{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:23Z","timestamp":1778048303768,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00766","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7935-7944","source":"Crossref","is-referenced-by-count":0,"title":["SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination"],"prefix":"10.1109","author":[{"given":"Sangha","family":"Park","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungryong","family":"Yoo","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisoo","family":"Mok","sequence":"additional","affiliation":[{"name":"Daegu Gyeongbuk Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref2","author":"Bricken","year":"2023","journal-title":"Towards Monosemanticity: Decomposing Language Models With Dictionary Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref4","article-title":"Do you keep an eye on what i ask? mitigating multimodal hallucination via attention-guided ensemble decoding","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Cho"},{"key":"ref5","article-title":"Sparse autoencoders find highly interpretable features in language models","author":"Cunningham","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","author":"Daujotas","year":"2024","journal-title":"Case study: Interpreting, Manipulating, and Controlling CLIP with sparse autoencoders"},{"key":"ref8","author":"Elhage","year":"2022","journal-title":"Toy models of superposition"},{"key":"ref9","article-title":"Do i know this entity? knowledge awareness and hallucinations in language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ferrando"},{"key":"ref10","article-title":"Scaling and evaluating sparse autoencoders","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref12","article-title":"Self-introspective decoding: Alleviating hallucinations for large vision-language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Huo"},{"key":"ref13","article-title":"Interpreting and editing vision-language representations to mitigate hallucinations","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Jiang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02328"},{"key":"ref15","article-title":"See what you are told: Visual attention sink in large multimodal models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref17","author":"Li","year":"2024","journal-title":"Llava-next: Stronger llms supercharge multimodal capabilities in the wild"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref19","author":"Li","year":"2025","journal-title":"The hidden life of tokens: Reducing hallucination of large vision-language models via visual information steering"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.blackboxnlp-1.19"},{"key":"ref21","article-title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref24","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref26","article-title":"Reducing hallucinations in large vision-language models via latent space steering","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu"},{"key":"ref27","author":"Lou","year":"2025","journal-title":"Sae-v: Interpreting multimodal models for enhanced alignment"},{"key":"ref28","author":"Olah","year":"2022","journal-title":"Mechanistic interpretability, variables, and the importance of interpretable bases"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00024.001","article-title":"Zoom in: An introduction to circuits","volume-title":"Distill","author":"Olah","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.58809\/qaig7530"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02783"},{"key":"ref36","article-title":"Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet","author":"Templeton","year":"2024","journal-title":"Transformer Circuits Thread"},{"key":"ref37","article-title":"Activation addition: Steering language models without optimization","author":"Turner","year":"2023"},{"key":"ref38","article-title":"MLLM can see? dynamic correction decoding for hallucination mitigation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref39","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref40","article-title":"Understanding and mitigating hallucination in large vision-language models via modular attribution and intervention","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Yang"},{"key":"ref41","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023"},{"key":"ref42","author":"Zhang","year":"2024","journal-title":"Large multi-modal models can interpret features in large multi-modal models"},{"key":"ref43","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhou"},{"key":"ref44","article-title":"Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding","author":"Zhu","year":"2024"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491964.pdf?arnumber=11491964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:24Z","timestamp":1778046804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00766","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}