{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T22:20:15Z","timestamp":1784845215653,"version":"3.55.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031703676","type":"print"},{"value":"9783031703683","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70368-3_9","type":"book-chapter","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T23:03:11Z","timestamp":1725058991000},"page":"143-159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["$$\\sigma $$-GPTs: A New Approach to\u00a0Autoregressive Models"],"prefix":"10.1007","author":[{"given":"Arnaud","family":"Pannatier","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evann","family":"Courdier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Fleuret","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"9_CR1","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: Advances in Neural Information Processing Systems, vol. 34, pp. 17981\u201317993 (2021)"},{"key":"9_CR2","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers (2023)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"9_CR4","unstructured":"Chen, C., Borgeaud, S., Irving, G., Lespiau, J.B., Sifre, L., Jumper, J.: Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)"},{"key":"9_CR5","unstructured":"Gokaslan, A., Cohen, V.: Openwebtext corpus (2019). http:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"9_CR6","unstructured":"Golovneva, O., Allen-Zhu, Z., Weston, J., Sukhbaatar, S.: Reverse training to nurse the reversal curse (2024)"},{"key":"9_CR7","unstructured":"Gulrajani, I., Hashimoto, T.: Likelihood-based diffusion language models. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=e2MCL6hObn"},{"key":"9_CR8","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Kakogeorgiou, I., Gidaris, S., Karantzalos, K., Komodakis, N.: Spot: self-training with patch-order permutation for object-centric learning with autoregressive transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22776\u201322786 (2024)","DOI":"10.1109\/CVPR52733.2024.02149"},{"key":"9_CR10","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., HAN, W.S.: Draft-and-revise: effective image generation with contextual RQ-transformer. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 30127\u201330138. Curran Associates, Inc. (2022)"},{"key":"9_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-031-20050-2_5","volume-title":"Computer Vision - ECCV 2022","author":"J Lezama","year":"2022","unstructured":"Lezama, J., Chang, H., Jiang, L., Essa, I.: Improved masked image generation with token-critic. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13683, pp. 70\u201386. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_5"},{"key":"9_CR12","unstructured":"Lou, A., Meng, C., Ermon, S.: Discrete diffusion modeling by estimating the ratios of the data distribution (2024)"},{"key":"9_CR13","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. In: International Conference on Learning Representations (2017)"},{"key":"9_CR14","unstructured":"OpenAI: New embedding models and API updates (2024). https:\/\/openai.com\/blog\/new-embedding-models-and-api-updates. Accessed 01 Mar 2024"},{"key":"9_CR15","unstructured":"Papadopoulos, V., Wenger, J., Hongler, C.: Arrows of time for large language models (2024)"},{"issue":"8","key":"9_CR16","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"9_CR17","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: Proceedings of the 40th International Conference on Machine Learning, ICML 2023. JMLR.org (2023)"},{"key":"9_CR18","unstructured":"Varma, V., Shah, R., Kenton, Z., Kram\u00e1r, J., Kumar, R.: Explaining grokking through circuit efficiency. arXiv preprint arXiv:2309.02390 (2023)"},{"key":"9_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"9_CR20","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: International Conference on Learning Representations (2023)"},{"key":"9_CR21","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc. (2019)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70368-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T15:50:48Z","timestamp":1732722648000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70368-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703676","9783031703683"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70368-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}