{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T18:09:18Z","timestamp":1783534158261,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["2024M071077003"],"award-info":[{"award-number":["2024M071077003"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62407012"],"award-info":[{"award-number":["62407012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755724","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"5020-5029","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0192-0967","authenticated-orcid":false,"given":"Shibo","family":"Sun","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5885-0794","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2270-3378","authenticated-orcid":false,"given":"Donglin","family":"Di","sequence":"additional","affiliation":[{"name":"Li Auto, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3603-5581","authenticated-orcid":false,"given":"Mingjie","family":"Wei","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2079-1252","authenticated-orcid":false,"given":"Lanshun","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5981-4752","authenticated-orcid":false,"given":"Wei-Nan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-9542","authenticated-orcid":false,"given":"Dechen","family":"Zhan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-1672","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9472-7152","authenticated-orcid":false,"given":"Lei","family":"Fan","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, et al.","author":"Ahn Michael","year":"2024","unstructured":"Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, et al., 2024. Autort: Embodied foundation models for large scale orchestration of robotic agents. arXiv preprint arXiv:2401.12963 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning. In The Twelfth International Conference on Learning Representations.","author":"Brahman Faeze","year":"2024","unstructured":"Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D Hwang, Xiang Lorraine Li, Hirona Jacqueline Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, and Yejin Choi. 2024. PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"e_1_3_2_1_5_1","volume-title":"Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Alex Schwing, and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems, Vol. 34 (2021), 17864-17875."},{"key":"e_1_3_2_1_6_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Nvlm: Open frontier-class multimodal llms. arXiv preprint arXiv:2409.11402","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuolin Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2024. Nvlm: Open frontier-class multimodal llms. arXiv preprint arXiv:2409.11402 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al., 2023. Palm-e: An embodied multimodal language model. (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Identifying the defective: Detecting damaged grains for cereal appearance inspection","author":"Fan Lei","unstructured":"Lei Fan, Yiwen Ding, Dongdong Fan, Yong Wu, Maurice Pagnucco, and Yang Song. 2023a. Identifying the defective: Detecting damaged grains for cereal appearance inspection. In ECAI. IOS Press, 660-667."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3338517"},{"key":"e_1_3_2_1_11_1","volume-title":"GrainBrain: Multiview Identification and Stratification of Defective Grain Kernels","author":"Fan Lei","year":"2025","unstructured":"Lei Fan, Dongdong Fan, Yiwen Ding, Yong Wu, Donglin Di, Maurice Pagnucco, and Yang Song. 2025a. GrainBrain: Multiview Identification and Stratification of Defective Grain Kernels. IEEE Transactions on Industrial Informatics (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02376"},{"key":"e_1_3_2_1_13_1","unstructured":"Roya Firoozi Johnathan Tucker Stephen Tian Anirudha Majumdar Jiankai Sun Weiyu Liu Yuke Zhu Shuran Song Ashish Kapoor Karol Hausman et al. 2023. Foundation models in robotics: Applications challenges and the future. The International Journal of Robotics Research (2023) 02783649241281508."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13646"},{"key":"e_1_3_2_1_15_1","first-page":"79081","article-title":"Leveraging pre-trained large language models to construct and utilize world models for model-based task planning","volume":"36","author":"Guan Lin","year":"2023","unstructured":"Lin Guan, Karthik Valmeekam, Sarath Sreedharan, and Subbarao Kambhampati. 2023. Leveraging pre-trained large language models to construct and utilize world models for model-based task planning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 79081-79094.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence Vol. 45 1 (2022) 87-110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"e_1_3_2_1_18_1","volume-title":"Counterfactual planning in AGI systems. arXiv preprint arXiv:2102.00834","author":"Holtman Koen","year":"2021","unstructured":"Koen Holtman. 2021. Counterfactual planning in AGI systems. arXiv preprint arXiv:2102.00834 (2021)."},{"key":"e_1_3_2_1_19_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 9118-9147","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022a. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning. PMLR, 9118-9147."},{"key":"e_1_3_2_1_21_1","unstructured":"Wenlong Huang Fei Xia Ted Xiao Harris Chan Jacky Liang Pete Florence Andy Zeng Jonathan Tompson Igor Mordatch Yevgen Chebotar et al. 2022b. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al., 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Conference on Robot Learning. PMLR, 80-93","author":"Li Chengshu","year":"2023","unstructured":"Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Mart\u00edn-Mart\u00edn, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun, et al., 2023. Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In Conference on Robot Learning. PMLR, 80-93."},{"key":"e_1_3_2_1_24_1","volume-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895","author":"Li Feng","year":"2024","unstructured":"Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024c. Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Mini-gemini: Mining the potential of multi-modality vision language models. arXiv preprint arXiv:2403.18814","author":"Li Yanwei","year":"2024","unstructured":"Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, and Jiaya Jia. 2024b. Mini-gemini: Mining the potential of multi-modality vision language models. arXiv preprint arXiv:2403.18814 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_1_27_1","volume-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575","author":"Lin Ziyi","year":"2023","unstructured":"Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, et al., 2023. Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_29_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024b. LLaVA-NeXT: Improved reasoning OCR and world knowledge."},{"key":"e_1_3_2_1_30_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"e_1_3_2_1_32_1","volume-title":"STRUX: An LLM for Decision-Making with Structured Explanations. arXiv preprint arXiv:2410.12583","author":"Lu Yiming","year":"2024","unstructured":"Yiming Lu, Yebowen Hu, Hassan Foroosh, Wei Jin, and Fei Liu. 2024. STRUX: An LLM for Decision-Making with Structured Explanations. arXiv preprint arXiv:2410.12583 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Lu Yujie","year":"2023","unstructured":"Yujie Lu, Pan Lu, Zhiyu Chen, Wanrong Zhu, Xin Eric Wang, and William Yang Wang. 2023. Multimodal procedural planning via dual text-image prompting. arXiv preprint arXiv:2305.01795 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Feast your eyes: Mixture-of-resolution adaptation for multimodal large language models. arXiv preprint arXiv:2403.03003","author":"Luo Gen","year":"2024","unstructured":"Gen Luo, Yiyi Zhou, Yuxin Zhang, Xiawu Zheng, Xiaoshuai Sun, and Rongrong Ji. 2024. Feast your eyes: Mixture-of-resolution adaptation for multimodal large language models. arXiv preprint arXiv:2403.03003 (2024)."},{"key":"e_1_3_2_1_35_1","first-page":"25081","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu Yao","year":"2023","unstructured":"Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, and Ping Luo. 2023. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems, Vol. 36 (2023), 25081-25094.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","unstructured":"OpenAI. 2023. GPT-4o System Card."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"e_1_3_2_1_38_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"Tianhe Ren Qing Jiang Shilong Liu Zhaoyang Zeng Wenlong Liu Han Gao Hongjie Huang Zhengyu Ma Xiaoke Jiang Yihao Chen et al. 2024a. Grounding dino 1.5: Advance the'' edge'' of open-set object detection. arXiv preprint arXiv:2405.10300 (2024)."},{"key":"e_1_3_2_1_40_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et al. 2024b. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"FLAP: Flow-adhering planning with constrained decoding in LLMs. arXiv preprint arXiv:2403.05766","author":"Roy Shamik","year":"2024","unstructured":"Shamik Roy, Sailik Sengupta, Daniele Bonadiman, Saab Mansour, and Arshit Gupta. 2024. FLAP: Flow-adhering planning with constrained decoding in LLMs. arXiv preprint arXiv:2403.05766 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00779"},{"key":"e_1_3_2_1_43_1","volume-title":"Conference on robot learning. PMLR, 492-504","author":"Shah Dhruv","year":"2023","unstructured":"Dhruv Shah, B\u0142a\u017cej Osi\u0144ski, Sergey Levine, et al., 2023. Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action. In Conference on robot learning. PMLR, 492-504."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30006"},{"key":"e_1_3_2_1_46_1","unstructured":"Tom Silver Varun Hariprasad Reece S Shuttleworth Nishanth Kumar Tom\u00e1s Lozano-P\u00e9rez and Leslie Pack Kaelbling. 2022. PDDL planning with pretrained large language models. In NeurIPS 2022 foundation models for decision making workshop."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01082"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"e_1_3_2_1_50_1","volume-title":"Actplan-1k: Benchmarking the procedural planning ability of visual language models in household activities. arXiv preprint arXiv:2410.03907","author":"Su Ying","year":"2024","unstructured":"Ying Su, Zhan Ling, Haochen Shi, Jiayang Cheng, Yauwai Yim, and Yangqiu Song. 2024. Actplan-1k: Benchmarking the procedural planning ability of visual language models in household activities. arXiv preprint arXiv:2410.03907 (2024)."},{"key":"e_1_3_2_1_51_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_53_1","volume-title":"Jian Wang, and Wenjie Li.","author":"Wang Hanlin","year":"2024","unstructured":"Hanlin Wang, Chak Tou Leong, Jian Wang, and Wenjie Li. 2024b. E2CL: Exploration-based Error Correction Learning for Embodied Agents. arXiv preprint arXiv:2409.03256 (2024)."},{"key":"e_1_3_2_1_54_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"e_1_3_2_1_57_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_58_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang et al. 2024a. Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wu Zhongze","year":"2024","unstructured":"Zhongze Wu, Hongyan Xu, Yitian Long, Shan You, Xiu Su, Jun Long, Yueyi Luo, and Chang Xu. 2024b. Detecting Any instruction-to-answer interaction relationship: Universal Instruction-to-Answer Navigator for Med-VQA. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_60_1","unstructured":"Le Xue Manli Shu Anas Awadalla Jun Wang An Yan Senthil Purushwalkam Honglu Zhou Viraj Prabhu Yutong Dai Michael S Ryoo et al. 2024. xgen-mm (blip-3): A family of open large multimodal models. arXiv preprint arXiv:2408.08872 (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3563775"},{"key":"e_1_3_2_1_62_1","volume-title":"Learning Adaptive Lighting via Channel-Aware Guidance. arXiv preprint arXiv:2412.01493","author":"Yang Qirui","year":"2024","unstructured":"Qirui Yang, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Bo Li, Huanjing Yue, and Jingyu Yang. 2024. Learning Adaptive Lighting via Channel-Aware Guidance. arXiv preprint arXiv:2412.01493 (2024)."},{"key":"e_1_3_2_1_63_1","volume-title":"DSDNet: Raw Domain Demoir\\'eing via Dual Color-Space Synergy. arXiv preprint arXiv:2504.15756","author":"Yang Qirui","year":"2025","unstructured":"Qirui Yang, Fangpu Zhang, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue, and Jingyu Yang. 2025b. DSDNet: Raw Domain Demoir\\'eing via Dual Color-Space Synergy. arXiv preprint arXiv:2504.15756 (2025)."},{"key":"e_1_3_2_1_64_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_65_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024b. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_66_1","volume-title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning. arXiv preprint arXiv:2407.05047","author":"Zhang Min","year":"2024","unstructured":"Min Zhang, Xian Fu, Jianye Hao, Peilong Han, Hao Zhang, Lei Shi, Hongyao Tang, and Yan Zheng. 2024a. MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning. arXiv preprint arXiv:2407.05047 (2024)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610065"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00912"},{"key":"e_1_3_2_1_69_1","volume-title":"Conference on Robot Learning. PMLR, 2165-2183","author":"Zitkovich Brianna","year":"2023","unstructured":"Brianna Zitkovich, Tianhe Yu, Sichun Xu, Peng Xu, Ted Xiao, Fei Xia, Jialin Wu, Paul Wohlhart, Stefan Welker, Ayzaan Wahid, et al., 2023. Rt-2: Vision-language-action models transfer web knowledge to robotic control. In Conference on Robot Learning. PMLR, 2165-2183."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:01:35Z","timestamp":1765339295000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3755724","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755724","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}