{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:01:18Z","timestamp":1781366478235,"version":"3.54.1"},"reference-count":43,"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\/icassp49660.2025.10888428","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":10,"title":["Lenna: Language Enhanced Reasoning Detection Assistant"],"prefix":"10.1109","author":[{"given":"Fei","family":"Wei","sequence":"first","affiliation":[{"name":"AMAP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ailing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangxiang","family":"Chu","sequence":"additional","affiliation":[{"name":"AMAP"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Bloom: A 176-bparameter open-access multilingual language model","author":"Scao","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref6","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref7","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref8","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref9","article-title":"Instructdet: Diversifying referring object detection with generalized instructions","author":"Dang","year":"2023"},{"key":"ref10","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref11","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref15","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref17","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022"},{"key":"ref18","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2022","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref20","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"NeurIPS 2021","author":"Chu","year":"2021"},{"key":"ref23","article-title":"Conditional positional encodings for vision transformers","volume-title":"ICLR 2023","author":"Chu","year":"2023"},{"key":"ref24","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":"ref25","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25261"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref34","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref38","article-title":"Grounding language models to images for multimodal generation","author":"Koh","year":"2023"},{"key":"ref39","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02561"},{"key":"ref41","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref42","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"}],"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\/10888428.pdf?arnumber=10888428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:57Z","timestamp":1774416417000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888428","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}