{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:01Z","timestamp":1785649621148,"version":"3.56.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032319197","type":"print"},{"value":"9783032319203","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31920-3_1","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:25:11Z","timestamp":1785648311000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enabling 8B Bitwise Autoregressive Image Generation on\u00a0Edge GPUs"],"prefix":"10.1007","author":[{"given":"Enrico","family":"Vezzali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Bolelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costantino","family":"Grana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Benini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Allegretti, S., et\u00a0al.: How does connected components labeling with decision trees perform on GPUs? In: CAIP (2019)","DOI":"10.1007\/978-3-030-29888-3_4"},{"key":"1_CR2","unstructured":"Black Forest Labs: Flux.1 (2024). https:\/\/blackforestlabs.ai\/"},{"key":"1_CR3","doi-asserted-by":"publisher","unstructured":"Chen, J., et\u00a0al.: PixArt-$$\\Sigma $$: weak-to-strong training of diffusion transformer for 4K text-to-image generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15090, pp. 74\u201391. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73411-3_5","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Dettmers, T.: GPT3.int8: 8-bit matrix multiplication for transformers at scale. In: NeurIPS (2022)","DOI":"10.52202\/068431-2198"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"1_CR6","unstructured":"Firoozi, R.: Foundation models in robotics: applications, challenges, and the future. Int. J. Robot. Res. 44(5) (2025)"},{"key":"1_CR7","unstructured":"Frantar, E.: GPTQ: accurate post-training quantization for generative pre-trained transformers (2022). arXiv:2210.17323"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Golda, A.: Privacy and security concerns in generative AI: a comprehensive survey. IEEE Access 12 (2024)","DOI":"10.1109\/ACCESS.2024.3381611"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Han, J.: Infinity: scaling bitwise autoregressive modeling for high-resolution image synthesis. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, J.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"1_CR11","unstructured":"Heusel, M.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS (2017)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Lee, D.: Autoregressive image generation using residual quantization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"1_CR13","unstructured":"Li, D.: Playground v2.5: three insights towards enhancing aesthetic quality in text-to-image generation (2024). arXiv:2402.17245"},{"key":"1_CR14","unstructured":"Li, K.: Memory-efficient visual autoregressive modeling with scale-aware KV cache compression. arXiv:2505.19602 (2025)"},{"key":"1_CR15","unstructured":"Li, M.: SVDQuant: absorbing outliers by low-rank components for 4-bit diffusion models. arXiv:2411.05007 (2024)"},{"key":"1_CR16","unstructured":"Lin, J.: AWQ: activation-aware weight quantization for LLM compression and acceleration. MLSys 6 (2024)"},{"key":"1_CR17","unstructured":"Liu, Z.: KIVI: a tuning-free asymmetric 2bit quantization for KV cache. arXiv:2402.02750 (2024)"},{"key":"1_CR18","unstructured":"Mentzer, F.: High-fidelity generative image compression. In: NeurIPS (2020)"},{"key":"1_CR19","unstructured":"Podell, D.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"1_CR20","unstructured":"Qin, Z.: Head-aware KV cache compression for efficient visual autoregressive modeling. arXiv:2504.09261 (2025)"},{"key":"1_CR21","unstructured":"Razavi, A., Van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: NeurIPS (2019)"},{"key":"1_CR22","unstructured":"Tang, H.: HART: efficient visual generation with hybrid autoregressive transformer. arXiv:2410.10812 (2024)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Tian, K., et\u00a0al.: Visual autoregressive modeling: scalable image generation via next-scale prediction. In: NeurIPS (2024)","DOI":"10.52202\/079017-2694"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Urbanek, J.: A picture is worth more than 77 text tokens: evaluating CLIP-style models on dense captions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"1_CR25","unstructured":"Van Den\u00a0Oord, A., et\u00a0al.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Vezzali, E.: A deep-learning-based method for real-time barcode segmentation on edge CPUs. In: CAIP (2025)","DOI":"10.1007\/978-3-032-04968-1_16"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Vezzali, E.: Mosaic-SR: an adaptive multi-step super-resolution method for low-resolution 2D barcodes. In: ICIP (2025)","DOI":"10.1109\/ICIP55913.2025.11084637"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Vezzali, E.: State-of-the-art review and benchmarking of barcode localization methods. Eng. Appl. Artif. Intell. (2025)","DOI":"10.1016\/j.engappai.2025.110259"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring CLIP for assessing the look and feel of images. In: AAAI, vol. 37 (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"1_CR30","unstructured":"Wei, R.: FPQVAR: floating point quantization for visual autoregressive model with FPGA hardware co-design. arXiv:2505.16335 (2025)"},{"key":"1_CR31","unstructured":"Xiao, G.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: ICML (2023)"},{"key":"1_CR32","unstructured":"Xie, E.: SANA: efficient high-resolution image synthesis with linear diffusion transformers. arXiv preprint arXiv:2410.10629 (2024)"},{"key":"1_CR33","unstructured":"Xie, R.: LiteVAR: compressing visual autoregressive modelling with efficient attention and quantization. arXiv:2411.17178 (2024)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J.: ImageReward: learning and evaluating human preferences for text-to-image generation. In: NeurIPS (2023)","DOI":"10.52202\/075280-0700"},{"key":"1_CR35","unstructured":"Yu, J.: Vector-quantized image modeling with improved VQGAN. arXiv:2110.04627 (2021)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, R.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31920-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:25:13Z","timestamp":1785648313000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31920-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032319197","9783032319203"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31920-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}