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
Flagged first, then by citations
Cited by
Sorted by citations
Items 201–300 of 859
Bootstrap3D: Improving Multi-View Diffusion Model with Synthetic Data
Sun, Z., Wu, T., Zhang, P., Zang, Y., Dong, X., Xiong, Y., Lin, D., & Wang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01458 · Cited by 9
“With advancements in large language models [3, 10, 19, 24, 35, 60, 75, 81, 93], multimodal large language models (MLLMs) [2, 5, 25, 27, 37, 47, 48, 52, 74, 99] like GPT-4V [59] have demonstrated powerful image understanding and open-world knowledge.”
No Code, No Cloud: On-Device Mockup-to-Code with Lightweight Vision-Language AI
Kuganathan, A., Purandare, M., & Stolze, M. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789144
Guo, Z., Jiang, Y., Leiva, L. A., & Oulasvirta, A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791178
JustShape: Exploring Co-Speech Gestures for Multimodal LLM-Powered 3D Parametric Modeling
Duan, R., Chen, Y., Hu, Y., Liu, Z., Zhu, C., Hu, X., Ma, D., Wang, X., & Ramani, K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790641
A Survey: Systematic Review of Embodied AI AgentsPreprint
Zhang, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6572191 · Cited by 1
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
NVIDIA, :, Azzolini, A., Bai, J., Brandon, H., Cao, J., Chattopadhyay, P., Chen, H., Chu, J., Cui, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.15558 · Cited by 187
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
Koh, J. Y., Lo, R., Jang, L., Duvvur, V., Lim, M. C., Huang, P.-Y., Neubig, G., Zhou, S., Salakhutdinov, R., & Fried, D. (2024) · arXiv · doi:10.48550/arxiv.2401.13649 · Cited by 1
MoDe: Multi-modal discriminative priors for prompt tuning
Huang, X., Zhu, C., Shao, M., et al. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133555
CLIP-DSA: A CLIP-Based Discriminative and Self-supervised Framework for Few-Shot Anomaly Detection
Zeng, S., Chen, Y., Li, M. N., Wu, Y., & Tian, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_3
ILD: Image-Level Labels Driven Active Learning Object Detection
Tian, R., Zhang, J., Zhang, Y., Zhang, M., Zhang, Z., Zhang, Y., Li, Y., & Zuo, W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3613389
“With the success of large-scale language models such as BERT [25] and GPT-3 [26], the initial explorations of the vision-language model [12], [27], [28] are started.”
Local differential privacy for tensors in distributed computing systems
Yuan, Y., Tang, X., Huang, Y., Wu, Y., & Wang, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133704 · Cited by 1
Mo, J., Chen, Y., Lin, R., Ni, Y., Liang, F., Zeng, M., Hu, X., & Li, M. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3631045 · Cited by 1
“With the advent of Multimodal Large Language Models (MLLMs) such as Flamingo [3], GPT-4V [4], and CogVLM [5], there has been a significant shift in the ability of AI to interpret multimodal inputs—including human motion—within an open-vocabulary framework.”
Cyclic Pseudo-Label Generation and Refinement for Weakly Supervised Referring Expression Grounding
Wu, J., Ji, Z., Wang, Y., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3642691
“A common approach to transfer modality knowledge is by using MLP layers [57], [58], [59] or designing a bridge module [17], [60] to align visual features output from visual models to the LLM feature space.”
Boosting Multi-Modal Large Language Model With Enhanced Visual Features
Ma, Y., Lin, W., Wang, Z., Ji, J., Sun, X., Lin, C., & Ji, R. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3644851
“…components: a pre-trained vision encoder [1], [15], [16], [17] designed to extract hierarchical features from input images; a connector [18], [19] that projects image features from the visual space into the textual space; and a pre-trained LLM [2], [3], [4] that generates responses based on…”
InfluentialMoPD: Mixture-of-Prompts Distillation for Vision-Language Models
Chen, Y., Fu, S., & Zhang, Y. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3645615
“…[1], BLIP [2], Flamingo [3], and LLaVA [4] possess a remarkable zero-shot generalization ability and address various downstream vision tasks, such as image classification [1], [5], [6], object detection [7], segmentation [8], visual question answering [2], [3], [9], [10], and visual reasoning [4].”
Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
Zhan, W., Lin, M., Lin, Z., & Ji, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_27
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Zeng, Z., Gu, L., Duan, Z., Li, F., Snoek, C. G. M., Wang, M., & Shi, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_29
Balancing privacy and performance: the impact of facial defacing on AI in medical imaging
Wang, Y., Dai, Y., Guan, H., Li, C.-Y., Vora, M., Ujano, D., Nandi, A., Wu, J., Zhang, P., Honce, J. M., et al. (2026) · EBioMedicine · doi:10.1016/j.ebiom.2026.106457
“We compared the performance of three VLMs-Fla-mingo, 35 Med-Flamingo, 36 and Med-PaLM-2 37 -under a zero-shot evaluation setting (shown as Appendix Fig.”
Wajeed, D. M. A., & Sultana, R. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-5017-2.ch001
MMToT: Multi-Modal Token-of-Thought Reasoning for Large Models
Xu, N., Lu, Z., Tian, H., Zheng, B., Cao, J., & Liu, A.-A. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3654463
Multi-Modal Refined Prompting for Advancing Knowledge-Based Visual Question Answering
Zhu, L., Ying, M., Zhang, C., Liu, D., Wu, L. Y., Zhang, S., & Li, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3660119
Buehler, M. J. (2026) · Nano Futures · doi:10.1088/2399-1984/ae4152 · Cited by 2
Lu, K., Zhang, R., Huang, X. L., Xie, Y., Ma, W., Xia, R., Zhang, H. C., Ning, X., & Zhu, D. (2026) · Journal of Remote Sensing · doi:10.34133/remotesensing.1041 · Cited by 4
Chen, W., Li, W., & Shu, Y. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3662460
“Some studies focus on optimizing computational e ffi ciency [6], [53], [54], while others develop unified multi-task learning frameworks enabling joint training mechanisms [55].”
Kou, L., Fan, W., Huang, X., et al. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2026.3661996
Beyond Real Versus Fake: Towards Intent-Aware Video Analysis
Atreya, S., Quignon, N., Chopin, B., Das, A., & Dantcheva, A. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3663642 · Cited by 1
“Flamingo [36] was the first MLM and was followed by a myriad of other models, each designed for specific tasks using various modalities.”
Dual Adaptive Disentangled Representation Learning With Multimodal Data for Disease Diagnosis
Chen, X., Pan, W., Wang, T., Zhang, X., Xiong, W., Tian, T., Feng, Q., & Huang, M. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3664047
“In recent years, deep learning techniques, particularly those based on transformers and graph neural networks (GNNs), have gained widespread application in the exploration of nonlinear relationships among multimodal data, thereby enhancing modality fusion [13], [29], [30], [31], [32].”
GIGAS: Adversarial Attacks on Visual Question Answering With Multi-Modal Generative Models
Li, Y., Yu, J., Zeng, T., et al. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3664103
“Recently, several studies [42], [43], [44] have begun to introduce visual content into large language models [45].”
FiR-Rad: Fine-Grained Reinforcement With Structured Reasoning for Chest X-Ray Report Generation
Mei, X., Yang, L., Gao, D., Cai, X., Han, J., & Liu, T. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3665561 · Cited by 2
“General-purpose multimodal large language models (MLLMs), such as Flamingo [37], GPT-4 [11], LLaVA [12], and Qwen-VL [13], have achieved strong performance in vision–language understanding across various domains.”
Wang, L., Li, D., Gao, Z. Y., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3668268
Context-Aware Embodied Question Answering Agent With Large Language Model
Wang, Z., Luo, H., Jiang, B., Li, J., Zheng, J., & Bai, X. P. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668526
LAMAR: LLM-Guided Adaptive Perceptual Modeling for Micro-Action Recognition
Ru, Y., Wang, L. L.-C., Ma, H., et al. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411411
“5-VL can provide sophisticated semantic reasoning [1, 21], offering domain knowledge not accessible to purely visual models.”
Cliva-Med: A Lightweight Vision-Language Model for Medical Visual Question Answering
Santoso, J. S., Ma, X., Song, K., Jin, R., Qiu, X., & Zhao, H. (2025) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai67447.2025.11412636
“Flamingo [32] pioneered this paradigm by injecting visual tokens into frozen LLMs via gated cross-attention layers, while BLIP-2 [4] advanced this approach through query transformer-based bridging of vision and language encoders.”
Zhang, H., & Huang, K. (2025) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai67447.2025.11412806
“Recent progress in this field has shown that models such as PaLM-E [6] and Flamingo [7] can jointly process visual and textual information, delivering flexible outputs beyond simple image captioning, including medical report generation and image understanding tasks.”
Topic Identification and Comparative Analysis on LLM Research
Fan, H., & Li, H. (2025) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai67447.2025.11412484
“Subsequently, more multi-modal [7] and cross-modal [8] technological achievements symbolized that LLM research was breaking through the limitations of single modalities and developing towards multimodal collaboration.”
A novel multi-agent spatiotemporal fusion framework for intelligent skin cancer diagnosis
Zheng, P., Yang, J., Wen, X., & Hu, B. (2026) · Frontiers in Oncology · doi:10.3389/fonc.2026.1759960 · Cited by 1
Oracle-grasp: zero-shot affordance-aligned robotic grasping using large multimodal models
Giuili, A., Atari, R., & Sintov, A. (2026) · Intelligent Service Robotics · doi:10.1007/s11370-026-00707-4 · Cited by 1
“Prominent examples of LMMs include GPT-4o [33], Flamingo [34] and LLaVA [35], which have demonstrated impressive capabilities in grounding visual scenes through natural language reasoning [16].”
DiffAlign: Rethinking Text-to-Image Generation with Training-Free Layout Guidance
Zhou, T., & Wang, L. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00181
“An LLM can read the prompt, list the instances, and infer relations [13] [14] [15].”
Thangaraj, S., Shukla, N. K., & Krishnamurthy, V. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402186
“The rise of multi-modal LLMs such as GPT-4V [4], Kosmos-1 [5], and Flamingo [6] has expanded the ability to jointly reason over visual and textual inputs.”
Evaluating Semantic and Perceptual Alignment in Multilingual Story Visualization
Tewari, K., Surendra, S. N., Sharma, D., & Pal, S. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742414.3794743 · Cited by 1
Performance Evaluation and Improvement of Artificial Intelligence Models in Image Recognition
包, 婉. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.152044
Ma, K., Zhan, Q., Zhang, T., Shi, Y., Fang, Z., Shah, S. Y. A., Kablan, O. A. B. K., & Zhang, B. (2026) · Transactions in GIS · doi:10.1111/tgis.70226 · Cited by 2
Training-free enhancement of satellite remote sensing VLMs via Geo-Contrastive Decoding
Shangguan, Z., Zhang, J., Xing, K., Gong, Z., Zhang, Y., Xu, Y., & Liang, F. (2026) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-026-00885-7
Self-citationEvaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection
Basnet, S., Farabi, S., Ranasinghe, T., et al. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00172
Joint Training of Heterogeneous Decoder Architectures with Learned Fusion for Image CaptioningPreprint
Tariq, B., & Khalid, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6386061
Evolution 6.0: Robot Evolution through Generative Design
Khan, M. H., Myshlyaev, A., Lykov, A., Cabrera, M. A., & Tsetserukou, D. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3776734.3794510 · Cited by 2
LLM-based Method for Constructing Fault Trees
Liu, H., Valcamonico, D., Marchetti, S., et al. (2025) · International Conference on System Reliability and Safety · doi:10.1109/icsrs68021.2025.11422073 · Cited by 1
“Some preliminary studies in literature have explored such multimodal capabilities in LLMs, allowing them to process both textual and image data [8].”
Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
Chen, L. Y., Ni, B., Yang, Q., Wang, Z., Ding, K., Wang, Y., Peng, H., & Xiang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37627-5_30
SHC: Deeply Activating Human-Like Cognitive Ability for Visual Question Answering
Wang, F., Wang, Z., An, G., Lang, C., & Wu, D. O. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3673273
“The first one uses linear projectors [8], MLP [9], [10] or resamplers [11].”
HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation
Mahmoud, Y., Yaqoot, Y., Cabrera, M. A., et al. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3776734.3794528
OmniForcing: Unleashing Real-Time Joint Audio-Visual Generation
Su, Y., Li, Y., Xue, Z., Huang, J., Fu, S., Li, H., Huang, H., & Duan, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_31 · Cited by 21
MIME: Mutual information-guided mixture of experts for robust multimodal sentiment analysis
Zhang, D., Xiao, Q., He, X., & Zhang, J. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00587-9 · Cited by 1
“In the vision-language domain, meth-ods like BLIP-2 (Li et al. 2023) and Flamingo (Alayrac et al. 2022) have shown that bridging pre-trained unimodal encoders through lightweight adapters can achieve strong multimodal understanding with minimal fine-tuning.”
Role of prior in human activity recognition: A survey
Zhang, Y., Piet, A., Roelen, S. D., Ali, O., Krajewski, J., Huang, X., & Grzegorzek, M. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114406
CIVA-Net: Cross Modal Attention Fusion for AI Generated Content Detection
Momen, A., Saha, S., Khan, S. S., Biswas, T., & Salam, A. (2026) · International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) · doi:10.1109/icecte69292.2026.11429462
“Larger frameworks such as SimVLM, Flamingo, and LLaVA also show that scaling and instruction tuning improve logic [15].”
TIKD: Where text meets vision for knowledge distillation
Liang, X., Yin, C., Li, M., & Lin, Y.-E. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132045
Differential attention for retinal image captioning via cross-modal integration
Hieu, N. H., Thanh, L. V., Lan, L. T. H., & Pham, H. V. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05208-6
A Survey on RL-Powered Visual Reasoning for Multimodal Models
Dai, W. (2025) · International Conference on Artificial Intelligence, Systems and Network Security (AISNS) · doi:10.1145/3797161.3797177
“Multimodal large language models (MLLMs), also known as vision-language models (VLMs), have advanced the capabilities of AI in a variety of perception and understanding tasks [1, 19].”
Lu, Z., Zeng, W., Cheng, M., & Wang, C. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3675459
Yi, Z., Zhao, J., Lv, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6438441
Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
Guesmi, A., & Shafique, M. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_26
Emergent AI Behaviors in Multi-Modal Fusion Models: Risks, Patterns, and Control
Nath, K., Kohli, R., Lata, S., et al. (2025) · 2025 2nd Asian Conference on Intelligent Technologies (ACOIT) · doi:10.1109/acoit66109.2025.11437087
“Such models, e.g., CLIP, Flamingo, Gemini, and GPT-4V, show incredible strengths when it comes to zero-shot arguments, imaginative synthesis, and cross-modality understanding [1], [2].”
Zhang, Y., & Ma, L. (2026) · Algorithms · doi:10.3390/a19030238
Enabling Ergonomic Human-Robot Interaction Through Large Language Modeling
Monica, L., Madonna, M., Nardo, M. D., Carra, S., & Anastasi, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.02.270 · Cited by 1
HTHTA-ViT++: An Efficient Vision Transformer with Hierarchical GRU Guided Token Attention
Khurmi, S., Yadav, N., Sharma, P., Arora, V., Tomar, A., sharma, K., & Kumar, B. (2025) · International Conference on Artificial Intelligence and Speech Technology (AIST) · doi:10.1109/aist68591.2025.11441535
“Cross domain giants such as Flamingo [26] and Perceiver IO [25] relied on massive language vision backbones with a single shared sequence ; they were pre trained on billions of examples and remained impractical for constrained hardware.”
A Focused Survey on Multimodal Recipe Extraction from Cooking Videos
Alj, K. S., Smith, K. S., & Salih-Alj, Y. (2025) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict68299.2025.11442087
“In contrast, foundation models, including Flamingo [32], Video-ChatGPT [8], GPT-4V [33], and Video-LLaVA [34] are pretrained on broad data and adapted to multimodal tasks via projection layers and cross-modal bridges.”
Augmented Reality Visual Retrieval for Object Detection and Corpus-Guided Content Generation
Taheritajar, A., Zhao, J. L., & Orlosky, J. (2026) · IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR) · doi:10.1109/aixvr67263.2026.00015
“Multimodal large language models (MLLMs), such as CLIP [12], Flamingo [13], and GPT-4V [14], integrate vision and language to support tasks like captioning, visual question answering (VQA), and cross-modal retrieval.”
Cognitive-Load-Aware Multimodal Video Segmentation for Adaptive Consumer Media Systems
da Silva, W. F., Dong, F., Abel, A. K., & Fernando, A. (2026) · International Conference on Consumer Electronics · doi:10.1109/icce67443.2026.11449659
VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
Gao, Z., Shen, S., Chai, T., Wang, W., Xu, H., Xing, W., Li, W., Fan, Q., Gao, Y., & Tao, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_14
Sun, X., Luo, L., & Peng, H. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133397
Jia, X. (2026) · doi:10.1109/icpege67691.2026.11451328
“The emergence of MLLMs has significantly advanced the frontier of vision-language understanding, enabling strong performance on tasks like visual reasoning and dialogue [1, 2].”
VIMAR: vision-language informed malware analysis and reasoning model
Xu, S. (2026) · Cybersecurity · doi:10.1186/s42400-025-00481-3
Scalable Multilingual Fake News Detection using Parameter-Efficient Transformers
Shiwali, S., Tyagi, P., & Kumar, P. (2026) · doi:10.1109/i5cps67958.2026.11452295
“Next steps will look into these areas: • Spotting Fake Info Across Media: Have the system to also work with images, also audiovisual with the help of such tools as [10] and Flamingo [11].”
Литвиненко, М. І., Осієвський, С., Ленець, В. Г., Гармаш, Н. В., Орєхов, С. В., & Дрозд, К. А. (2026) · Системи обробки інформації · doi:10.30748/soi.2026.184.06
Qaisar, I., Sun, K., Jia, Q., et al. (2026) · Building and Environment · doi:10.1016/j.buildenv.2026.115200
Kasturi, A., Proctor, A. R., Vosoughi, A., Zhang, C. T., Hadjiyski, N., Palka, S. V., Davis, J. G., Cardamone, L. M., Helmy, S. M., Cardona, J., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-45573-3 · Cited by 1
Zeeshan, M., Sharafi, M., Savary, B., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37095-2_37
Distribution-Aware Prompt Learning for Vision-Language Models With Dynamic Boundary Prototype
Yang, X., Zhong, X., & Wang, N. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3678014
Mastering Deep Learning: From Neurons to Large Language Models
Firouzi, F., Farahani, B., & Ray, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-06286-4_3 · Cited by 1
Xue, Q., Yu, Y., yan, Y., Zhang, J., & Li, Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115112
Worst-Projection-Gap Guided Pruning for Long-Tail Visual Token CoveragePreprint
Liu, Y., Su, Y., Hao, W., & Wang, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6505413
Multimodal sentiment analysis with query-based distillation and asymmetric fusion
Zhang, H., Shang, Y., Liu, T., et al. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133494
ProCap: Projection-Aware Captioning for Spatial Augmented Reality
Cao, Z., Deng, Y., Ling, H., et al. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr67842.2026.00026
“Early VLMs achieve contrastive pre-training on large-scale image-text data [34, 54], with strong cross-domain generalization, laying the foundation for subsequent training paradigms [3,12,64] and generalized visual language tasks ( e.g . image retrieval, text generation, etc .)”
Li, D., Liang, Y., Qian, S., Sun, Y., Wu, H., Jia, W., Han, W., & Fu, Y. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114705
Wang, Z., Li, Y., Fu, J., & Zhang, G. (2026) · Synthesis lectures on human language technologies · doi:10.1007/978-3-032-06264-2_4
Transformers and Foundation Models for Hyperspectral Imaging
Hong, D., Li, X., & Li, C. (2026) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-95-2038-1_5
Wang, Z., & Chen, W. (2026) · Synthesis lectures on human language technologies · doi:10.1007/978-3-032-06264-2_2
Wang, Z., Zhang, G., Shi, N., & Lin, C. (2026) · Synthesis lectures on human language technologies · doi:10.1007/978-3-032-06264-2_3
Zhang, Y., Shaik, F. A., Acharjee, S., Khalid, F., & Oussalah, M. (2026) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2026.112674 · Cited by 2
In-Context Learning in Large Language Models: Mechanisms, Challenges, and Frontiers
Yuan, Y. (2026) · ITM Web of Conferences · doi:10.1051/itmconf/20268403003 · Cited by 1
MEGAEL: automated multimodal event generation for IoT-driven process mining using generative AI
Iman, E. K., Sbaï, H., & Nassima, A. M. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00700-y · Cited by 1
“Recent extensions like BLIP (Li et al. 2022) and Flamingo (Alayrac et al. 2022) enhance vision-language understanding through improved training objectives and architectures.”
A Correlation-Aware and Dynamic Multi-Level Fusion Approach for Multimodal Relation Extraction
Liu, J., Wang, J., Zhang, H., & Mo, H. (2026) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice68970.2026.11466279
“Flamingo [14] efficiently connects frozen visual encoders with LLMs via the Perceiver Resampler module and gated cross-attention layers, boasting excellent few-shot learning capability and multi-task adaptability.”
How to train your global workspace? Evaluating and efficiently learning multimodal representations
Devillers, B. (2022) · theses.fr (ABES) · doi:10.70675/101815c7zb6faz411czaa4bz7149c56f0e5d
Breaking and Securing Vision-Language Models: An Adversarial Robustness Study
Hossain, M. Z., Shahid, A. R., & Imteaj, A. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00215
“The rapid advancements in artificial intelligence have led to the development of powerful Vision-Language Models [1]–[3] that can understand both visual and textual content.”
Protecting Deep Learning Systems Against Attack : Enhancing Adversarial Robustness and Detection
Picot, M. (2023) · theses.fr (ABES) · doi:10.70675/baaedc7fzdbaaz4337z89a4z5cb4d019c9f8
Video question answering with limited supervision
Engin, D. (2024) · theses.fr (ABES) · doi:10.70675/c9c7dcf2z4ca3z4e91z9d27zdacd00f76581
Teodorescu, L. (2023) · theses.fr (ABES) · doi:10.70675/08e0bf33z987fz4ff6zbdd7zbf6cf87e81f0 · Cited by 1
Text-Based Semantic Image Editing
Couairon, G. (2023) · theses.fr (ABES) · doi:10.70675/c4c397d4zb2e4z41f7z9374z64ed51cfba38
Representation learning of multimodal and longitudinal data for renal transplantation monitoring
Milecki, L. (2024) · theses.fr (ABES) · doi:10.70675/8478bb39za27fz4524z8e86z5df6c7d2fc00 · Cited by 1
Répondre aux questions visuelles à propos d'entités nommées
Lerner, P. J. (2023) · theses.fr (ABES) · doi:10.70675/78c96766zfc95z4da8zb67aze67555da6c75
Analyzing the Effects of Prompt Styles on Large Language Model Chatbot Responses
Kolahchi, N., & Totaro, M. W. (2026) · International Symposium on Digital Forensics and Security (ISDFS) · doi:10.1109/isdfs69419.2026.11458993
“Alayrac et al. designed a new multimodal architecture (Flamingo) that connects an LLM to a vision encoder, enabling the model to perform few-shot learning via prompting on image and video tasks [12].”
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
