{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:16Z","timestamp":1777889416356,"version":"3.51.4"},"reference-count":55,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371450"],"award-info":[{"award-number":["62371450"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00347","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3639-3649","source":"Crossref","is-referenced-by-count":0,"title":["SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Sudong","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Information Engeering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enci","family":"Liu","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianing","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University;"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engeering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University;"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00253"},{"key":"ref4","article-title":"Training diffusion models with reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Black","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref8","article-title":"Pali: A jointlyscaled multilingual language-image model","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref10","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 %* chatgpt quality"},{"key":"ref11","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chuang","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref13","first-page":"8469","article-title":"Palm-e: An embodied multimodal language model","volume-title":"International Conference on Machine Learning (ICML)","author":"Driess","year":"2023"},{"key":"ref14","author":"Elbayad","year":"2019","journal-title":"Depth-adaptive transformer"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"ref24","article-title":"Hallucinations in neural machine translation","author":"Lee","year":"2018","journal-title":"OpenReview"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref27","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Li","year":"2022"},{"key":"ref28","author":"Li","year":"2023","journal-title":"A large-scale dataset towards multi-modal multilingual instruction tuning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref32","author":"Liu","year":"2023","journal-title":"Aligning large multi-modal model with robust instruction tuning"},{"key":"ref33","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.4"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1269"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref42","volume-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref44","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02779"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref49","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"International Conference on Machine Learning (ICML)","author":"Zeng","year":"2021"},{"key":"ref50","author":"Zhang","year":"2023","journal-title":"Internlmxcomposer: A vision-language large model for advanced text-image comprehension and composition"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.120"},{"key":"ref54","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2024"},{"key":"ref55","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu","year":"2024"}],"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\/11444144.pdf?arnumber=11444144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:41Z","timestamp":1777612361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00347","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}