{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:27Z","timestamp":1777865307947,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01738","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18703-18713","source":"Crossref","is-referenced-by-count":1,"title":["Sparse Fine-Tuning of Transformers for Generative Tasks"],"prefix":"10.1109","author":[{"given":"Wei","family":"Chen","sequence":"first","affiliation":[{"name":"Purdue University,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingxi","family":"Yu","sequence":"additional","affiliation":[{"name":"Purdue University,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Miao","sequence":"additional","affiliation":[{"name":"Purdue University,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Purdue University,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2576"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref3","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref5","article-title":"Towards monosemanticity: Decomposing language models with dictionary learning","author":"Bricken","year":"2023","journal-title":"Transformer Circuits Thread"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4171\/022-3\/69"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref8","article-title":"Large convolutional model tuning via filter subspace","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2025"},{"key":"ref9","article-title":"Graph convolution with low-rank learnable local filters","author":"Cheng","year":"2020","journal-title":"arXiv"},{"key":"ref10","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref12","article-title":"Transcoders enable fine-grained interpretable circuit analysis for language models","author":"Dunefsky","year":"2024","journal-title":"AI Alignment Forum"},{"key":"ref13","article-title":"The vendi score: A diversity evaluation metric for machine learning","author":"Friedman","year":"2022","journal-title":"arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0699"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_13"},{"key":"ref17","article-title":"Lora: Lowrank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2021"},{"key":"ref18","article-title":"Sara: High-efficient diffusion model fine-tuning with progressive sparse low-rank adaptation","author":"Hu","year":"2024","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00752"},{"key":"ref20","article-title":"Learning to customize text-to-image diffusion in diverse context","author":"Kim","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref24","article-title":"Flexprefill: A context-aware sparse attention mechanism for efficient long-sequence inference","author":"Lai","year":"2025","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29266"},{"key":"ref26","article-title":"Dora: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref27","article-title":"Unlocking efficient, scalable, and continual knowledge editing with basis-level representation finetuning","author":"Liu","year":"2025","journal-title":"arXiv"},{"key":"ref28","article-title":"Re-imagining multimodal instruction tuning: A representation view","author":"Liu","year":"2025","journal-title":"arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.243"},{"key":"ref30","article-title":"Supervised dictionary learning","volume-title":"Advances in Neural Information Processing Systems","author":"Mairal","year":"2008"},{"key":"ref31","article-title":"Sparse feature circuits: Discovering and editing interpretable causal graphs in language models","author":"Marks","year":"2024","journal-title":"arXiv"},{"key":"ref32","article-title":"Continual learning with filter atom swapping","volume-title":"International Conference on Learning Representations","author":"Miao","year":"2021"},{"key":"ref33","first-page":"3376","article-title":"Spatiotemporal joint filter decomposition in 3d convolutional neural networks","volume":"34","author":"Miao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01031"},{"key":"ref35","article-title":"Tuning timestepdistilled diffusion model using pairwise sample optimization","author":"Miao","year":"2024","journal-title":"arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01876"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/381607a0"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv"},{"key":"ref39","article-title":"Efficient source-free time-series adaptation via parameter subspace disentanglement","author":"Patel","year":"2024","journal-title":"arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","article-title":"Posterior sampling via langevin dynamics based on generative priors","author":"Purohit","year":"2024","journal-title":"arXiv"},{"key":"ref42","first-page":"4198","article-title":"Dcfnet: Deep neural network with decomposed convolutional filters","volume-title":"International Conference on Machine Learning","author":"Qiu","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3472"},{"key":"ref44","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_20"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref49","article-title":"Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders","author":"Surkov","year":"2024","journal-title":"arXiv"},{"key":"ref50","article-title":"Sparse sinkhorn attention","volume-title":"International Conference on Machine Learning","author":"Tay","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00107"},{"key":"ref52","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.57"},{"key":"ref54","article-title":"Stochastic conditional generative networks with basis decomposition","author":"Wang","year":"2019","journal-title":"arXiv"},{"key":"ref55","first-page":"17826","article-title":"Image generation using continuous filter atoms","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01208"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.726"},{"key":"ref58","article-title":"Reft: Representation finetuning for language models","author":"Wu","year":"2024","journal-title":"arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref64","article-title":"Neat: Nonlinear parameter-efficient adaptation of pretrained models","author":"Zhong","year":"2024","journal-title":"arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445018.pdf?arnumber=11445018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:08Z","timestamp":1777529588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01738","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}