{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T18:36:45Z","timestamp":1758047805126,"version":"3.44.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/infocomwkshps65812.2025.11152896","type":"proceedings-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:28:22Z","timestamp":1757698102000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["AVLLM-Based Multimodal Reasoning Segmentation and Detection Approach for Intelligent Driving"],"prefix":"10.1109","author":[{"given":"Tantan","family":"Zhao","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Information & Communications Engineering,China"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Information & Communications Engineering,China"}]},{"given":"Zehua","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of British Columbia,Department of Electrical & Computer Engineering,Canada"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science & Technology,China"}]},{"given":"Xinyu","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Waterloo,Department of Electrical & Computer Engineering,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3292401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3307157"},{"key":"ref3","article-title":"YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles","author":"Benjumea","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3259999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref6","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Kojima"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref9","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref11","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref13","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref15","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref16","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref17","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref18","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref20","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"}],"event":{"name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","location":"London, United Kingdom","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,19]]}},"container-title":["IEEE INFOCOM 2025 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11152714\/11152715\/11152896.pdf?arnumber=11152896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T05:17:19Z","timestamp":1757740639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11152896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/infocomwkshps65812.2025.11152896","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}