{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:18:01Z","timestamp":1783455481448,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"BNBU Research","award":["UICR0700108-25"],"award-info":[{"award-number":["UICR0700108-25"]}]},{"name":"Beijing Normal-Hong Kong Baptist University, Zhuhai, PR China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3673772","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:53:27Z","timestamp":1773431607000},"page":"8813-8830","source":"Crossref","is-referenced-by-count":0,"title":["Hyper-Compression: Model Compression via Hyperfunction"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3691-5141","authenticated-orcid":false,"given":"Feng-Lei","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8504-6598","authenticated-orcid":false,"given":"Juntong","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-2110","authenticated-orcid":false,"given":"Dayang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelin","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The Chinese University of Hong Kong, HKSAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2656-7705","authenticated-orcid":false,"given":"Ge","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0688-202X","authenticated-orcid":false,"given":"Tieyong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10862-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2409160121"},{"key":"ref6","volume-title":"Ergodic Theory","author":"Cornfeld","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409079"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.174060306.65738406\/v1","article-title":"Qwen 2.5: A comprehensive review of the leading resource-efficient LLM with potentioal to surpass all competitors","author":"Ahmed","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref14","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref15","article-title":"A simple and effective pruning approach for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.425"},{"key":"ref18","article-title":"Sheared LLaMA: Accelerating language model pre-training via structured pruning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref19","article-title":"Accurate retraining-free pruning for pretrained encoder-based language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Park"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref22","article-title":"BiLLM: Pushing the limit of post-training quantization for LLMs","author":"Huang","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0323"},{"key":"ref24","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref26","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proc. 7th Annu. Conf. Mach. Learn. Syst.","author":"Zhao"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shen"},{"key":"ref28","article-title":"TensorGPT: Efficient compression of the embedding layer in LLMs based on the tensor-train decomposition","author":"Xu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref30","article-title":"COIN: Compression with implicit neural representations","author":"Dupont","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849795"},{"key":"ref32","article-title":"HyperNetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref33","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu"},{"key":"ref34","article-title":"Example-based hypernetworks for out-of-distribution generalization","author":"Volk","year":"2022"},{"issue":"276","key":"ref35","first-page":"1","article-title":"Deep network approximation: Achieving arbitrary accuracy with fixed number of neurons","volume":"23","author":"Zhang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/22M1511709"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330875"},{"key":"ref38","article-title":"Sheared LLaMA: Accelerating language model pre-training via structured pruning","author":"Xia","year":"2024"},{"key":"ref39","article-title":"TinyLlama: An open-source small language model","author":"Zhang","year":"2024"},{"key":"ref40","article-title":"Qwen2 technical report","author":"Team","year":"2024"},{"key":"ref41","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref42","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"issue":"2","key":"ref44","first-page":"107","article-title":"The CommitmentBank: Investigating projection in naturally occurring discourse","volume-title":"Proc. Sinn und Bedeutung","volume":"23","author":"De Marneffe","year":"2019"},{"key":"ref45","first-page":"90","article-title":"Choice of plausible alternatives: An evaluation of commonsense causal reasoning","volume-title":"Proc. AAAI Spring Symp.: Log. Formalizations Commonsense Reasoning","author":"Roemmele"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1023"},{"key":"ref47","article-title":"ReCoRD: Bridging the gap between human and machine commonsense reading comprehension","author":"Zhang","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref49","first-page":"1267","article-title":"WiC: The word-in-context dataset for evaluating context-sensitive meaning representations","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Pilehvar"},{"key":"ref50","article-title":"The Winograd schema challenge","volume-title":"Proc. 13th Int. Conf. Princ. Knowl. Representation Reasoning","author":"Levesque"},{"key":"ref51","article-title":"SpinQuant: LLM quantization with learned rotations","author":"Liu","year":"2024"},{"key":"ref52","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref55","article-title":"SQUANT: On-the-fly data-free quantization via diagonal hessian approximation","author":"Guo","year":"2022"},{"key":"ref56","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref57","first-page":"2397","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Biderman"},{"key":"ref58","article-title":"OpenLLaMA: An open reproduction of LLaMA","author":"Geng","year":"2023"},{"issue":"3","key":"ref59","first-page":"732","article-title":"Chaos: An introduction to dynamical systems","volume":"40","author":"Alligood","year":"1998","journal-title":"SIAM Rev."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/58562.59305"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002804"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41378-4"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11434864.pdf?arnumber=11434864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:36Z","timestamp":1783453476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":62,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3673772","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}