Cited by 966Domain Adaptation and Few-Shot LearningMultimodal Machine Learning ApplicationsAdvanced Neural Network Applications

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

Alayrac, Jean-Baptiste, Donahue, Jeff, Luc, Pauline, Miech, Antoine, Barr, Iain, Hasson, Yana, Lenc, Karel, Mensch, Arthur, Millican, Katherine, Reynolds, Malcolm, Ring, Roman, Rutherford, Eliza, Cabi, Serkan, Han, Tengda, Gong, Zhitao, Samangooei, Sina, Monteiro, Marianne, Menick, Jacob L, Borgeaud, Sebastian, Brock, Andy, Nematzadeh, Aida, Sharifzadeh, Sahand, Binkowski, Mikolaj, Barreira, Ricardo, Vinyals, Oriol, Zisserman, Andrew, Simonyan, Karén·2022·Advances in Neural Information Processing Systems 35

DOI 10.52202/068431-1723

Open this paper in CoChat — free account

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.

Integrity signals

Registry

Crossref · 10.52202/068431-1723

Cites

154 of 154 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Attention Is All You Need
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].”
BackgroundMethodInfluential
Long Short-Term Memory
Hochreiter, 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].”
Method
BERT: 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].”
BackgroundMethodInfluential
An 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.”
Background
Swin 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 )”
BackgroundMethodResultInfluential
End-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.”
BackgroundMethod
Learning 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.”
BackgroundMethodInfluential
Exploring 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

Flagged first, then by citations

Show all 154 references

Sorted by citations

Items 401–500 of 860

Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains
Tang, Z., Krishnan, R. M., Yu, Z., & Sun, C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00435
“[2 , 61]) capability to leave the capsule and generalize to novel domains.”
GHOST: Getting to the Bottom of Hallucinations with A Multi-round Consistency Benchmark
Vibashan, V. S., Chang, N., Schmalfuß, J., Patel, V. M., Yu, Z., & Álvarez, J. M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00596
MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models
Han, S., Lee, H., park, S., Lee, J.-R., & Lim, S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00112
“Early MLLMs, including BLIP-2 [13], MiniGPT-4 [32], Qwen-VL [2], and Flamingo [1], aligned visual features from frozen vision encoders with LLMs through lightweight projection or cross-attention modules, enabling effective performance on tasks like visual question answering and captioning.”
DREAM: Dynamic Prompts and GuidedMix for Efficient Continual Adaptation of Visual-Language Models
Chee, E. Y. L., Lee, M. L., & Hsu, W. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61042.2026.00567
“Advances in large-scale vision-language models (VLMs) [1, 23, 32] have demonstrated strong zero-shot and few-shot performance across diverse tasks.”
FG-Tracer: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation
Saporita, A., Pipoli, V., Bolelli, F., Baraldi, L., Acquaviva, A., & Ficarra, E. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00763
“Multimodal Large Language Models (MLLMs) [2, 14, 27, 44, 45] represent a significant advancement in artificial intelligence, as they extend the capabilities of traditional language models [3, 10, 33, 34] to support reasoning over non-textual modalities [8, 15, 37, 46].”
Influential
Evaluating and Mitigating Adversarial Vulnerabilities in Vision Foundation Models
Rajput, D. B. (2026) · IEEE Applied Sensing Conference (APSCON) · doi:10.1109/apscon68325.2026.11497446
“In vision, models like CLIP [8] and Flamingo [2] leverage vision-language pretraining.”
Interleaved Vision-and-Language Generation via Generative Voken
Zheng, K., He, X., & Wang, X. E. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00054 · Cited by 127
Understanding the Visual Projection Space of Multimodal LLMs
Jeong, S., Song, Y., & Kim, H. J. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00585
“This projected vector is prepended to the textual prompt as a pseudo-token, conditioning the autoregressive decoder during generation [1].”
Model-free Domain Adaptation for Concealed Multimodal Large-Language Models
Mitsuzumi, Y., Kimura, A., & Kashima, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00126
“These models serve as “foundation models” [3, 6] and demonstrate remarkable zero-shot capability for a variety of tasks, such as image understanding, reasoning, and generation.”
Crafting Descriptive Information for a Zero-shot Method to Improve Knowledge-Based Visual Question Answering Performance
Moradi, M. M., & Mudur, S. P. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00305
ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering
Shin, J., Hur, C., Cho, S., Choi, J., & Park, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00738
“However, most of these efforts fall into the category of simple perceptual-level understanding, such as processing straight-forward videos, and are based on an end-to-end approach [1, 13, 16, 47].”
FinePruner: Unbiased Attention-Head-Level Fine-Grained Token Reduction for Efficient Inference of Large Vision-Language Models
Wang, Z., Zheng, X., & Peng, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3687073
LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling
Li, X., Zhu, H., Ren, S., Yang, L., Wang, P., Wang, H., Shen, X., Liu, Q., & Xie, C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00444 · Cited by 1
“For evaluation, we show the details of datasets we used in Table 4.”
BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity
Koo, J., Lin, W.-T., Park, C., Park, C., & Sung, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00178 · Cited by 1
“Two representative approaches for achieving this are the Gated Mechanism [1, 25, 31, 50] and ControlNet [8, 35].”
Parameter-Efficient Fine-Tuning for Vision-Language Models: The Post-Transformer Evolution
Narasinghe, P., & Sudantha, B. H. (2026) · International Conference on Image Processing and Robotics (ICIPRoB) · doi:10.1109/iciprob69625.2026.11497870
“In the domain of multimodal learning, the convergence of Computer Vision (CV) and Natural Language Processing (NLP) has catalyzed the development of powerful Vision-Language Models (VLMs) such as CLIP [1], BLIP [2], LLaVA [3], and Flamingo [4].”
RegionAligner: Bridging Ego-Exo Views for Object Correspondence via Unified Text-Visual Learning
Su, Y. S., & Elhamifar, E. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00319
“Our work addresses these gaps by explicitly modeling and mitigating these challenges. object-level image understanding [1, 17, 44].”
Smart OCR: A Vertical AI Agent for Financial Document Validation — An Exploratory Case Study
Utyiama, D. M. D. S., Moraes, O. S. C., Guimarães, F. A. S., Ramos, P. B. S., & Marques, L. (2026) · Anais do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.5753/sbsi.2026.248680
“Mo-delos como CLIP [Radford et al. 2021], Flamingo [Alayrac et al. 2022] e Gemini (Google) integram representações visuais e textuais de forma end-to-end .”
Advancing In-Context Learning for Efficient and Stable Medical Report Generation
Li, M., Liu, R., Shi, Z., Han, M., Yao, L., Li, Z., Chang, X., Pohl, K. M., Islam, M. T., & Xing, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3689780
“Visual and textual inputs are concatenated and passed directly to the LLM without any architectural modiﬁcation, following the simple token-level fusion strategy used in Flamingo [56].”
A review of the emergence of AI-driven cognitive digital phenotyping: Multimodal sensing, foundation models, and the path toward digital twins for human cognition
Ali, M. Z., Zafar, A., Masood, H., Dong, J. J., & Lee, S. H. (. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100994 · Cited by 1
Seeing and Understanding: A Human-Centric Evaluation of Multimodal Language Models in Chinese Contexts
Li, J. J., Jiang, Z. J., Liu, Y., & Xu, H. (2025) · International Conference on Human-Engaged Computing (ICHEC) · doi:10.1145/3786995.3787004
Advanced Techniques for Dental Diagnosis Using Multimodal Vision Language Models Approaches with Prompt Engineering & Finetuning
Shuva, T. S., Noor, F. B., Mohammed, A., et al. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491593
“Extending transformers to multimodal learning, Vision–Language Models (VLMs) including CLIP, Flamingo, and similar architectures combine visual encoders with language models to learn joint image–text representations capable of zero-shot classification and visual question answering [7], [8].”
Mapping the Individual and Social Impacts of Foundation Models on Transportation RecommendationPreprint
Cullen, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6730118
A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotations
Cardullo, D., Teglia, S., & Amerini, I. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104929
“Specifically, we evaluated the performance of LADLE-MM using Flamingo [9], FLAVA [83], and Siglip [109] as alternative fixed reference spaces.”
Active Perception Strategies for Multimodal Integration and Latent Information Reasoning in Robotic Systems
Yang, Y., Yang, J., Lu, H., Liu, H. H., & Gao, W. (2026) · IEEE Systems Journal · doi:10.1109/jsyst.2026.3680039
“Recent advancements in large language models (LLMs) have significantly improved task comprehension and reasoning, leading to the development of multimodal LLMs (MLLMs) [1], [2].”
Visual–Language Model–Driven Annotation and Analysis of Maneuver Data for Enhanced Vehicle Safety
Bai, L., 原崇裕, Osman, I. I., Lin, Z., Mirab, G., Saheb, A., Parnian, N., Shapiro, E., Shehata, M. S., & Liu, Z. (2026) · SAE International Journal of Transportation Safety · doi:10.4271/09-14-01-0032
Beyond the frame: generating culturally rich captions for Chinese relics with retrieval-augmented knowledge
Mi, C., & Xie, S. (2026) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqag059
UniAVLM: Unified Large Audio-Visual Language Models for Comprehensive Video Understanding
闫乐成, Lyu, C., Li, W., Samih, Y., & Jiang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7084-3_7
CoMAG: Collaborative GNN–LLM learning for multimodal attributed graphs
Liang, S., Wen, Y., Huang, C., Liu, Y., Nie, Y., Feng, J., Huang, Y., Ye, J., & Wu, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116864
Cloud-Type Classification Using Vision-Language Model With Cloud Multimodal Adapter
Liu, S., Chu, Y., Zhang, Z., & Xiao, B. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3691532
LABMA: Latent-bottleneck attention-based multimodal architecture for integration of transcriptomics, proteomics, and MRI in neurodegeneration
Niwarthana, A., & Rajapakse, J. C. (2026) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2026.111740
Toward a Unified Vision-Language Generative Model
Wang, P. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1014640 · Cited by 4
Optimizing Medical Record Data for Improved Diagnosis Utilizing Large Language Models Gemma 3 to improve Health Disease Care
Liu, D. M. J., & Hwa, K. (2025) · International Conference on Biomedical and Bioinformatics Engineering (ICBBE) · doi:10.1145/3794209.3794281
Protocol-Agnostic Q-Space Learning for Diffusion MRI Microstructural Parameter Reconstruction Using Diffusion Models
Xu, X., Wu, X., Ren, H., Zhao, H., & Gan, S. (2026) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml68972.2026.11507078
“Recent advances in multimodal modeling have explored resampling and aggregation mechanisms, such as the Perceiver Resampler [22], [23], to map variable-length inputs into a fixed-dimensional latent space.”
Prompt-guided electroencephalogram–language alignment for classifying comorbidity in pediatric epilepsy
Ruoxuan, D., Kang, H., Ma, C., Cai, Q., Wang, M. X., An, J., & Gao, Z. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115064
CoSE: connectivity-oriented semantic enhancement for mitigating hallucinations in multimodal LLMs
Hu, Y., Fan, Z., Li, G., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104478
Multi-Agent LLM Framework for Imageability Assessment in Trusted Multimodal Data Spaces
Zhang, B., Huang, G., & Xu, C. (2025) · International Conference on Big Data Economy and Information Management (BDEIM) · doi:10.1145/3800000.3800222
Human–AI Interaction in LLM
Zakershahrak, M. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_72 · Cited by 2
CLIP-HBD: Hierarchical Boundary-Constrained Decoding for Open-Vocabulary Semantic Segmentation
Wang, Y.-X., Zhou, Q., Yang, A., et al. (2026) · Computers · doi:10.3390/computers15050318
Token-Anchored Semantic Drift: Untargeted Transferable Attacks Against Commercial MLLMs
Shen, T. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519348
“MLLMs combine a pretrained vision encoder with a large language model and have become the dominant paradigm for multimodal reasoning and description generation [1], [2], [13]–[15].”
SADL: sampling, deliberation, and pseudo-labeling for in-context learning in compositional visual question answering
Dang, L. H., Le, T. M., Le, V., Phuong, T. M., & Tran, T. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01411-z · Cited by 2
“For the first baseline, we examine the vanilla few-shot prompting [1], wherein the model seeks to identify an answer a ∗ for a question q that is grounded with an image v , given in-context samples C structured as image-query-answer triplets C = { c i | c i ≡ ( v i , q i , a i ) ; for i = 1 , 2 ,…”
Influential
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
Guo, Y., Zhuang, S., Huang, Z., Fu, C., Li, C., Lyu, J., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37602-2_36 · Cited by 1
REC-RL: Referring Expression Counting via Gaussian and Range-Based Reward Optimization
Liu, H., Teng, Y., Bai, K., Qi, P., Yan, H., Li, L., & Feng, J. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630559
Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
Wu, Y., Wei, C., Lin, F., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37718-0_13
Image Emotion Classification Through Chain of Thought Prompts
Xiao, Y., & Wang, S. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9493-1_5
Context-Aware Sustainable AI Kitchen Assistant Using Multimodal Input and Constraint Optimization
Felicita, S. A., Shankari, R., R, S. N., et al. (2026) · doi:10.1109/icsmile69273.2026.11519298
MILES - Multimodal Intelligent Assistant for 3D Model Generation and Holographic Interaction Using Voice and Gesture Control
Marx, G. S. K., Karthikeyan, J., & Sreeji, S. (2026) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate69073.2026.11518707
“Different directions such as visual instruction tuning [12] and BLIP-2 [13] have tried to enhance multimodal under-understanding, and Flamingo [14] has shown the ability to perform few-shot learning, but spatial reasoning problems are still difficult [17].”
Vision–language models as an integrative layer for clinical artificial intelligence in radiology: A systems-level perspective
Avakian, A. (2026) · Clinical Imaging · doi:10.1016/j.clinimag.2026.110841
Ask the right question: Bayesian-optimized prompting for cross-level knowledge distillation in traffic HOI detection
Liu, J., Chen, Y., Liu, X., & Liu, R. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134025
Emotion Understanding in Visual Scenes via Instruction-Tuned Multimodal Large Language Models
Wei, Q., Cao, F., Zhan, M., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9507-5_2
QMATE: Mitigating gradient conflict with query-enhanced multi-task adaptive transformer for unifying EEG representation
Xiong, W., Lin, J., Li, J., Li, J., & Jiang, C. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116270
Embodied AI
Wang, X., Feng, T., Liu, H., & Zhu, W. (2026) · Springer eBooks · doi:10.1007/978-981-95-7750-7_1
MMA++: Effective Multi-Modal Adaptation for Vision-Language Models
Yang, L., Zhang, R., Wang, Y., & Xie, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3691448
“M ULTI-MODAL learning has become a cornerstone of modern artiﬁcial intelligence, especially with the emergence of large-scale Vision-Language Models (VLMs) [1], [2], [3], [4].”
Beyond single and earthbound: Exploring multi-image grounding in remote sensing with Large Vision-Language Models
An, X., Zhong, C., Sun, J., Liu, J., & He, W. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.05.023
MedLAMA: Medical lesion-aware multimodal alignment
Xue, Z., Liu, T., Li, X., & Tong, W. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134088
Modeling Human-Like Interpretable Reasoning for Blind Image Quality AssessmentPreprint
Li, Y., Yu, Y., Lin, Y., Yang, Y., Chu, C., & Nishida, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6835720
Predicting stock price movements using hyperbolic space representation learning with cross-attention and multimodal data fusion
Fukasawa, T., Murayama, Y., & Izumi, K. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12118-8
“Since the degree of superiority may depend on both dataset characteristics and evaluation metrics, we interpret the results with these contextual dependencies explicitly stated.”
NeuralFur: Animal Fur Reconstruction from Multi-View Images
Sklyarova, V., Kabadayi, B., Yiannakidis, A., Becherini, G., Black, M. J., & Thies, J. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00038
“Large-scale pretraining approaches, such as CLIP [41], show strong generalization across diverse visual tasks, as do more recent models like BLIP [25], LLaVA [26, 27], and Flamingo [1].”
Trustworthy Multimodal Federated Learning: A Survey of Feasibility, Adversariality, and SecurityPreprint
Yuan, Z., Luo, Y., Deng, G., Chen, S., Jiang, W., Yang, X., Wu, S., Wang, K., Wang, M., Rao, C., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6849573
Multimodal Fusion in the Era of Large Models: Methods, Evaluation, and Frontier Challenges
蒋, 松. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.153086
Text-guided few-shot liver and tumor segmentation
Chen, H., Xu, A., Zhang, L., Ouyang, M., Zhu, Z., & Wang, J. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1823870
“Nevertheless, most existing medical FSL methods rely exclusively on visual similarity metrics deﬁned over pixel intensities or low-level texture features [42, 43].”
Novel acoustic-vibration fusion-driven method for evaluating and predicting the sound quality of EV reducers using a wavelet kernel convolutional neural network
Xin, Y., Songlin, M., Li, H., et al. (2026) · Measurement · doi:10.1016/j.measurement.2026.122092
Generative anomaly detection: a comprehensive review of modeling principles, advances, and future opportunities
Zhu, J., Fan, Y., Han, G., Shi, X., Deng, F., & Chen, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11591-w
Linear Scaling Video VLMs for Long Video Understanding
Eyzaguirre, C., Wu, J., & Niebles, J. C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_13
SUVI: Scalable Unified Vector Intelligence for Efficient Edge Deployment
Vyas, N. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536337
“However, many current models rely on a dual-tower architecture: a large language model (LLM) coupled with a separate pre-trained visual encoder such as CLIP-ViT-L or SigLIP [3], [4], usually connected through a learnable projector [1], [2].”
RLMS: A Reinforcement Learning-based Multimodal Summarization Approach for Multimodal Input Data
Phani, S., & Abdul, A. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11415-7
Multimodal and Vision Language Few Shot Learning: A Survey
Alkinde, A., Kurugöllü, F., & Harous, S. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11542210
“Flamingo [24] further improved adaptability through gated cross-attention layers and a Perceiver Resampler, enabling few-shot multimodal reasoning from interleaved visual and textual inputs.”
Architecting Multi-Model Agentic AI Systems: A Taxonomy and Reference Architecture for Specialized LLMs in Production Agents
Shivam, S., Parikh, M., Nutalapati, V., Soni, V. R., & Venganti, V. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541520
“Vision-Language Models (VLMs) fuse visual encoders with language model decoders for joint reasoning over images, screenshots, and structured documents [17][18].”
NavBuddy: An AI-Augmented Navigation Assistant for Context-Aware Route Guidance
Bakes, A., Nguyen, T., Elhenawy, M. M. Z., & Rakotonirainy, A. (2026) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi68585.2026.11539871
“This follows established in-context learning practice [5]–[8] and its multimodal extensions [14], [15].”
Adaptive Multi-Modal Routing for Cost-Aware Presentation Summarization
Jadav, V. R., Garg, A., & Isanaka, V. (2026) · doi:10.1109/icaiset66439.2026.11541977
“Recent large-scale multi-modal architectures such as Flamingo and PaLI-style models [13], [14] extend these capabilities to few-shot visual reasoning and long-context processing.”
Bridging the Semantic Void: A Dual-branch RAG Framework to Enhance GUI Component Description for BVI Users
Wu, Y., Zhou, S., Wang, Z., Li, L., & Bu, J. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800448
Learning Instance-Level Knowledge With Image-Level Supervision for Open-Vocabulary Object Detection in Remote Sensing Images
Li, Y., Bai, Y., Ma, J., Temirbayev, A. A., Li, Y., Shang, C., & Shen, Q. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3699883
Transformer-Based Encoders Significantly Improve Remote Sensing Image Captioning: A Systematic Encoder Ablation Study
Dilsiz, E., & Karaca, A. C. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537113
“Moreover, unified vision–language foundation models including BLIP [10], BLIP-2 [11], OFA [12], and Flamingo [13] demonstrate that large-scale multimodal pretraining substantially enhances cross-modal reasoning and caption generation performance.”
Category-Guided Vision-Language Model for IoMT-Enabled Medical Report Generation Under Heterogeneous Imaging Data
Liu, X., Jin, Q., Zhang, T.-T., Tang, Z., Chen, Y., & Liu, Z. H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3699691
“To improve training e ﬃ ciency, Flamingo [30] employs lightweight adapters, and BLIP-2 [31] introduces a Q-Former to reduce parameter tuning.”
CLIP-guided anomaly detection for power line inspection with multi-scale attention
Xie, T., Liao, H., Wei, H., et al. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3896
Parameter-Efficient Fine-Tuning for Multimodal Fusion: A Survey of Injection-Driven Integration MechanismsPreprint
Rong, Y., Zhang, Z., Hao, X., Li, J., Shi, H., Li, H., Peng, H., (6938), Y. L., & Ma, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6876241
Deciphering Object Concepts: Hierarchical Cross-Modal Relational Reasoning for Mining Object-Attribute-Affordance Associations
Wang, Y., Yang, M., Zhu, Y., Yan, J., Fang, F., Yang, X., & Deng, C. D. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3700158
“Recently, many works [37], [38], [39], [40] have focused on prompting large pre-trained vision-language models to adapt to speciﬁc downstream tasks.”
HI-APP: Hardware-friendly Fully-Integer Approximation of Nonlinear Functions in Quantized CLIP-ViTs
Kang, B. J., & Kim, H. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539556
“Recently, visual language models (VLMs) have shown strong performance in multi-modal tasks such as image cap-tioning and visual question answering [1], [2].”
Three‐Dimensional Object Perception Can Emerge From Predictive Learning
Day, J., Arora, T., Liu, J., Li, L. E., & Cai, M. B. (2026) · Developmental Science · doi:10.1111/desc.70218
Multimodal Vision Haptic Fusion Using Transformer Models for Intelligent Surgical Robotics Systems
Sharma, N., Jain, B., Gaur, M., & Jain, N. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0358-9.ch006
StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset
Wu, Z., Liu, Z., Chen, A., Zhang, J., Li, R., Ge, H., Wang, Z., Xiao, C., & Liang, C. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02898-w
“It ﬁrst achieves remarkable success in visual question answering (Li et al., 2023; Liu et al., 2023; Alayrac et al., 2022) and subsequently extends to the VideoQA (Li et al., 2024; Zhang et al., 2023; Lin et al., 2024; Li et al., 2024; Ren et al., 2024; Jin et al., 2024; Cheng et al., 2024; Maaz et…”
Traditional and Modern Approaches
Zheng, C., & Li, Q. (2026) · Wireless networks · doi:10.1007/978-3-032-18761-1_2
Integrating AI image generation into the designer's creative process for mascot creation
Ardhianto, P., & AQUIREL, T. F. (2026) · Journal of Graphic Engineering and Design · doi:10.24867/jged-2026-2-033 · Cited by 1
Improving Reliability in Multimodal Legal Interpretation of Traffic Signs
Zin, M. M., Mar, A. A., Fungwacharakorn, W., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1527-0_8
Text-conditioned irregular floorplan generation via composable inpainting diffusion
Zhang, H., Savov, A., & Dillenburger, B. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.107037 · Cited by 1
ORBIT-CL: A Semantically-Aware and Lightweight Multimodal Transformer for Cyberbullying Detection
Alqaraleh, S. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.18187
“…Contrastive Learning (RGCL) baseline (0.870) and the 80-billion parameter Flamingo model (0.866), proving that the lightweight, text-centric fusion is a highly effective and efficient alternative to heavy VLMs. [22] 0.866 RGCL [23] 0.870 PALI-X-VPD (SOTA) [24] 0.892 ORBIT-CL (Full) 0.895 ± 0.01”
Influential
Mllm-guided hierarchical semantic ensemble with adaptive visual fusion for zero-shot composed video retrieval
Meng, Y., Liu, L., Wu, M., Ding, Z., & Qian, S. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02394-8
Ibcl: instance-aware bias calibration with contrastive learning for visual question answering
Liu, C., Wu, H., Sun, B., & Fang, Z. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02402-x
CARM: Cross-Modal Alignment Recovery for Lightweight Referring Expression Comprehension
Zheng, G., Zhang, Q., Song, M., Zhang, X., & Wang, J. (2026) · Electronics · doi:10.3390/electronics15122509
A hierarchical evaluation framework for security and trustworthiness in Large Vision-Language Models
Feng, X., Feng, M., Zhang, N., Gu, T., Chang, L., & Bin, C. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114161
AURA: Adaptive Unified Routing Architecture with Cross-Attention and Expert Balancing for Multimodal Product Classification
Van, D. C., Tam, T. D., Hung, D. M., et al. (2025) · doi:10.1109/defi67526.2025.11551638
“Flamingo [26] integrates visual and textual experts for few-shot vision-language tasks, while Sparse Mixture of Modality Experts (SMoME) has been proposed for tasks like video question answering [27].”
Image Caption Generator with Multilingual Translation Using Deep Learning
Reddy, V. R., Lalbee, S., Nandini, S., et al. (2026) · doi:10.1109/icsscna68616.2026.11546921
POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction
Smock, B., Liang, L., Sokolov, M., Ramesh, A., Faucon-Morin, V., Khanam, T., & Courtland, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36207-0_1
GrowCap: Lightweight Image Captioning with Enhanced Hard Prompts
Tian, H., Ning, B., & Zhou, X. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-7996-9_2
Cross-Media Intelligence
Pan, Y., Zhuang, Y., Wu, F., Yang, Y., Xiao, J., Huang, T., Zhu, W., & Zhang, S. (2026) · Advanced topics in science and technology in China · doi:10.1007/978-981-95-8037-8_4
Image Caption Generation Using Visual Attention Prediction and Contextual Spatial Relation Extraction
Joseph, S., Tejaswini, N. P., Jha, S. K., et al. (2026) · International Conference on Integrated Intelligence and Communication Systems (ICIICS) · doi:10.1109/iciics67880.2026.11483510
ZERO Mind: Self-Evolving Lifelong Multimodal Memory Architectures for Autonomous Space Digital Twins
Dhinakaran, K., G, B. T., & Kavin, V. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11545864
“CLIP and ALIGN learned joint vision-text spaces at web scale [1]; Flamingo and ImageBind extended few-shot and multi-sensor binding capabilities [2], [3]; LLaVA and visual instruction tuning add instruction-following capabilities [4].”
Mitigating Multimodal Hallucination Through Effective and Perception-Aware Granularity Alignment
Zhang, Z., Lin, J., Zhang, Y., Xia, R., & Zhou, C. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3703183
Adaptive Knowledge Generation via Reinforcement-Guided Pattern Completion for Zero-Shot Visual Question Answering
Sun, Z., Su, D., Li, X., et al. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810578
Effective Reinforcement Learning for Remote Sensing Vision-Language Models via Supervised Knowledge Injection
Zhang, Z., Liu, P., Shen, H., Zhao, T., Liu, Z., & Yin, J. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3703992
B-HFA: Parameter-Efficient Vision-Language Retrieval via Block-shared Adapters and Hierarchical Aggregation
Xu, R., Yao, L., Wu, Z., Zhang, X., & Wu, G. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810607

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.
ORCID: Alayrac, Jean-Baptiste
Miech, Antoine
Lenc, Karel
Vinyals, Oriol
Zisserman, Andrew
Venue: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Published: 2022
Pages: 23716-23736
ISSN: 1049-5258 (ISSN-L)
DOI: 10.52202/068431-1723
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

Flamingo: A Visual Language Model for Few-Shot Learning

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Metadata

Record

About these checks