{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T22:14:47Z","timestamp":1778278487138,"version":"3.51.4"},"reference-count":30,"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\/iros60139.2025.11247780","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"16702-16709","source":"Crossref","is-referenced-by-count":1,"title":["AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning"],"prefix":"10.1109","author":[{"given":"Kai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.115"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref3","article-title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","author":"Fu","year":"2024"},{"key":"ref4","article-title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","author":"Chu","year":"2023"},{"key":"ref5","article-title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","author":"Huang","year":"2023","journal-title":"Neural Information Processing Systems"},{"key":"ref6","article-title":"An Embodied Generalist Agent in 3D World","author":"Huang","year":"2023"},{"key":"ref7","article-title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","author":"Lu","year":"2024"},{"key":"ref8","article-title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","author":"Qi","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_27"},{"key":"ref11","article-title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs","author":"Zhang","year":"2024"},{"key":"ref12","article-title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","author":"Xing","year":"2024"},{"key":"ref13","article-title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","author":"Li","year":"2024"},{"key":"ref14","article-title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","author":"Rao","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref16","article-title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","author":"Zhu","year":"2024"},{"key":"ref17","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"ref18","article-title":"SQA3D: Situated Question Answering in 3D Scenes","author":"Ma","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref20","article-title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","author":"Chen","year":"2024"},{"key":"ref21","article-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","author":"Bai","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref24","article-title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","author":"Yu","year":"2023"},{"key":"ref25","article-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","author":"Fu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.421"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref30","article-title":"GPT-4 Technical Report","year":"2023"}],"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\/11247780.pdf?arnumber=11247780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:09Z","timestamp":1766061549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247780","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}