{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:55:23Z","timestamp":1784138123687,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888427","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning"],"prefix":"10.1109","author":[{"given":"Yuqi","family":"Pang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqin","family":"Tu","sequence":"additional","affiliation":[{"name":"University of California,Computer and Science Engineering,Santa Cruz,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Cao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Chatgpt","year":"2023"},{"key":"ref2","author":"Zhang","year":"2022","journal-title":"Opt: Open pre-trained transformer language models"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref4","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref5","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Sight beyond text: Multi-modal training enhances llms in truthfulness and ethics","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following","author":"Tu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.479"},{"key":"ref9","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref10","author":"Dai","year":"2023","journal-title":"Instructblip: Towards general purpose vision-language models with instruction tuning"},{"key":"ref11","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref13","author":"Su","year":"2022","journal-title":"Language models can see: Plugging visual controls in text generation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44696-2_39"},{"key":"ref15","author":"Berrios","year":"2023","journal-title":"Towards language models that can see: Computer vision through the lens of natural language"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01281"},{"key":"ref17","first-page":"21548","article-title":"A contrastive framework for neural text generation","volume":"35","author":"Su","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","author":"Chuang","year":"2023","journal-title":"Dola: Decoding by contrasting layers improves factuality in large language models"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","author":"Menon","year":"2022","journal-title":"Visual classification via description from large language models"},{"key":"ref21","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","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref23","author":"Zhu","year":"2023","journal-title":"Language-bind: Extending video-language pretraining to n-modality by language-based semantic alignment"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref27","author":"Fu","year":"2023","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888427.pdf?arnumber=10888427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:40Z","timestamp":1774416100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888427","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}