{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T10:17:47Z","timestamp":1789294667363,"version":"build-2803163510"},"reference-count":54,"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\/iccv51701.2025.00324","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3390-3400","source":"Crossref","is-referenced-by-count":1,"title":["FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization"],"prefix":"10.1109","author":[{"given":"Hao Mark","family":"Chen","sequence":"first","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shell Xu","family":"Hu","sequence":"additional","affiliation":[{"name":"Samsung AI Center,Cambridge,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Hospedales","sequence":"additional","affiliation":[{"name":"Samsung AI Center,Cambridge,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxiang","family":"Fan","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Ainsworth","year":"2022","journal-title":"Git re-basin: Merging models modulo permutation symmetries"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref3","volume-title":"Code alpaca: An instruction-following llama model for code generation","author":"Chaudhary","year":"2023"},{"key":"ref4","author":"Chen","year":"2021","journal-title":"Evaluating large language models trained on code"},{"key":"ref5","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International conference on machine learning","author":"Chen","year":"2018"},{"key":"ref6","first-page":"2039","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"ref10","author":"Goodfellow","year":"2014","journal-title":"Qualitatively characterizing neural network optimization problems"},{"key":"ref11","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"issue":"2","key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref13","author":"Face","year":"2024","journal-title":"Open LLM Leaderboard"},{"key":"ref14","author":"Ilharco","year":"2022","journal-title":"Editing models with task arithmetic"},{"key":"ref15","author":"Izmailov","year":"2018","journal-title":"Averaging weights leads to wider optima and better generalization"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref19","first-page":"53","article-title":"Block-coordinate frank-wolfe optimization for structural svms","volume-title":"International Conference on Machine Learning","author":"Lacoste-Julien","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref22","author":"Li","year":"2023","journal-title":"Loftq: Lora-fine-tuning-aware quantization for large language models"},{"key":"ref23","author":"Liu","year":"2024","journal-title":"Dare: Diversity-aware model merging for sparse-to-dense mixture-of-experts"},{"key":"ref24","article-title":"Towards impartial multi-task learning","author":"Liu","year":"2021","journal-title":"iclr"},{"key":"ref25","author":"Liu","year":"2023","journal-title":"Resolving interference when merging models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref27","author":"Liu","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"ref28","first-page":"78905","article-title":"Twin-merging: Dynamic integration of modular expertise in model merging","volume":"37","author":"Lu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2308"},{"key":"ref32","author":"Mammen","year":"2021","journal-title":"Federated learning: Opportunities and challenges"},{"key":"ref33","author":"Mitchell","year":"2022","journal-title":"Editing models with task arithmetic"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref35","author":"Prakash","year":"2023","journal-title":"Unified model for image, video, audio and language tasks"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref37","author":"Singh","year":"2021","journal-title":"Merging models with fisher-weighted averaging"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"ref39","first-page":"8728","article-title":"Adashare: Learning what to share for efficient deep multi-task learning","volume":"33","author":"Sun","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","author":"Tang","year":"2023","journal-title":"Concrete subspace learning based interference elimination for multi-task model fusion"},{"key":"ref41","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref43","author":"Wang","year":"2024","journal-title":"Localizing task information for improved model merging and compression"},{"key":"ref44","author":"Wang","year":"2022","journal-title":"lo-fi: distributed fine-tuning without communication"},{"key":"ref45","author":"Wei","year":"2025","journal-title":"Modeling multi-task model merging as adaptive projective gradient descent"},{"key":"ref46","author":"Wortsman","year":"2022","journal-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0310"},{"key":"ref49","volume-title":"Model merging in 11 ms, mllms, and beyond: Methods, theories, applications and opportunities","author":"Yang"},{"key":"ref50","author":"Yang","year":"2023","journal-title":"Adamerging: Adaptive model merging for multi-task learning"},{"key":"ref51","author":"Yang","year":"2024","journal-title":"Representation surgery for multi-task model merging"},{"key":"ref52","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","journal-title":"Advances in neural information processing systems"},{"key":"ref53","author":"Yu","year":"2024","journal-title":"Unleashing the power of multitask learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras"},{"key":"ref54","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in neural information processing systems"}],"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\/11445818.pdf?arnumber=11445818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:03Z","timestamp":1777530063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00324","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}