{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:04Z","timestamp":1774419844862,"version":"3.50.1"},"reference-count":36,"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\/icassp49660.2025.10888636","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework"],"prefix":"10.1109","author":[{"given":"Zhenda","family":"Yu","sequence":"first","affiliation":[{"name":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Shen","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanxiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Fang","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianghao","family":"Zang","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Ban","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"TeleAI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zerui","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmei","family":"Kang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"issue":"140","key":"ref4","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"3","key":"ref6","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"ref8","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref13","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Vlap: Efficient video-language alignment via frame prompting and distilling for video question answering","author":"Wang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref16","article-title":"Crema: Multimodal compositional video reasoning via efficient modular adaptation and fusion","author":"Yu","year":"2024"},{"key":"ref17","article-title":"Instruction tuning for large language models: A survey","author":"Zhang","year":"2023"},{"key":"ref18","article-title":"Speciality vs generality: An empirical study on catastrophic forgetting in fine-tuning foundation models","author":"Lin","year":"2023"},{"key":"ref19","article-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning","author":"Luo","year":"2023"},{"key":"ref20","article-title":"Investigating the catastrophic forgetting in multimodal large language models","author":"Zhai","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35400"},{"key":"ref22","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"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref24","article-title":"Star: A benchmark for situated reasoning in real-world videos","author":"Wu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"issue":"07","key":"ref27","first-page":"11109","article-title":"Reasoning with heterogeneous graph alignment for video question answering","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Jiang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref31","first-page":"2917","article-title":"Revisiting the","volume-title":"video\" in video-language understanding,\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Buch"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref35","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref36","article-title":"Lstp: Language-guided spatial-temporal prompt learning for long-form video-text understanding","author":"Wang","year":"2024"}],"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\/10888636.pdf?arnumber=10888636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:00Z","timestamp":1774416300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888636","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}