms with generative comprehension. Preprint, arXiv:2307.16125.
  19. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, and Rongrong Ji. 2024b. Mme: A comprehensive evaluation benchmark for multimodal large language models. Preprint, arXiv:2306.13394.
  20. Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the V in VQA matter: Elevating the role of image understanding in Visual Question Answering. In Conference on Computer Vision and Pattern Recognition (CVPR).
  21. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, and Tianyi Zhou. 2024. Hallusionbench: An advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.…
  22. Muyang He, Yexin Liu, Boya Wu, Jianhao Yuan, Yueze Wang, Tiejun Huang, and Bo Zhao. 2024. Efficient multimodal learning from data-centric perspective. Preprint, arXiv:2402.11530. — [arXiv:2402.11530](https://arxiv.org/abs/2402.11530) find
  23. Drew A Hudson and Christopher D Manning. 2019a. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6700–6709.
  24. Drew A. Hudson and Christopher D. Manning. 2019b. Gqa: A new dataset for real-world visual reasoning and compositional question answering. Preprint, arXiv:1902.09506.
  25. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134. find
  26. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, and 1 others. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. find
  27. Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, and Ali Farhadi. 2016. A diagram is worth a dozen images. Preprint, arXiv:1603.07396.
  28. Chenglin Li, Feng Han, Yikun Wang, Ruilin Li, Shuai Dong, Haowen Hou, Haitao Li, Qianglong Chen, Feng Tao, Jingqi Tong, and 1 others. 2025. Videopro: Adaptive program reasoning for long video understanding. arXiv preprint arXiv:2509.17743.
  29. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023b. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355.
  30. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023c. Evaluating object hallucination in large vision-language models. Preprint, arXiv:2305.10355.
  31. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. Improved baselines with visual instruction tuning. arXiv:2310.03744.
  32. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024a. Improved baselines with visual instruction tuning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26296–26306.
  33. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024b. Llava-next: Improved reasoning, ocr, and world knowledge. find
  34. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Llava-next: Improved reasoning, ocr, and world knowledge. find
  35. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual instruction tuning. Advances in neural information processing systems, 36:34892– 34916.
  36. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, and Dahua Lin. 2024d. Mmbench: Is your multi-modal model an all-around player? Preprint, arXiv:2307.06281.
  37. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, and 1 others. 2023c. Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281.
  38. Yuliang Liu, Zhang Li, Mingxin Huang, Biao Yang, Wenwen Yu, Chunyuan Li, Xu-Cheng Yin, Cheng-Lin Liu, Lianwen Jin, and Xiang Bai. 2024e. Ocrbench: on the hidden mystery of ocr in large multimodal models. Science China Information Sciences, 67(12).
  39. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, Yaofeng Sun, Chengqi Deng, Hanwei Xu, Zhenda Xie, and Chong Ruan. 2024. Deepseek-vl: Towards real-world vision-language understanding. Preprint, arXiv:2403.05525.
  40. Shengbang Tong, David Fan, Jiachen Zhu, Yunyang Xiong, Xinlei Chen, Koustuv Sinha, Michael Rabbat, Yann LeCun, Saining Xie, and Zhuang Liu. 2024b. Metamorph: Multimodal understanding and generation via instruction tuning. arXiv preprint arXiv:2412.14164. find
  41. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. Chartqa: A benchmark for question answering about charts with visual and logical reasoning. Preprint, arXiv:2203.10244.
  42. Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024c. Eyes wide shut? exploring the visual shortcomings of multimodal llms. Preprint, arXiv:2401.06209.
  43. Minesh Mathew, Dimosthenis Karatzas, and C. V. Jawahar. 2021. Docvqa: A dataset for vqa on document images. Preprint, arXiv:2007.00398.
  44. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, and 1 others. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288.
  45. OpenAI. 2023a. Chatgpt (august 3 version). find
  46. Liao Qu, Huichao Zhang, Yiheng Liu, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Daniel K Du, Zehuan Yuan, and Xinglong Wu. 2024. Tokenflow: Unified image tokenizer for multimodal understanding and generation. arXiv preprint arXiv:2412.03069. — [arXiv:2412.03069](https://arxiv.org/abs/2412.03069) find
  47. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8…
  48. Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Ve… — [arXiv:2508.10104](https://arxiv.org/abs/2508.10104) find
  49. Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards vqa models that can read. Preprint, arXiv:1904.08920. find
  50. Wei Song, Yuran Wang, Zijia Song, Yadong Li, Haoze Sun, Weipeng Chen, Zenan Zhou, Jianhua Xu, Jiaqi Wang, and Kaicheng Yu. 2025. Dualtoken: Towards unifying visual understanding and generation with dual visual vocabularies. arXiv preprint arXiv:2503.14324. — [arXiv:2503.14324](https://arxiv.org/abs/2503.14324) find
  51. Chameleon Team. 2024. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818.
  52. Shengbang Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, Ziteng Wang, Rob Fergus, Yann LeCun, and Saining Xie. 2024a. Cambrian-1: A fully open, vision-centric exploration of multimodal llms. Preprint, arXiv:2406.…
  53. Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, Olivier Hénaff, Jeremiah Harmsen, Andreas Steiner, and Xiaohua Zhai. 2025. Siglip 2: Multilingual vision-language encoders with improv… find
  54. Aaron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2018. Neural discrete representation learning. Preprint, arXiv:1711.00937. find
  55. Haochen Wang, Anlin Zheng, Yucheng Zhao, Tiancai Wang, Zheng Ge, Xiangyu Zhang, and Zhaoxiang Zhang. 2024a. Reconstructive visual instruction tuning. arXiv preprint arXiv:2410.09575. — [arXiv:2410.09575](https://arxiv.org/abs/2410.09575) find
  56. Haochen Wang, Anlin Zheng, Yucheng Zhao, Tiancai Wang, Zheng Ge, Xiangyu Zhang, and Zhaoxiang Zhang. 2024b. Reconstructive visual instruction tuning. Preprint, arXiv:2410.09575. — [arXiv:2410.09575](https://arxiv.org/abs/2410.09575) find
  57. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024c. Qwen2-vl: Enhancing vision-language model’s perception of the…
  58. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024d. Qwen2-vl: Enhancing vision-language model’s perception of the…
  59. Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu, and 1 others. 2024e. Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869. — [arXiv:2409.18869](https://arxiv.org/abs/2409.18869) find
  60. Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, and 1 others. 2024a. Janus: Decoupling visual encoding for unified multimodal understanding and generation. arXiv preprint arXiv:2410.13848.
  61. Yecheng Wu, Zhuoyang Zhang, Junyu Chen, Haotian Tang, Dacheng Li, Yunhao Fang, Ligeng Zhu, Enze Xie, Hongxu Yin, Li Yi, and 1 others. 2024b. Vila-u: a unified foundation model integrating visual understanding and generation. arXiv preprint arXiv:2409.04429. — [arXiv:2409.04429](https://arxiv.org/abs/2409.04429) find
  62. Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, and 8 others. 2024c. Deepseek-vl2: Mixture-of-experts vision-language models for…
  63. Rongchang Xie, Chen Du, Ping Song, and Chang Liu. 2024. Muse-vl: Modeling unified vlm through semantic discrete encoding. arXiv preprint arXiv:2411.17762. — [arXiv:2411.17762](https://arxiv.org/abs/2411.17762) find
  64. Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth anything: Unleashing the power of large-scale unlabeled data. In CVPR. find
  65. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, and 1 others. 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800.
  66. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, and 3 others. 2024. Mmmu: A massive multi-discipline multimodal u…
  67. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, and 1 others. 2023. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. arXiv preprint arXiv:2311.16502.
  68. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023. Sigmoid loss for language image pre-training. In Proceedings of the IEEE/CVF international conference on computer vision, pages 11975–11986.
  69. Jie Zhang, Shuai Dong, Shiguang Shan, and Xilin Chen. 2025. Towards transferable defense against malicious image edits. IEEE Trans. Pattern Anal. Mach. Intell., PP. find
  70. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595. find
  71. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Preprint, arXiv:2306.05685.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-autoregressive-semantic-visual-reconstruction-helps/