{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:15:51Z","timestamp":1783340151281,"version":"3.54.6"},"reference-count":84,"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\/iros60139.2025.11246481","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"14915-14922","source":"Crossref","is-referenced-by-count":4,"title":["PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models"],"prefix":"10.1109","author":[{"given":"Dingkun","family":"Guo","sequence":"first","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Xiang","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd9461"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104848"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Rt-2: Visionlanguage-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref6","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231193710"},{"key":"ref9","article-title":"Chatgpt: Generative pre-trained transformer for conversational agents","year":"2023"},{"key":"ref10","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610090"},{"key":"ref14","article-title":"Probabilistic surface friction estimation based on visual and haptic measurements","volume-title":"CoRR","author":"Le","year":"2020"},{"key":"ref15","article-title":"Galileo: Perceiving physical object properties by integrating a physics engine with deep learning","volume":"28","author":"Wu","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.39"},{"key":"ref17","article-title":"Visual grounding of learned physical models","volume-title":"ICML","author":"Li"},{"key":"ref18","article-title":"Reasoning about physical interactions with object-oriented prediction and planning","volume-title":"International Conference on Learning Representations","author":"Janner"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.046"},{"key":"ref20","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Learning long-term visual dynamics with region proposal interaction networks","author":"Qi","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3574322\/mm1"},{"key":"ref23","article-title":"Physion: Evaluating physical prediction from vision in humans and machines","author":"Bear","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1167\/jov.23.9.5622"},{"key":"ref25","article-title":"Mind\u2019s eye: Grounded language model reasoning through simulation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.726"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref29","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref30","article-title":"Internlm-xcomposer: A visionlanguage large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref31","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023"},{"key":"ref32","article-title":"Generative pretraining in multimodality","author":"Sun","year":"2023"},{"key":"ref33","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory","author":"Zhu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref37","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref38","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref39","article-title":"An empirical study of scaling instruct-tuned large multimodal models","author":"Lu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref41","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref42","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref44","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref45","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023"},{"key":"ref46","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref47","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref48","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref52","article-title":"Planning with large language models via corrective re-prompting","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Raman"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref54","article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023"},{"key":"ref55","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref56","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref58","article-title":"Grounded decoding: Guiding text generation with grounded models for robot control","author":"Huang","year":"2023"},{"key":"ref59","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref60","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811685"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref65","first-page":"1602","article-title":"Volumetric grasping network: Real-time 6 dof grasp detection in clutter","volume-title":"Conference on Robot Learning","author":"Breyer"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561954"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00299","article-title":"6-dof graspnet: Variational grasp generation for object manipulation","volume-title":"CoRR","author":"Mousavian","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.091"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610652"},{"key":"ref72","article-title":"Contactgraspnet: Efficient 6-dof grasp generation in cluttered scenes","volume-title":"CoRR","author":"Sundermeyer","year":"2021"},{"key":"ref73","first-page":"23 192","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","volume":"35","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref74","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/70.744611"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298801"},{"key":"ref78","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref79","article-title":"Interfacing foundation models\u2019 embeddings","author":"Zou","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref81","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2019"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00228"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"}],"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\/11246481.pdf?arnumber=11246481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:34:45Z","timestamp":1766061285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246481","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}