The DOI matches its Crossref record; 154 of the 154 references it cites were found in a registry or an index.
Flamingo: A Visual Language Model for Few-Shot Learning
Abstract
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of our models, exploring and measuring their ability to rapidly adapt to a variety of image and video tasks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer, captioning tasks, which evaluate the ability to describe a scene or an event, and close-ended tasks such as multiple-choice visual question-answering. For tasks lying anywhere on this spectrum, a single Flamingo model can achieve a new state of the art with few-shot learning, simply by prompting the model with task-specific examples. On numerous benchmarks, Flamingo outperforms models fine-tuned on thousands of times more task-specific data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“vision-language models (VLMs) such as VilBERT 19 and Flamingo 2 combine a language model with an image encoder and are trained on a multi-modal corpus of text-image pairs.This enables them to predict how a given sequence of words will continue in the context of a given image.”
From Talking about Large Language Models (2024) · cites this paper as [2]
In the citing paper
“the latest generation of language models are multimodal, allowing interleaved image and text input (OpenAI, 2023a; Alayrac et al., 2022; Team et al., 2023; Li et al., 2023b)”
From Cognitive Architectures for Language Agents (2023) · cites this paper as Alayrac et al., 2022
In the citing paper
“The Switch Transformer [201] was one of the first MoE-based Transformers, activating experts selectively in each layer, reducing computational overhead while outperforming dense Transformers in NLP tasks.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [201]
In the citing paper
“The dominant architectural paradigm connects specialized, external multimodal encoders-such as CLIP for vision or CLAP for audio-to the LLM backbone via alignment modules like Q-Former or simple MLPs [19, 86, 615, 1139], a modular design that allows for independent encoder updates without retraining the entire model [624].”
From A Survey of Context Engineering for Large Language Models (2025) · cites this paper as [19]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“Language modelling has recently made substantial progress following the introduction of Transformers [115].”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“To ensure that at initialization, the conditioned model yields the same results as the original language model, we use a tanh-gating mechanism [41].”
MethodBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 4×
“In particular, BERT [23] inspired a large body of vision-language work [16, 28, 29, 38, 59, 61, 66, 101, 106, 107, 109, 118, 121, 142, 143, 151].”
BackgroundMethodInfluentialAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“Im ag e ImageNet-1k [94] 3 Object classification Val Top-1 acc.”
BackgroundSwin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 12×
“We evaluate the ability of our models to rapidly adapt to new tasks using in-context learning , analogously to GPT-3 [11], by interleaving support example pairs in the form of ( 𝑖𝑚𝑎𝑔𝑒, 𝑡𝑒𝑥𝑡 ) or ( 𝑣𝑖𝑑𝑒𝑜, 𝑡𝑒𝑥𝑡 ) , followed by the query visual input, to build a prompt (details in Method FT Shot OKVQA ( I )”
BackgroundMethodResultInfluentialEnd-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · cited 2×
“[13] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko.”
BackgroundMethodLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 12×
“[85] we use “prompt-ensembling” in which we embed multiple texts using templates such as “A photo of a {class_name}” and average the resulting embedding.”
BackgroundMethodInfluentialExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 3×
“To measure the importance of text pretraining, we compare the performance of using a frozen decoder-only Transformer either pretrained on MassiveText (our main model) or pretrained on the C4 dataset [87] (row (iv) of Table 10).”
BackgroundMethod
Cited by
Sorted by citations
Items 701–800 of 860
Yang, T., Chen, L., & Zhao, Y. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818070
RM-MLLM: Robust scene understanding in adverse weather with RGB-multispectral fusion
Ju, H., Yeo, S. D., Park, I., Jin, Y., Nalçakan, Y., & Kim, S. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.112317
Gradient-Informed Mixture of Fusion Experts for Parameter-Efficient Multimodal Sentiment Analysis
Ren, Q., Bai, Y., Zhang, H., Ren, X., & Lei, B. (2026) · International Conference on Artificial Intelligence and Computing (AIC) · doi:10.1109/aic65131.2026.11633836
“…modality-specific encoders into a single language-model framework: OneLLM [15] routes audio, video, and image through a universal perception module that feeds a shared LLaMA backbone, and LLaVA [16], Flamingo [17], Otter [18], ImageBind-LLM [19], and Video-LLaMA [20] follow related templates.”
Spatial Information and Metadata Generation in Aerial Robotics with Vision-Language Models
Wachtler, E., Barišić, A., Petrović, T., & Bogdan, S. (2026) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit70676.2026.11630756
“Recent advances include models such as LLaVA [4], Gemini [5], Flamingo [6] and Janus-Pro [7] among others.”
Multimodal Vision-Language Models for High- Stakes Decision Making
Mandal, B., Sardana, S., & Garg, D. (2026) · IEEE Global Symposium on Emerging and Communication Technologies (GSEACT) · doi:10.1109/gseact68539.2026.11620182
“Regardless of their functionality, helpfulness, coherency, and task completion are the most common optimization goals of modern VLMs [13].”
Chen, J., & Guan, X. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634436
Designing and Evaluating Vision-Language Models for Painting Analysis
Adeyi, J., Sahni, N., Hassan, E., et al. (2026) · IEEE International Conference on Intelligent Reality (ICIR) · doi:10.1109/icir70631.2026.11628134
“Subsequent research introduced large-scale generative vision-language models capable of direct image-to-text generation [4],[5].”
Peykani, P., Charles, V., Emrouznejad, A., Ghanidel, S., & Sabour, D. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10720-6 · Cited by 1
Large Language Model-Assisted Distillation–Fusion Framework for Visual Emotion Recognition
Ma, Y., Zeng, Y., Chen, Z., et al. (2026) · Algorithms · doi:10.3390/a19080669
Giri, S., Zheng, Q., Zhang, X., et al. (2026) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2026.08.008
STAR: Mitigating hallucinations in vision-language models through object-centric prompting
Ma, J. B., & Han, H. G. (2026) · Pattern Recognition Letters · doi:10.1016/j.patrec.2026.08.013
DataMind AI: A Dynamic, Agentic Framework for Real-Time Multimodal Retrieval-Augmented Generation
Banerjee, K., Kumar, A., Kumar, P., Goswami, K., Singh, A., Sharma, K., Giri, A., & Karri, S. B. (2026) · International Conference on Sustainable Engineering and Technology Innovations (ICSETI) · doi:10.1109/icseti67678.2026.11636548
“Models such as Flamingo [5] have demonstrated the potential of interlacing visual and textual information for few-shot learning.”
Nguyen, T., Yoon, H. S., Luu, T. M., Yoon, E., & Yoo, C. D. (2026) · IEEE Access · doi:10.1109/access.2026.3723028
Yi, Z., Zhao, J., Lv, J., & Wang, T. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104700 · Cited by 1
Medeiros, M. D. A., Silva, M., Brandão, D., & da Silva, I. M. D. (2026) · IEEE International Workshop on Metrology for Automotive (MetroAutomotive) · doi:10.1109/metroautomotive69354.2026.11644637
“Recent advances in large language models (LLMs) have demonstrated strong capabilities for multimodal reasoning, enabling the integration of heterogeneous data sources into unified representations [8], [9].”
Learning Interpretable Interior Style Semantics via Large Multimodal Model Representations
Yamamori, J., Togo, R., Yamashiro, T., et al. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630254
Smart Rice Mill: AI, IoT, Computer Vision and Blockchain-Based Intelligent Rice Processing
Dewangan, N. K., & Shrivastava, P. (2026) · doi:10.52711/book.anv.9788199786417-08
Zhang, S., Shan, L., Qiu, R., & Zhong, W. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3723919 · Cited by 2
“More importantly, VLMs enable explicit modeling of semantic relationships beyond low-level feature interaction, offering a principled way to align visual representations with language-guided semantics [16], [17].”
Future perspectives and emerging technologies
Pun, M.-O., Wu, Q., Wang, Z., et al. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-329152-4.00017-9
Self Explaining Vision Transformer using Large Language Models for Trustworthy Image Classification
Thangavelu, K., Yakkanti, B., Gajendran, R., Surampudi, Y., Selvaraj, A., & Bharath Kumara, J. (2026) · International Conference on Intelligent and Sustainable AI Systems (ICOSAAS) · doi:10.1109/icosaas68663.2026.11649134
Temporal Coherence in Video-Language Models for Long-Form Narrative Understanding
M, T. S. M. (2026) · Eduschool Journal of Artificial Intelligence Research (EJAIR) · doi:10.63090/ejair/3139.7336.0006
Examining the Visual Capabilities of Multimodal Large Language Models for Automotive Applications
Mitrenga, M., Kővári, B., & Gáspár, P. (2026) · International Conference on Control, Automation and Diagnosis (ICCAD) · doi:10.1109/iccad69956.2026.11642952
“Early models such as CLIP [14] learned similarity relationships between images and text, while more recent systems—Flamingo [15], BLIP-2 [16], Qwen-VL [17], and Florence-2 [8]—perform fully integrated cross-attention–based multimodal processing.”
Reddy, V., Boyapati, B. S. P., & Vadalasetty, V. S. T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7303181
RCLIP: Residual logits adaptation of CLIP for few-shot learning
Zhang, Y., Liu, Z., Hu, A., & Gu, G. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116847
Risk-Aware False-Alarm Suppression for Resource-Constrained Edge–Cloud Fire Detection
Zhao, L., Liu, Y., Yu, T., Ou, Y., Zhang, H., & Yu, X. (2026) · IEEE Access · doi:10.1109/access.2026.3724816
VLM4FD: A Multimodal Vision-Language Model for Cross-Condition Bearing Fault Diagnosis
Guo, J., Wang, H., Zhang, P., Yang, C., Zhang, Y., Zhang, H., & Ju, H. (2026) · Proceedings of the 2026 2nd International Conference on Artificial Intelligence and Computational Intelligence · doi:10.1145/3810280.3810375
Hu, W., & Sun, Q. (2026) · Journal of King Saud University: Computer and Information Sciences · doi:10.1007/s44443-026-00998-8
“…metrics, a standardized suite of automated assessment tools was employed to measure the quality of the generated descriptions, including: BLEU-(Alayrac et al. 2022; Li et al. 2023; Hu et al. 2023; Hu et al. 2024; Papineni et al. 2002), which evaluates fluency and accuracy; METEOR (Banerjee et…”
InfluentialBi, X., Sun, H., Qiao, W., et al. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134076
Large Vision Models (LVMs) for Video Intelligence
Bhatti, U. A., Gulzar, Y., Ghadi, Y. Y., & Bhatti, M. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0965-9.ch008
C-P&M: Unified cross-prompt and cross-model adversarial attack on multimodal large language models
Bao, Q.-Q., Yan, Y., Ding, X., et al. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134821
Kolozali, Ş., Kalantarhormozi, A., Ahmad, A., et al. (2026) · doi:10.1109/dph70309.2026.11650519
“Multimodal large language models (MLLMs), including Flamingo [9], PaLM-E [10], and BLIP-2 [11], demonstrate strong cross-modal reasoning capabilities.”
Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs
Zhang, R., de Winter, J., Dodou, D., Seyffert, H. C., & Eisma, Y. B. (2026) · Computational Brain & Behavior · doi:10.1007/s42113-026-00333-4
“Recent developments in artificial intelligence have led to the development of Multimodal Large Language Models (MLLMs), which extend traditional LLMs by incorporat - ing visual inputs (Alayrac et al., 2022; Liu et al., 2023).”
The LLM conjuncture: Genres in flux and progenitors of the next wave
Wei, Y., Wang, Y., Liu, X., Watada, J., & Pan, J. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.112398
Adaptive Cross-Modal Fusion With Instance-Level Gating for Vision-Language Understanding
Patel, U. A., Patel, S., Nanavati, J., et al. (2026) · International Conference on Circuit, Power and Computing Technologies · doi:10.1109/iccpct70290.2026.11655009
Blur-guided motion and spatio-temporal swarm graph modeling for UAV intent understanding
Zamir, M., Zhong, T., Zhou, F., & Khan, M. S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116895
Wang, Z., Cui, Z., Yang, Z., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7327622
Srinivasan, A., Jena, P., Topale, A., Venna, V. K., & Sarvadevabhatla, R. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36033-5_37
ProcessMM: An OCR-enhanced domain-specific multimodal model for manufacturing process planning
Ruxi, Z., Du, X., Feixiong, T., Jiayuan, L., Liu, X., Zheng, S., & Lv, J. (2026) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2026.103405
Arzu, G. E., Umar, M., Fayaz, M., Ali, U., Dang, L. M., & Moon, H. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116901
You, E., & Oh, S. (2026) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice70481.2026.00019
“Vision-Language Models began with Flamingo [1] and BLIP-2 [6] before advancing to LLaVA [7] followed by InstructBLIP [3] and more recently to Qwen2-VL [11] and InternVL2.”
Task-Adaptive Calibration for Multimodal Long-Context ExtensionPreprint
Li, X., Guo, Z., & Liu, R. (2026) · Research Square · doi:10.21203/rs.3.rs-10769418/v1
Comparative Study of ResNet-152 and ViTPose-G for Human Pose Detection on the COCO Yoga Dataset
Arora, A., Trivedi, S., Sharma, R., Tiwari, R., Chaudhary, S., & Garg, P. (2026) · International Conference on Emerging VLSI and Semiconductor Technology for AI and Computing Applications (EVST) · doi:10.1109/evst69093.2026.11660623
“Vision Transformers work well and are not that complicated because they use a special way of looking at parts of images[7],[9].”
EVLM: Intent-Driven Edge Vision Language Model for UAV-Based Power Line Inspection
Farahani, R., Azimi, Z., Murturi, I., Göknil, A., Sen, S., Timmerer, C., & Dustdar, S. (2026) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge72783.2026.00014
“Moreover, instruction tuning supports reliable prompt-conditioned multi-modal reasoning (Flamingo [29], InstructBLIP [30], Qwen2-VL [31]), while compact VLMs (MobileVLM V2 [32], TinyLLaVA [33], SmolVLM [10]) reduce model and inference cost for practical on-device deployment.”
Multimodal LLMs as Image-to-Tabular Translators for Ultra-Short-Term Photovoltaic Forecasting
da Fontoura, D. D. C. N., & de Aguiar, M. S. (2026) · doi:10.5753/semish.2026.23777
“In parallel, multimodal LLMs have evolved toward more reliable joint processing of text and images [Alayrac et al. 2022, Li et al. 2023, Liu et al. 2023].”
Foundation models in medical image analysis: A systematic review and quantitative analysis
Rajendran, P., Safari, M., He, W., Hu, M., Shah, K. D., Wang, S., Zhou, J., & Yang, X. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104293 · Cited by 8
LLM-Driven Cognitive SemCom Systems
Wu, W., Zhou, F., Wang, L., Wu, Y., Li, Y., & Hu, H. (2026) · Wireless networks · doi:10.1007/978-981-92-0982-8_10
Improving Policy Learning via Language-Guided State Representation in World Models
Zhang, L., Kan, M., Shan, S., & Chen, X. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3728343
“To enable the language instruction to guide task-relevant visual feature extraction, we fuse these two modalities using a perceiver resampler (PRS) [42].”
Khan, M. T. A., & Bombardelli, J. (2026) · Journal of Robotic Surgery · doi:10.1007/s11701-026-03866-9
SSNP: support sets are natural prompts for in-context few-shot image recognition
Meng, Y., Liu, L., Zheng, W., Wu, M., & Qian, S. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02589-z
Frequency-aware multimodal fusion framework for emotion recognition in conversation
Wu, C., Tang, J., Zhao, C., Zuo, S., & Kong, W. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02630-1
Query-based multimodal interaction and adaptive gated fusion for Alzheimer's disease detection
Shao, Y., Tan, C., Huo, H., & Fang, T. (2026) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2026.1913697
Yang, C.-C., Li, A.-S., Chen, X.-L., et al. (2026) · International Conference on Geoinformatics · doi:10.1109/geoinformatics72247.2026.11665114
“In this domain, Liu et al. utilized generated instruction-following data to connect a vision encoder with an LLM [3], and Flamingo enabled rapid few-shot adaptation by conditioning on interleaved visual and textual inputs [4].”
TRACE: Intervention-aware temporal representation learning for video understanding
Chaudhry, H. N., Kulsoom, F., Mohsin, S. M., Aslam, S., & Mohsin, S. M. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100976
Fanijo, S. O., Jannesari, A., & Dickerson, J. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100983
Kwon, J.-H., & Shin, J. (2026) · Journal of Korean Institute of Industrial Engineers · doi:10.7232/jkiie.2026.52.4.374
Multimodal-guided self-distillation for unified person search
Yang, X., Zhou, H., Zhu, H., & Wang, N. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109581
Towards Efficient Vision-Language Model Inference via Stepwise Visual Token PruningPreprint
Hyun, M., Kang, D., Chang, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7396808
A Review of Neural Question Generation: Approaches, Challenges, and Future Directions
Guo, S., Pang, L., Zhang, J., Li, C., & Chen, H. (2026) · ACM Computing Surveys · doi:10.1145/3843765
“For example, Flamingo [4] demonstrated that the MLLM can process sequences of alternating images and texts and produce coherent outputs purely via multimodal prompting.”
Ma, F., Lin, Y., Jia, R., et al. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116167
Deep Learning-Based Multi-Source Data Fusion Methods for Intelligent Information Processing
Lin, G. (2026) · International Conference on Artificial Intelligence, Virtual Reality and Interaction Design · doi:10.1145/3820915.3820932
“[7] [8] [9] [10] [11] [12] Application-driven evidence from autonomous perception and multi-sensor analytics shows that geometry-aware fusion (e.g., LiDAR–camera) and unified bird’s-eye-view representations can standardize heterogeneous sources into consistent intermediate features, while edge AI…”
Gao, L., Shen, G., Hu, W., Chen, W., & Chen, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7417887
Visual Question Answering: A Survey on Architectures, Datasets, Evaluation Metrics and ApplicationsPreprint
Mech, K., & Kalita, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7417407
Vision-guided multi-image prompt learning for zero and few-shot pipeline anomaly detection
Wu, C., Wang, Y., Qiao, B., & Zhang, H. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02652-9
Structured context augmentation for multimodal LLMs in character art analysis
Ming, Z., Ning, W., Chen, G., & Chen, K. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02584-4
“The dynamic line thickness suggests intentional abstraction, emphasizing symbolism over detail [2] Style and Technique: Strongly object-picto - graphic: recognition relies on silhouette and a few high-salience features (horn/ear projections, eyes, tail).”
InfluentialDas, A., Biswas, S., Chattopadhyay, S., Lodh, A., Pal, A., Banerjee, P., Singh, N., Jawahar, C. V., Lladós, J., & Karatzas, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37676-3_40
Ahmadi, E., Chowdhury, A. F., Wang, C., & Jasim, M. (2026) · Journal of Intelligent Construction · doi:10.26599/jic.2026.9180128
pFedSpec: Personalized Federated Learning with Spectral Allocation and Adaptive Rank ControlPreprint
Quan, P. K., Linh, N. Q., Truong, V. V., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7428968
ECC: Encoder-Centric Corruption for Fine-Grained Vision in VLMs
Choi, H., Kim, D., Cha, S., Yi, K. M., & Min, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37044-0_8
UniReflect: Self-reflection Tuning for Unified Multimodal Understanding and Generation
Wei, C., Huang, Z., Tan, H., Liang, D., Gao, L., Yan, P., & Wei, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37577-3_19
Towards Reliable Multimodal Intelligence via Uncertainty-Aware Inference
Gong, T., Gao, S., Song, Q., Sun, Q., Zhou, H., Li, J., & Cao, Y. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2025.00.215
DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy
Kim, H., Lee, K., Shin, Y., & Kim, H. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_5
SAFE-EQA: Semantic-Aware Efficient Exploration for Embodied Question Answering
Tang, Y., Xia, K., Zhang, J., Yu, Z., Yu, Z., Dong, D., Yi, R., Zhu, C., & Xu, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_1
DiNBV-Grasp: Real-Time Distance-Aware Two-Stage Next-Best-View for Robotic Grasping
Xie, Z., Gong, J., Tan, X., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_37
Preventing Expert Collapse in MoE-dVLMs via Modality-Wise Norm Alignment
Liu, Z., Cao, Z., Zhang, H., Yu, C., Niu, L., & Meng, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_20
ATOMIC: A Domain-Specific Vision-Language Model for Transmission Electron Microscopy
Tu, C.-R., Hsueh, H.-W., & Hsu, S.-H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_24
To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models
Jiang, S., Liang, Y., Liang, J., He, R., & Tan, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_23
EmbedCopilot-Bench: Evaluating Vision-Language Models for Hardware-Aware Embedded System Development
Yuan, D., Deng, Y., & Chen, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_19
Zhu, B., Sun, Q., Yang, X., & Zhang, H. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03012-w
“Thanks to the Web-scale data and self-supervised strategies, foundation models like CLIP (Radford et al., 2021) empower zero-shot transfer to a wide variety of domains (Brown et al., 2020; Alayrac et al., 2022; Yu et al., 2022).”
A Review of Large Language Models in the Field of Mathematical Problem Solving
Wang, Z. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682313
Thang, H. V., Chau, I., & Tran, C. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31236-5_27
Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards
Choi, S.-Y., & Lee, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37362-5_12
Sikiru, Y., Thakuria, A., & Erkinbaev, C. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112392
DICE: Disentangled Instance-Class KnowlEdge Prompt Tuning via SAE for Vision-Language Models
Lee, D., Jang, S., & Kim, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36846-1_35
VLMSysTrojan: Stealthy System-Aware Backdoor Attacks Against Vision-Language Models
Cheng, Y., Li, Z., Wu, J., Zhang, Z., & Chen, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37718-0_25
P‐42: Unsupervised Video Anomaly Detection with Vision–Language Model as Assistance
Jiang, Y., Huai, L., Liu, Y., et al. (2026) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.70001_498
Jung, C., Fitzgerald, J., Seefried, E., Bradford, M., & Blanchard, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37261-1_32
Alkhadour, W. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0136-3.ch008
PACO: Stabilizing Vision Embeddings Along Local Paths for Robust Vision-Language Models
Tang, Q., Pi, J., Yang, Z., Liu, X., Xu, P., & Ruan, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_14
Leveraging Vision Foundation Models for Robust Scene Understanding and Real-World Deployment
Alkhadour, W. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0136-3.ch007
LLM-Driven Abstractive Semantic Descriptions: An Approach for Multimodal Semantic Extraction
Sun, Y., & Li, C. (2026) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda69573.2026.11676578
“Subsequent works, including Flamingo [3], BLIP-2 [4], and LLaVA [5], introduce large language models (LLMs) as decoders to enable conditional generation from visual inputs.”
Self-Supervised and Multimodal Vision Foundation Models
Zraqou, J. S., & Alkhateeb, J. H. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0136-3.ch011
Multi-Level collaborative optimization for Multi-Modal media manipulation detection and grounding
Su, W., Guo, Z., Wang, L., & Yang, G. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104773
Benchmarking Vietnamese image captioning: A spatially-aware transformer and the HDUCap dataset
Hoang, A. C., Nguyen, H. L., Pham, T.-A., et al. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104963
Xue, W., Luo, T., Wei, Q., et al. (2026) · Journal of Social Computing · doi:10.23919/jsc.2026.0009
Kale, Y. S., & Ocansey, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7460118
HERO: Enhancing Multimodal Faithfulness via Dynamic Entropy-Aware Reinforcement Learning
Yang, X., Zhang, Q., Zhang, Y., Lin, K.-Y., Hu, J., Jiang, D., & Zheng, W.-S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_25
CTEPM: Continuous-Time Event Process Memory for Long-Video Language Models
Liu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_25
Contrastive-Guided Self-supervised Latent Visual Reasoning for Hallucination Mitigation
戴傲雪, & Wang, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_28
Shuai, W., Zhai, S., Hongtao, S., Lyu, Y., Yifan, Y., & Miao, W. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7471843
Graph-based Multi-Agent LLM Framework for OCR-based Visual Question Answering
Dang, T. L.-T., Nguyen, H. M., & Nguyen, K. V. (2026) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr72750.2026.11685818
“Large VLMs such as Flamingo [13] and BLIP-2 [14] likewise rely on implicit inter-979-8-3195-0175-2 nal representations, leaving hallucination a persistent concern in text-rich scenes [15], [16].”
Metadata
- Authors
- Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., Ring, R., Rutherford, E., Cabi, S., Han, T., Gong, Z., Samangooei, S., Monteiro, M., Menick, J. L., Borgeaud, S., Brock, A., Nematzadeh, A., Sharifzadeh, S., Binkowski, M., Barreira, R., Vinyals, O., Zisserman, A., & Simonyan, K.
- Venue
- Advances in Neural Information Processing Systems 35
- Published
- 2022
- Pages
- 23716-23736
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133196460
- Cited by
- 966
- References
- 154
- Citations by year
- 2026: 847 · 2025: 107 · 2024: 3 · 2023: 7 · 2022: 2
- FWCI
- 15.48
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Oxford University Research Archive (ORA) (University of Oxford) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- vision-language models, few-shot learning, image-text models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
