{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:07:30Z","timestamp":1783400850098,"version":"3.54.6"},"reference-count":322,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3560423","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T17:37:08Z","timestamp":1744738628000},"page":"6531-6549","source":"Crossref","is-referenced-by-count":27,"title":["Hadamard Product in Deep Learning: Introduction, Advances and Challenges"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0650-1856","authenticated-orcid":false,"given":"Grigorios G.","family":"Chrysos","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongtao","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Razvan","family":"Pascanu","sequence":"additional","affiliation":[{"name":"DeepMind, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip H.S.","family":"Torr","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volkan","family":"Cevher","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref6","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref13","first-page":"597","article-title":"On the computational complexity of self-attention","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Keles"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01035"},{"key":"ref15","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hua"},{"key":"ref16","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref18","article-title":"Multilinear operator networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref19","first-page":"77546","article-title":"Monarch mixer: A simple sub-quadratic GEMM-based architecture","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02560"},{"key":"ref22","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref24","article-title":"Vision-RWKV: Efficient and scalable visual perception with RWKV-like architectures","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Duan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_4"},{"key":"ref28","article-title":"Parallelizing linear transformers with the delta rule over sequence length","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref29","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu"},{"key":"ref30","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dao"},{"key":"ref31","article-title":"HGRN2: Gated linear RNNs with state expansion","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Qin"},{"key":"ref32","first-page":"56501","article-title":"Gated linear attention transformers with hardware-efficient training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3231971"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref35","article-title":"FedPara: Low-rank hadamard product for communication-efficient federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hyeon-Woo"},{"key":"ref36","article-title":"HiRA: Parameter-efficient hadamard high-rank adaptation for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref37","article-title":"MLAE: Masked LoRa experts for parameter-efficient fine-tuning","author":"Wang","year":"2024"},{"key":"ref38","first-page":"28390","article-title":"Conditional generation using polynomial expansions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chrysos"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2655720"},{"key":"ref41","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref42","first-page":"26980","article-title":"Extrapolation and spectral bias of neural nets with hadamard product: A polynomial net study","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref43","volume-title":"Finite Dimensional Vector Spaces","author":"Halmos","year":"1948"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(73)90023-2"},{"key":"ref45","volume-title":"Le\u00e7ons Sur La Propagation Des Ondes Et Les \u00e9quations De L\u2019hydrodynamique","author":"Hadamard","year":"1903"},{"key":"ref46","first-page":"240","article-title":"Resolution d\u2019une question relative aux determinants","volume":"2","author":"Hadamard","year":"1893","journal-title":"Bull. Des Sci. Math."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/040"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1515\/crll.1911.140.1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199"},{"key":"ref51","article-title":"Survey of dropout methods for deep neural networks","author":"Labach","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3074329"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2462751"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2307\/3029337"},{"key":"ref56","volume-title":"Analysis: Spaces of Differentiable Functions, Ser. Encyclopaedia of Mathematical Sciences","author":"Nikol\u2019skii","year":"2013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1971.4308320"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7906(02)00045-9"},{"key":"ref59","first-page":"448","article-title":"Optimal perceptual inference","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit.","author":"Hinton"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1063\/1.36241"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1063\/1.36246"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1364\/AO.26.004972"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155142"},{"key":"ref64","first-page":"2377","article-title":"Training very deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.152"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"ref67","first-page":"9204","article-title":"Pay attention to MLPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref68","first-page":"17627","article-title":"Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096453"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109763"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102346"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01547"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_40"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00735"},{"key":"ref76","article-title":"Multiplicative filter networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fathony"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01577"},{"key":"ref78","article-title":"Residual multiplicative filter networks for multiscale reconstruction","author":"Shekarforoush","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref81","first-page":"7360","article-title":"Semi-supervised StyleGAN for disentanglement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nie"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534045"},{"key":"ref83","first-page":"9423","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01441"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00325"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3154925"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103928"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102310"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00842"},{"key":"ref95","article-title":"Edge guided GANs with semantic preserving for semantic image synthesis","author":"Tang","year":"2020"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101899"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6850"},{"key":"ref98","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref100","first-page":"33330","article-title":"Point transformer V2: Grouped vector attention and partition-based pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref101","first-page":"2771","article-title":"3D human tongue reconstruction from single \u201cin-the-wil","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ploumpis"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058891"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"ref104","article-title":"Adversarial audio synthesis with complex-valued polynomial networks","author":"Wu","year":"2022"},{"key":"ref105","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref106","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref107","first-page":"22605","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ging"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.071"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/BF02288739"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1950-0034746-2"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.2307\/2334380"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310791"},{"key":"ref116","article-title":"Automatic lipreading to enhance speech recognition (speech reading)","author":"Petajan","year":"1984"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/35.41402"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref121","first-page":"361","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.4324\/9780203786031-11"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref126","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref127","first-page":"2063","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref129","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3534619"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00502"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.3390\/math10183244"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00170"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2938724"},{"key":"ref138","first-page":"3442","article-title":"Multilinear latent conditioning for generating unseen attribute combinations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Georgopoulos"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.3390\/s21051756"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108239"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00127"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/IPIN54987.2022.9918137"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00979"},{"key":"ref144","first-page":"6594","article-title":"Modulating early visual processing by language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"De Vries"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref146","article-title":"On self modulation for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00016"},{"key":"ref151","first-page":"5825","article-title":"Multi-modality latent interaction network for visual question answering","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Gao"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI53629.2021.9624447"},{"key":"ref156","first-page":"11041","article-title":"Robust visual reasoning via language guided neural module networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akula"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00189"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_13"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01758"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207000"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref165","first-page":"4655","article-title":"Visual question answering with question representation update (QRU)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01093"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.013"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102829"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10980-w"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00220"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3170904"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00112"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119122"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5701"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/3492324.3494162"},{"key":"ref185","first-page":"2731","article-title":"Quaternion knowledge graph embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref186","first-page":"4289","article-title":"Simple embedding for link prediction in knowledge graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kazemi"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291014"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1088\/0957-0233\/22\/11\/114012"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191013"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/1544955"},{"key":"ref191","article-title":"Overview of ImageCLEF 2018 medical domain visual question answering task","volume-title":"Proc. CLEF 2018 Work. Notes","author":"Hasan","year":"2018"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104183"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3006872"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.103087"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3034123"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168331"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3103517"},{"key":"ref199","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"issue":"1","key":"ref200","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref201","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00027"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00276"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00396"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00349"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"ref209","first-page":"870","article-title":"Convolutional generation of textured 3D meshes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pavllo"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref215","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref216","first-page":"26326","article-title":"Gradient-free structured pruning with unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nova"},{"key":"ref217","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012"},{"key":"ref218","first-page":"3084","article-title":"Adaptive dropout for training deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref219","first-page":"10890","article-title":"R-drop: Regularized dropout for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref220","first-page":"351","article-title":"Dropout: Explicit forms and capacity control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"ref222","article-title":"Cross-domain few-shot classification via learned feature-wise transformation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tseng"},{"key":"ref223","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref224","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref225","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref226","article-title":"xLSTM: Extended long short-term memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Beck"},{"key":"ref227","article-title":"Gated slot attention for efficient linear-time sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_40"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_31"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00291"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00895"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3185113"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.06.036"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.81"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_40"},{"key":"ref236","article-title":"Feat: Face editing with attention","author":"Hou","year":"2022"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref238","first-page":"570","article-title":"Learning to predict layout-to-image conditional convolutions for semantic image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00049"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3021387"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3188878"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"},{"key":"ref243","article-title":"Masknet: Introducing feature-wise multiplication to ctr ranking models by instance-guided mask","author":"Wang","year":"2021"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2579259"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928895"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.063"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475343"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12549"},{"key":"ref249","article-title":"FaceShifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2019"},{"key":"ref250","article-title":"LR-GAN: Layered recursive generative adversarial networks for image generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00665"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01890"},{"key":"ref253","first-page":"841","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cadene"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152630"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00360"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.283"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"ref259","first-page":"4587","article-title":"DisPFL: Towards communication-efficient personalized federated learning via decentralized sparse training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty429"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102260"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3049224"},{"key":"ref264","article-title":"Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"MacKay"},{"key":"ref265","first-page":"10867","article-title":"Superposition of many models into one","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheung"},{"key":"ref266","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00509"},{"key":"ref269","first-page":"4189","article-title":"Recurrent highway networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zilly"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00572"},{"key":"ref271","article-title":"An attention free transformer","author":"Zhai","year":"2021"},{"key":"ref272","article-title":"Fastformer: Additive attention can be all you need","author":"Wu","year":"2021"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12060797"},{"key":"ref274","article-title":"Mega: Moving average equipped gated attention","author":"Ma","year":"2022"},{"key":"ref275","article-title":"Gated delta networks: Improving mamba2 with delta rule","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref276","first-page":"6010","article-title":"Searching for efficient transformers for language modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"So"},{"key":"ref277","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.191"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.067"},{"key":"ref280","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref281","first-page":"855","article-title":"On the computational efficiency of training neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Livni"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683721"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01145"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1016\/s0076-5392(08)x6115-6"},{"key":"ref285","first-page":"2847","article-title":"On the expressive power of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raghu"},{"key":"ref286","article-title":"Multiplicative interactions and where to find them","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jayakumar"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.007"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3331380"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref290","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman"},{"key":"ref291","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/304"},{"key":"ref293","first-page":"8119","article-title":"Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep relu networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref294","article-title":"The spectral bias of polynomial neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choraria"},{"key":"ref295","first-page":"23551","article-title":"Generalization properties of NAS under activation and skip connection search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref296","article-title":"Controlling the complexity and lipschitz constant improves polynomial nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhenyu"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref298","first-page":"854","article-title":"Parseval networks: Improving robustness to adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cisse"},{"key":"ref299","first-page":"6542","article-title":"Lipschitz-margin training: Scalable certification of perturbation invariance for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tsuzuku"},{"key":"ref300","first-page":"3839","article-title":"Lipschitz regularity of deep neural networks: Analysis and efficient estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Virmaux"},{"key":"ref301","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Szegedy"},{"key":"ref302","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref303","first-page":"3517","article-title":"Sound and complete verification of polynomial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rocamora"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.2307\/1910129"},{"key":"ref305","first-page":"29909","article-title":"Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref306","article-title":"Analysing mathematical reasoning abilities of neural models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Saxton"},{"key":"ref307","first-page":"4442","article-title":"Learning equations for extrapolation and control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sahoo"},{"key":"ref308","article-title":"How neural networks extrapolate: From feedforward to graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref309","first-page":"1328","article-title":"On the power of over-parametrization in neural networks with quadratic activation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1137\/16M1093896"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1002\/sapm192761164"},{"key":"ref312","first-page":"167","article-title":"Solutions to some functional equations and their applications to characterization of probability distributions","volume":"30","author":"Khatri","year":"1968","journal-title":"Sankhy\u0101: Indian J. Statist., Ser. A"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(94)00014-5"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1080\/03081087.2017.1346060"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1007\/s41980-018-00193-0"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1007\/BF01110298"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2020.01.005"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2006.07.008"},{"issue":"1","key":"ref319","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.jmva.2011.07.004","volume":"104","author":"Caro-Lopera","year":"2012","journal-title":"J. Multivariate Anal."},{"key":"ref320","article-title":"PolyGAN: High-order polynomial generators","author":"Chrysos","year":"2019"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10965485.pdf?arnumber=10965485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:57:04Z","timestamp":1751929024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10965485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":322,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3560423","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":[[2025,8]]}}}