{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:11:40Z","timestamp":1793823100126,"version":"4.6.1"},"reference-count":36,"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\/iros60139.2025.11246663","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4188-4195","source":"Crossref","is-referenced-by-count":1,"title":["Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies"],"prefix":"10.1109","author":[{"given":"Anant","family":"Garg","sequence":"first","affiliation":[{"name":"IIIT Hyderabad,Robotics Research Center,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K. Madhava","family":"Krishna","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad,Robotics Research Center,India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802498"},{"key":"ref2","first-page":"2","author":"Black","year":"2024","journal-title":"Training Diffusion Models with Reinforcement Learning"},{"key":"ref3","first-page":"1","author":"Blattmann","year":"2023","journal-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref5","first-page":"2","author":"Clark","year":"2024","journal-title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards"},{"key":"ref6","first-page":"1","author":"Ding","year":"2024","journal-title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning"},{"key":"ref7","first-page":"2","author":"Dosovitskiy","year":"2017","journal-title":"CARLA: An Open Urban Driving Simulator"},{"key":"ref8","first-page":"2","author":"Fan","year":"2023","journal-title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models"},{"key":"ref9","first-page":"2","author":"Fu","year":"2021","journal-title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning"},{"key":"ref10","first-page":"2","author":"Gao","year":"2024","journal-title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control"},{"key":"ref11","first-page":"1","author":"Gao","year":"2024","journal-title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability"},{"key":"ref12","first-page":"1","author":"Hafner","year":"2020","journal-title":"Dream to Control: Learning Behaviors by Latent Imagination"},{"key":"ref13","first-page":"1","author":"Hafner","year":"2019","journal-title":"Learning Latent Dynamics for Planning from Pixels"},{"key":"ref14","first-page":"1","author":"Hafner","year":"2022","journal-title":"Mastering Atari with Discrete World Models"},{"key":"ref15","first-page":"1","author":"Hafner","year":"2024","journal-title":"Mastering Diverse Domains through World Models"},{"key":"ref16","first-page":"2","author":"Hu","year":"2023","journal-title":"GAIA-1: A Generative World Model for Autonomous Driving"},{"key":"ref17","first-page":"1","author":"Janner","year":"2022","journal-title":"Planning with Diffusion for Flexible Behavior Synthesis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3497918"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref23","first-page":"2","author":"Mnih","year":"2013","journal-title":"Playing Atari with Deep Reinforcement Learning"},{"key":"ref24","first-page":"1","author":"Pan","year":"2022","journal-title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models"},{"key":"ref25","first-page":"2","author":"Pearce","year":"2023","journal-title":"Imitating Human Behaviour with Diffusion Models"},{"key":"ref26","first-page":"2","author":"Ren","year":"2024","journal-title":"Diffusion Policy Policy Optimization"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610519"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref30","first-page":"4","author":"Schulman","year":"2017","journal-title":"Trust Region Policy Optimization"},{"key":"ref31","first-page":"2","author":"Shah","year":"2023","journal-title":"ViNT: A Foundation Model for Visual Navigation"},{"key":"ref32","first-page":"4","author":"Song","year":"2022","journal-title":"Denoising Diffusion Implicit Models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610665"},{"key":"ref34","first-page":"2","author":"Tan","year":"2020","journal-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref36","first-page":"1","author":"Yang","year":"2024","journal-title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following"}],"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\/11246663.pdf?arnumber=11246663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:47Z","timestamp":1766061407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246663","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}