{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T20:00:18Z","timestamp":1785441618210,"version":"3.56.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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]]},"DOI":"10.1109\/iccv51701.2025.02009","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21635-21644","source":"Crossref","is-referenced-by-count":0,"title":["Hallucinatory Image Tokens: A Training-Free EAZY Approach to Detecting and Mitigating Object Hallucinations in LVLMs"],"prefix":"10.1109","author":[{"given":"Liwei","family":"Che","sequence":"first","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tony Qingze","family":"Liu","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Jia","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyi","family":"Qin","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Pavlovic","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["New Brunswick, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref3","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref4","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 %* chatgpt quality"},{"key":"ref5","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chuang","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref7","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.439"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref11","article-title":"Self-introspective decoding: Alleviating hallucinations for large vision-language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Huo","year":"2025"},{"key":"ref12","article-title":"Interpreting and editing vision-language representations to mitigate hallucinations","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Volcano: mitigating multimodal hallucination through self-feedback guided revision","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref19","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref24","article-title":"Towards interpreting visual information processing in vision-language models","author":"Neo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","year":"2020","journal-title":"Interpreting gpt: The logit lens"},{"key":"ref26","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref29","article-title":"Aligning large multimodal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"An 11 m -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681076"},{"key":"ref33","article-title":"Don\u2019t miss the forest for the trees: Attentional vision calibration for large vision language models","author":"Woo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref36","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","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\/11444119.pdf?arnumber=11444119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:09:18Z","timestamp":1785438558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02009","relation":{},"subject":[],"published":{"date-parts":[[2025,10]]}}}