{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T12:38:22Z","timestamp":1778589502710,"version":"3.51.4"},"reference-count":44,"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\/iros60139.2025.11246909","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"12510-12517","source":"Crossref","is-referenced-by-count":1,"title":["Enhanced Motion Forecasting with Plug-and-Play Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Katie","family":"Luo","sequence":"first","affiliation":[{"name":"Cornell University,Computer and Information Sciences Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwei","family":"Ji","sequence":"additional","affiliation":[{"name":"Waymo LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[{"name":"Waymo LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Waymo LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Xie","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dragomir","family":"Anguelov","sequence":"additional","affiliation":[{"name":"Waymo LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxing","family":"Tan","sequence":"additional","affiliation":[{"name":"Waymo LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Waymo one is now open to everyone in SF","year":"2024"},{"key":"ref2","article-title":"Autopilot and Full Self-Driving (Supervised)","year":"2024","journal-title":"Tesla"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref7","article-title":"Maptr: Structured modeling and learning for online vectorized hd map construction","author":"Liao","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref14","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref15","article-title":"Gemini: A family of highly capable multimodal models","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02258"},{"key":"ref17","first-page":"202","article-title":"Investigating the catastrophic forgetting in multimodal large language model fine-tuning","volume-title":"Conference on Parsimony and Learning","author":"Zhai"},{"key":"ref18","article-title":"Intentnet: Learning to predict intention from raw sensor data","author":"Casas","year":"2018","journal-title":"CoRL"},{"key":"ref19","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"2019","journal-title":"CoRL"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00865"},{"key":"ref21","first-page":"2553","article-title":"Prank: motion prediction based on ranking","volume":"33","author":"Biktairov","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196697"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref25","article-title":"Multiple futures prediction","volume":"32","author":"Tang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"ref28","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref31","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"CoRL"},{"key":"ref32","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41368-023-00239-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref35","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01420"},{"key":"ref37","article-title":"Motion transf. with global intention localization and local movement refinement","author":"Shi","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_7"},{"key":"ref39","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"ref41","first-page":"arXiv\u20132312","article-title":"Trajeglish: Learning the language of driving scenarios","author":"Philion","year":"2023"},{"key":"ref42","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref44","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"NeurIPS"}],"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\/11246909.pdf?arnumber=11246909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:13:57Z","timestamp":1765520037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246909","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}