{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:15Z","timestamp":1778048475941,"version":"3.51.4"},"reference-count":55,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00408","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4190-4200","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction"],"prefix":"10.1109","author":[{"given":"Ce","family":"Zhang","sequence":"first","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yale","family":"Song","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruta","family":"Desai","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael Louis","family":"Iuzzolino","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Tighe","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gedas","family":"Bertasius","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satwik","family":"Kottur","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref7","article-title":"Egoplan-bench: Benchmarking egocentric embodied planning with multimodal large language models","author":"Chen","year":"2023"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","article-title":"Better & faster large language models via multi-token prediction","author":"Gloeckle","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref14","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_25"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref17","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00945"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref24","article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023"},{"key":"ref25","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.122"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.98"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1090"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01780"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_32"},{"key":"ref34","article-title":"Schema: State changes matter for procedure planning in instructional videos","author":"Niu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"ref36","article-title":"Egovideo: Exploring egocentric foundation model and downstream adaptation","author":"Pei","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref41","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00119"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01425"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"ref46","article-title":"Octopus: Embodied vision-language programmer from environmental feedback","author":"Yang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00295"},{"key":"ref51","article-title":"Antgpt: Can large language models help longterm action anticipation from videos?","author":"Zhao","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref54","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"}],"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\/11492137.pdf?arnumber=11492137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:05:35Z","timestamp":1778047535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00408","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}