{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:38Z","timestamp":1777865438669,"version":"3.51.4"},"reference-count":53,"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":["U21A20518,U23A20341,62272157"],"award-info":[{"award-number":["U21A20518,U23A20341,62272157"]}],"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\/iccv51701.2025.00221","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2292-2302","source":"Crossref","is-referenced-by-count":0,"title":["AVAM: A Universal Training-Free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-Image Question Answering"],"prefix":"10.1109","author":[{"given":"Kang","family":"Zeng","sequence":"first","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guojin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Cheng","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","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":"Deepseek 1lm: Scaling opensource language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01311"},{"key":"ref8","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref14","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref17","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"GLM","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Free video-llm: Prompt-guided visual perception for efficient training-free video 11 ms","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref20","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01050"},{"key":"ref27","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1250"},{"key":"ref31","article-title":"Multi-stage vision token dropping: Towards efficient multimodal large language model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref33","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref38","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Qwen2 technical report","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Muirbench: A comprehensive benchmark for robust multi-image understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Valid: Mitigating the hallucination of large vision language models by visual layer fusion contrastive decoding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01843"},{"key":"ref46","article-title":"mplug-owl3: Towards long image-sequence understanding in multimodal large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref49","article-title":"[cls] attention is all you need for trainingfree visual token pruning: Make vlm inference faster","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Token-level correlation-guided compression for efficient multimodal document understanding","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Sparsevlm: Visual token sparsification for efficient vision-language model inference","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01278"}],"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\/11444624.pdf?arnumber=11444624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:33:01Z","timestamp":1777530781000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00221","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}