{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:07:49Z","timestamp":1778080069785,"version":"3.51.4"},"reference-count":85,"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\/iros60139.2025.11245817","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15808-15815","source":"Crossref","is-referenced-by-count":2,"title":["GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning"],"prefix":"10.1109","author":[{"given":"Huy Hoang","family":"Nguyen","sequence":"first","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Vuong","sequence":"additional","affiliation":[{"name":"MBZUAI,Department of Computer Vision,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Reid","sequence":"additional","affiliation":[{"name":"MBZUAI,Department of Computer Vision,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh Nhat","family":"Vu","sequence":"additional","affiliation":[{"name":"TU Wien,Automation & Control Institute,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811568"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA48506.2021.9561398","article-title":"End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from rgb","volume-title":"ICRA","author":"Ainetter"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3328964"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3640732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref8","article-title":"M2t2: Multi-task masked transformer for object-centric pick and place","volume-title":"CoRL","author":"Yuan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref10","article-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","author":"Yuan","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10802256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128811"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref17","article-title":"Introducing ChatGPT","journal-title":"Software"},{"key":"ref18","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"CoRL","author":"Shridhar"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref20","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref22","article-title":"Langrasp: Using large language models for semantic object grasping","author":"Mirjalili","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref24","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681173"},{"key":"ref26","article-title":"Robomamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024"},{"key":"ref27","article-title":"Jamba: A hybrid transformer-mamba language model","author":"Lieber","year":"2024"},{"key":"ref28","article-title":"Res-vmamba: Fine-grained food category visual classification using selective state space models with deep residual learning","author":"Chen","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3407111"},{"key":"ref30","article-title":"S 2mamba: A spatial-spectral state space model for hyperspectral image classification","author":"Wang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3414293"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e38495"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00176"},{"key":"ref34","article-title":"Pointmamba: A simple state space model for point cloud analysis","author":"Liang","year":"2024"},{"key":"ref35","article-title":"Pointramba: A hybrid transformer-mamba framework for point cloud analysis","author":"Wang","year":"2024"},{"key":"ref36","article-title":"Mail: Improving imitation learning with mamba","author":"Jia","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907124"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594116"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3174274"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989191"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3406191"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145064"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3413164"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196740"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_21"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812360"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3488774"},{"key":"ref56","article-title":"Hifi-cs: Towards open vocabulary visual grounding for robotic grasping using vision-language models","author":"Bhat","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref59","article-title":"Cross-modal feature alignment and fusion for composed image retrieval","volume-title":"CVPR Workshops","author":"Wan"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3539193"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3458281"},{"key":"ref62","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref63","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref64","article-title":"Plainmamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref66","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref69","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024"},{"key":"ref70","article-title":"Ml-mamba: Efficient multi-modal large language model utilizing mamba-2","author":"Huang","year":"2024"},{"key":"ref71","article-title":"A survey on vision mamba: Models, applications and challenges","author":"Xu","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3243920"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref74","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref76","article-title":"Mambadfuse: A mamba-based dual-phase model for multi-modality image fusion","author":"Li","year":"2024"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1910"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1582"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2023.102970"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245817.pdf?arnumber=11245817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:11Z","timestamp":1766061311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245817","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}