{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:20Z","timestamp":1764399080648,"version":"3.46.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249019","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1374-1379","source":"Crossref","is-referenced-by-count":0,"title":["Herald: Democratizing Compositional Reasoning for Visual Tasks without Any Training"],"prefix":"10.1109","author":[{"given":"Guan-Yuan","family":"Tan","sequence":"first","affiliation":[{"name":"School of Information Technology, Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arghya","family":"Pal","sequence":"additional","affiliation":[{"name":"School of Information Technology, Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sailaja","family":"Rajanala","sequence":"additional","affiliation":[{"name":"School of Information Technology, Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rapha\u00ebl C.-W.","family":"Phan","sequence":"additional","affiliation":[{"name":"School of Information Technology, Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee-Ming","family":"Ting","sequence":"additional","affiliation":[{"name":"School of Information Technology, Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref3","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","author":"Lu","year":"2024","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"ref5","article-title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion","author":"Dongfu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29924"},{"key":"ref7","article-title":"Visual programming: Compositional visual reasoning without training. 2023 ieee","author":"Tanmay","year":"2022","journal-title":"CVPR"},{"journal-title":"Mixtral of experts","year":"2024","author":"Q.","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01259"},{"key":"ref10","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"He","year":"2021","journal-title":"ICLR"},{"issue":"70","key":"ref11","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","article-title":"Language models are few-shot learners","author":"Tom B","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref14","article-title":"Ledits: Real image editing with ddpm inversion and semantic guidance","author":"Tsaban","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume":"36","author":"Dongxu","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Wonjae","year":"2021","journal-title":"ICML, PMLR"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Junnan","year":"2022","journal-title":"ICML, PMLR."},{"key":"ref18","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Junnan","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Plug-and-play vqa: Zeroshot vqa by conjoining large pretrained models with zero training","author":"Huat","year":"2022","journal-title":"arXiv preprint"},{"volume-title":"Mixtral-8\u00d77b","year":"2023","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref23","first-page":"770","article-title":"Deep residual learning for image recognition","author":"Kaiming","year":"2016","journal-title":"CVPR"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/978-3-030-05318-5_6","volume-title":"Automated machine learning","author":"Feurer","year":"2019"},{"key":"ref25","first-page":"1946","article-title":"Auto-keras: An efficient neural architecture search system","author":"Haifeng","year":"2019","journal-title":"SIGKDD"},{"journal-title":"Meta-Llama, Llama 3","year":"2024","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"ref28","first-page":"3195","article-title":"Ok-vqa: A visual question answering benchmark requiring external knowledge","author":"Kenneth","year":"2019","journal-title":"CVPR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref30","first-page":"24824","article-title":"Chain-ofthought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref31","article-title":"A corpus for reasoning about natural language grounded in photographs","author":"Alane","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249019.pdf?arnumber=11249019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:49:55Z","timestamp":1764398995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249019","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}