{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T21:11:49Z","timestamp":1783804309288,"version":"3.55.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650020","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis"],"prefix":"10.1109","author":[{"given":"Aishik","family":"Nagar","sequence":"first","affiliation":[{"name":"ASUS Global Pte. Ltd.,ASUS Intelligent Cloud Services (AICS),Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shantanu","family":"Jaiswal","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheston","family":"Tan","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref4","first-page":"23 716","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":"ref5","article-title":"BLIP-2: Boot-strapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref7","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":"ref8","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref9","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref10","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref13","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.734"},{"key":"ref15","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref16","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"22 199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref21","first-page":"17 427","article-title":"PTR: A benchmark for part-based conceptual, relational, and physical reasoning","author":"Hong","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","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"},{"key":"ref23","article-title":"Holistic evaluation of language models","author":"Liang","year":"2022"},{"key":"ref24","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022"},{"key":"ref25","article-title":"Large language models still can\u2019t plan (a benchmark for LLMs on planning and reasoning about change)","author":"Valmeekam","year":"2022"},{"key":"ref26","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref28","article-title":"Dissecting zero- shot visual reasoning capabilities in vision and language models","author":"Nagar","journal-title":"The Second Tiny Papers Track at ICLR 2024."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref30","article-title":"ShapeWorld \u2013 a new test methodology for multimodal language understanding","author":"Kuhnle","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00546"},{"key":"ref32","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650020.pdf?arnumber=10650020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:55:13Z","timestamp":1725944113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650020","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}