{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:59:13Z","timestamp":1772935153582,"version":"3.50.1"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401706","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"2669-2672","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Large Vision Model Powered GUI Agent for Walmart Myassistant Application"],"prefix":"10.1109","author":[{"given":"Qixin","family":"Wang","sequence":"first","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puneet","family":"Girdhar","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaowei","family":"Hu","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Wang","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaitanya","family":"Devella","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayush","family":"Dwivedi","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlai","family":"Guo","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Terrence","family":"Liu","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manmohan","family":"Dogra","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Chen","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangwen","family":"Huang","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swati","family":"Pandey","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Balram","family":"Mirani","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diwash","family":"Pokharel","sequence":"additional","affiliation":[{"name":"University of Arkansas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Hayworth","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Walmart Global Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xintao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Arkansas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.729"},{"key":"ref2","volume-title":"On the effects of data scale on computer control agents, 2024c","author":"Li","year":"2024"},{"key":"ref3","article-title":"Gui agents with foundation models: A comprehensive survey","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Large language model-brained gui agents: A survey","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713600"},{"key":"ref6","article-title":"Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"9466","article-title":"A data-driven approach for learning to control computers","volume-title":"International conference on machine learning. PMLR","author":"Humphreys","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.702"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671646"},{"key":"ref10","article-title":"Mobileagent: enhancing mobile control via human-machine interaction and sop integration","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Multimodal web navigation with instruction-finetuned foundation models","author":"Furuta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Cognitive architectures for language agents","author":"Sumers","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref13","article-title":"The dawn of gui agent: A preliminary case study with claude 3.5 computer use","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Template matching advances and applications in image analysis","author":"Hashemi","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401706.pdf?arnumber=11401706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:24:36Z","timestamp":1772868276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401706","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}