{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:29:34Z","timestamp":1780518574245,"version":"3.54.1"},"reference-count":49,"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"}],"funder":[{"DOI":"10.13039\/501100003195","name":"Netherlands Ministry of Economic Affairs and Climate Policy","doi-asserted-by":"publisher","award":["101214398"],"award-info":[{"award-number":["101214398"]}],"id":[{"id":"10.13039\/501100003195","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00134","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1359-1368","source":"Crossref","is-referenced-by-count":1,"title":["TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning"],"prefix":"10.1109","author":[{"given":"Aritra","family":"Bhowmik","sequence":"first","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Mahdi","family":"Derakhshani","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Koelma","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki M.","family":"Asano","sequence":"additional","affiliation":[{"name":"University of Technology Nuremberg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin R.","family":"Oswald","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Honeybee: Locality-enhanced projector for multimodal 1lm","author":"Cha","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Empowering large language models on robotic manipulation with affordance prompting","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Jacob Devlin. Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01286"},{"key":"ref14","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Mixtral of experts","author":"Albert","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Alphablock: Embodied finetuning for vision-language reasoning in robot manipulation","author":"Jin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Llava-med: Training a large language-andvision assistant for biomedicine in one day","volume-title":"NeurIPS","author":"Li","year":"2023"},{"key":"ref22","author":"Li","year":"2023","journal-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref23","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref25","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Piotr Doll\u00e1r, and C Lawrence Zitnick. Microsoft coco: Common objects in context","volume-title":"ECCV","author":"Lin","year":"2014"},{"key":"ref27","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"ICLR","author":"Liu","year":"2023"},{"key":"ref28","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2019"},{"key":"ref31","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"ICLR","author":"Lu","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3406372"},{"key":"ref33","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref36","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"ICML","author":"Wang","year":"2022"},{"key":"ref40","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref42","article-title":"On the road with gpt-4v (ision): Early explorations of visual-language model on autonomous driving","author":"Wen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref47","article-title":"Mm1. 5: Methods, analysis & insights from multimodal 11 m fine-tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Internlmxcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Llavar: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023","journal-title":"arXiv preprint"}],"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\/11444213.pdf?arnumber=11444213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:56Z","timestamp":1777530176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00134","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}