{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:10:29Z","timestamp":1778051429811,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007482","name":"Arizona State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007482","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00166","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1653-1663","source":"Crossref","is-referenced-by-count":0,"title":["The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs"],"prefix":"10.1109","author":[{"given":"Tejas","family":"Anvekar","sequence":"first","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fenil","family":"Bardoliya","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavan K.","family":"Turaga","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chitta","family":"Baral","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek","family":"Gupta","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","author":"Bai","year":"2023"},{"key":"ref5","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Advances in Neural Information Processing Systems","author":"Barbu","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","article-title":"PaLM-E: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.trustnlp-main.33"},{"key":"ref11","article-title":"Commonsense-T2I challenge: Can text-to-image generation models understand commonsense?","author":"Fu","year":"2024"},{"key":"ref12","article-title":"Generalisation in humans and deep neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Geirhos","year":"2018"},{"key":"ref13","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"International Conference on Learning Representations","author":"Geirhos"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0702_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.904"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2808"},{"key":"ref19","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref20","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref27","article-title":"Seed-bench: Benchmarking multimodal llms with generative comprehension","author":"Li","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref33","article-title":"Math-Vista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu"},{"key":"ref34","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2015.00496"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","first-page":"10684","article-title":"Highresolution image synthesis with latent diffusion models","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Rombach"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00282"},{"key":"ref40","article-title":"Illusionvqa: A challenging optical illusion dataset for vision language models","author":"Shahgir","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref42","journal-title":"Gemma 3"},{"key":"ref43","year":"2025","journal-title":"Qwen2.5-VL"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref46","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00540"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1037\/a0029333"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1037\/a0029334"},{"key":"ref50","article-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution","author":"Wang","year":"2024"},{"key":"ref51","article-title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","author":"Wang","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00913"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.348"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11208962"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492508.pdf?arnumber=11492508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:10:39Z","timestamp":1778047839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00166","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}