{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:33Z","timestamp":1777865433987,"version":"3.51.4"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00770","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8219-8229","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Input-Adaptive Inference for Efficient VLN"],"prefix":"10.1109","author":[{"given":"Dongwoo","family":"Kang","sequence":"first","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akhil","family":"Perincherry","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Coalson","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aiden","family":"Gabriel","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lee","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanghyun","family":"Hong","sequence":"additional","affiliation":[{"name":"Oregon State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327494"},{"key":"ref4","article-title":"Post training 4-bit quantization of convolutional networks for rapiddeployment","volume":"32","author":"Banner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01540"},{"key":"ref10","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref12","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref14","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref16","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref17","article-title":"Reducing transformer depth on demand with structured dropout","author":"Fan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref20","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00400"},{"key":"ref23","article-title":"Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"International Conference on Learning Representations","author":"Hendrycks","year":"2019"},{"key":"ref28","first-page":"17","article-title":"Revisiting pruning at initialization through the lens of ramanujan graph","author":"Hoang","year":"2023","journal-title":"ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref31","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"International Conference on Learning Representations","author":"Huang","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref34","first-page":"3301","article-title":"Shallow-deep networks: Understanding and mitigating network overthinking","volume-title":"International conference on machine learning","author":"Kaya","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref38","article-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref40","article-title":"Relaxed quantization for discretized neural networks","author":"Louizos","year":"2018","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref42","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"7357","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","volume":"34","author":"Moudgil","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning","author":"Nagel","year":"2020"},{"key":"ref45","first-page":"26326","article-title":"Gradientfree structured pruning with unlabeled data","volume-title":"International Conference on Machine Learning","author":"Nova","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00364"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref50","article-title":"P4q: Learning to prompt for quantization in visual-language models","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01038"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref53","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref54","article-title":"Mixed precision dnns: All you need is a good parametrization","author":"Uhlich","year":"2019","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Efficientvlm: Fast and accurate vision-language models via knowledge distillation and modal-adaptive pruning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref59","article-title":"Sim-to-real transfer via 3d feature fields for vision-and-language navigation","author":"Wang","year":"2024","journal-title":"CoRL"},{"key":"ref60","article-title":"Last-mile embodied visual navigation","author":"Wasserman","year":"2023","journal-title":"CoRL"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1803"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref64","article-title":"Humanoidpano: Hybrid spherical panoramiclidar cross-modal perception for humanoid robots","author":"Zhang","year":"2025","journal-title":"arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref67","first-page":"42915","article-title":"Learning unforeseen robustness from out-of-distribution data using equivariant domain translator","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Zhu","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00364"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443508.pdf?arnumber=11443508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:32:33Z","timestamp":1777530753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00770","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}