{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:39:50Z","timestamp":1784925590197,"version":"3.55.0"},"reference-count":221,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2024.3506283","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T19:45:30Z","timestamp":1736451930000},"page":"2245-2264","source":"Crossref","is-referenced-by-count":252,"title":["Foundation Models Defining a New Era in Vision: A Survey and Outlook"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2407-7865","authenticated-orcid":false,"given":"Muhammad","family":"Awais","sequence":"first","affiliation":[{"name":"MBZ University of AI, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-7161","authenticated-orcid":false,"given":"Muzammal","family":"Naseer","sequence":"additional","affiliation":[{"name":"Computer Science Department and Center of Secure Cyber-Physical Security Systems, Khalifa University, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"MBZ University of AI, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9041-2214","authenticated-orcid":false,"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"MBZ University of AI, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8230-9065","authenticated-orcid":false,"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[{"name":"MBZ University of AI, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8216-1128","authenticated-orcid":false,"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-3143","authenticated-orcid":false,"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"MBZ University of AI, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref3","first-page":"7","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref4","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref5","article-title":"PaLM 2 technical report","author":"Anil","year":"2023"},{"issue":"8","key":"ref6","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref7","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref8","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref9","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref10","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref13","article-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","author":"Wu","year":"2023"},{"key":"ref14","article-title":"RefSAM: Efficiently adapting segmenting anything model for referring video object segmentation","author":"Yonglin","year":"2023"},{"key":"ref15","article-title":"Pave the way to grasp anything: Transferring foundation models for universal pick-place robots","author":"Yang","year":"2023"},{"key":"ref16","article-title":"Rsprompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model","author":"Chen","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref19","article-title":"Macaw-LLM: Multi-modal language modeling with image, video, audio, and text integration","author":"Lyu","year":"2023"},{"key":"ref20","article-title":"A bibliometric review of large language models research from 2017 to 2023","author":"Fan","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref22","article-title":"A survey for in-context learning","author":"Dong","year":"2022"},{"key":"ref23","article-title":"A comprehensive survey on pretrained foundation models: A history from bert to chatgpt","author":"Zhou","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/773"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref27","article-title":"Self-supervised multimodal learning: A survey","author":"Zong","year":"2023"},{"key":"ref28","article-title":"Vision-language models for vision tasks: A survey","author":"Jingyi","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref31","article-title":"Visual instruction tuning towards general-purpose multimodal model: A survey","author":"Huang","year":"2023"},{"key":"ref32","article-title":"A comprehensive survey on segment anything model for vision and beyond","author":"Zhang","year":"2023"},{"key":"ref33","article-title":"SegGPT: Segmenting everything in context","author":"Wang","year":"2023"},{"key":"ref34","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023"},{"key":"ref35","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref36","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"ref37","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref38","article-title":"A survey on generative diffusion model","author":"Cao","year":"2022"},{"key":"ref39","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref40","article-title":"Diffusion models: A comprehensive survey of methods and applications","author":"Yang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref43","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref44","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref46","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref47","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1167\/9.8.1037"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref55","article-title":"Classification is a strong baseline for deep metric learning","author":"Zhai","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref60","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref62","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"Huo","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref64","first-page":"3","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref68","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref69","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref70","article-title":"EVA-CLIP: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref71","article-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref72","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref75","article-title":"An inverse scaling law for clip training","author":"Li","year":"2023"},{"key":"ref76","article-title":"CLIPA-v2: Scaling CLIP training with 81.1% zero-shot imagenet accuracy within a 10,000 budget; an extra 4,000 unlocks 81.8% accuracy","author":"Li","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3390838"},{"key":"ref78","article-title":"Cream: Visually-situated natural language understanding with contrastive reading model and frozen large language models","author":"Kim","year":"2023"},{"key":"ref79","article-title":"Stone needle: A general multimodal large-scale model framework towards healthcare","author":"Liu","year":"2023"},{"key":"ref80","article-title":"FairCLIP: Social bias elimination based on attribute prototype learning and representation neutralization","author":"Wang","year":"2022"},{"key":"ref81","article-title":"Clip the bias: How useful is balancing data in multimodal learning?","author":"Alabdulmohsin","year":"2024"},{"key":"ref82","first-page":"13","article-title":"A closer look at the robustness of contrastive language-image pre-training (CLIP)","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tu"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref84","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref85","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref86","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref87","first-page":"1137","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref88","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref91","article-title":"Image as a foreign language: Beit pretraining for all vision and vision-language tasks","author":"Wang","year":"2022"},{"key":"ref92","article-title":"EVA-02: A visual representation for neon genesis","author":"Fang","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref95","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref97","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref102","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tsimpoukelli"},{"key":"ref103","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brock"},{"key":"ref104","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref105","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref106","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref107","article-title":"Language models are general-purpose interfaces","author":"Hao","year":"2022"},{"key":"ref108","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023"},{"key":"ref109","article-title":"Foundation transformers","author":"Wang","year":"2022","journal-title":"arXiv:2210.06423"},{"key":"ref110","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref111","first-page":"4","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref112","first-page":"8948","article-title":"Masked vision and language modeling for multi-modal representation learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kwon"},{"key":"ref113","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"ArXiv"},{"key":"ref114","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref115","article-title":"Image captioners are scalable vision learners too","author":"Tschannen","year":"2023"},{"key":"ref116","first-page":"31333","article-title":"A unified sequence interface for vision tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref117","first-page":"6666","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_b03425"},{"key":"ref119","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref120","first-page":"4","article-title":"PaLI: A jointly-scaled multilingual language-image model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref121","article-title":"mT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020"},{"key":"ref122","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref123","article-title":"Bridge-tower: Building bridges between encoders in vision-language representation learning","author":"Xu","year":"2022"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.40"},{"key":"ref125","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref126","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref127","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref128","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% chatGPT quality","author":"Chiang","year":"2023"},{"key":"ref129","article-title":"Taca: Upgrading your visual foundation model with task-agnostic compatible adapter","author":"Zhang","year":"2023"},{"key":"ref130","article-title":"Transfer visual prompt generator across LLMs","author":"Zhang","year":"2023"},{"key":"ref131","first-page":"32942","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dou"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref135","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref137","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"issue":"1","key":"ref138","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref139","article-title":"A length-extrapolatable transformer","author":"Sun","year":"2022"},{"key":"ref140","first-page":"4","article-title":"Masked vision and language modeling for multi-modal representation learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kwon"},{"key":"ref141","first-page":"29292","article-title":"Mass-producing failures of multimodal systems with language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref144","first-page":"3","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ordonez"},{"key":"ref145","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref148","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023"},{"key":"ref149","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref150","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref152","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023"},{"key":"ref153","article-title":"Prismer: A vision-language model with an ensemble of experts","author":"Liu","year":"2023"},{"key":"ref154","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref155","article-title":"COSA: Concatenated sample pretrained vision-language foundation model","author":"Chen","year":"2023"},{"key":"ref156","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref157","article-title":"VIMA: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref158","article-title":"MineDojo: Building open-ended embodied agents with internet-scale knowledge","author":"Fan","year":"2022"},{"key":"ref159","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"ref160","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2022"},{"key":"ref161","article-title":"GPT-4 technical report","year":"2023","journal-title":"PREPRINT"},{"key":"ref162","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Christiano"},{"key":"ref163","article-title":"LLaVAR: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"key":"ref164","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref165","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref166","article-title":"LLaMA-Adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref167","article-title":"Monkey: Image resolution and text label are important things for large multi-modal models","author":"Li","year":"2023"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref169","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref170","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref171","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref172","article-title":"Video-chatGPT: Towards detailed video understanding via large vision and language models","author":"Maaz","year":"2023"},{"key":"ref173","article-title":"Are emergent abilities of large language models a mirage?","author":"Schaeffer","year":"2023"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlp4convai-1.5"},{"key":"ref175","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","author":"Lu","year":"2023"},{"key":"ref176","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023"},{"key":"ref177","article-title":"Negative object presence evaluation (NOPE) to measure object hallucination in vision-language models","author":"Lovenia","year":"2023"},{"key":"ref178","article-title":"Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation","author":"M\u00fcndler","year":"2023"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref180","article-title":"Retrieval augmented chest X-ray report generation using openai GPT models","author":"Ranjit","year":"2023"},{"key":"ref181","article-title":"RETA-LLM: A retrieval-augmented large language model toolkit","author":"Liu","year":"2023"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref184","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref185","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.178"},{"key":"ref187","article-title":"Detecting and preventing hallucinations in large vision language models","author":"Gunjal","year":"2023"},{"key":"ref188","article-title":"Mitigating object hallucinations in large vision-language models through visual contrastive decoding","author":"Leng","year":"2023"},{"key":"ref189","article-title":"Seeing is believing: Mitigating hallucination in large vision-language models via clip-guided decoding","author":"Deng","year":"2024"},{"key":"ref190","article-title":"Skip n: A simple method to reduce hallucination in large vision-language models","author":"Han","year":"2024"},{"key":"ref191","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024"},{"key":"ref192","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref193","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref194","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref195","article-title":"QLORA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2023"},{"key":"ref196","article-title":"One-for-all: Generalized LoRA for parameter-efficient fine-tuning","author":"Chavan","year":"2023"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref198","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref200","article-title":"Sam fails to segment anything?\u2013sam-adapter: Adapting sam in underperformed scenes: Camouflage, shadow, and more","author":"Chen","year":"2023"},{"key":"ref201","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref202","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref203","first-page":"4555","article-title":"MixACM: Mixup-based robustness transfer via distillation of activated channel maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Muhammad"},{"key":"ref204","article-title":"How to jailbreak chatGPT","year":"2023"},{"key":"ref205","article-title":"Ignore previous prompt: Attack techniques for language models","author":"Perez","year":"2022"},{"key":"ref206","article-title":"Red-teaming large-language models","year":"2023"},{"key":"ref207","article-title":"More than you\u2019ve asked for: A comprehensive analysis of novel prompt injection threats to application-integrated large language models","author":"Greshake","year":"2023"},{"key":"ref208","article-title":"Are aligned neural networks adversarially aligned?","author":"Carlini","year":"2023"},{"key":"ref209","article-title":"Adversarial prompting for black box foundation models","author":"Maus","year":"2023"},{"key":"ref210","article-title":"Adversarial demonstration attacks on large language models","author":"Wang","year":"2023"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_42"},{"key":"ref212","article-title":"Attack-sam: Towards evaluating adversarial robustness of segment anything model","author":"Zhang","year":"2023"},{"key":"ref213","article-title":"On the robustness of segment anything","author":"Huang","year":"2023"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref215","article-title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","author":"Hall","year":"2023"},{"key":"ref216","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref218","article-title":"Stable diffusion v1\u20131 model card","year":"2024"},{"key":"ref219","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10834497.pdf?arnumber=10834497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:42:13Z","timestamp":1741372933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10834497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":221,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3506283","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}