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 301–400 of 860
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].”
Asamoah, J. K., Kyem, B. A., & Aboah, A. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3680396 · Cited by 2
“Larger-scale models like Flamingo [36] and BLIP [25] further improve generation and retrieval performance by combining visual encoding with more expressive language decoders.”
Diverse and efficient ensembling of deep networks
Ramé, A. (2023) · theses.fr (ABES) · doi:10.70675/fa295dcfz969ez4448z9a30z7c7bbfabb740
Study of the multimodal understanding of vision-language transformer models
Salin, E. (2023) · theses.fr (ABES) · doi:10.70675/2beca704z5d3bz421dzbf61z61e00610aaeb
Maier, A., Christlein, V., Breininger, K., Würfl, T., Unberath, M., & Rieß, C. (2026) · doi:10.1515/9783111386690-021
Foundation Vision-Language models
Laurençon, H. (2025) · theses.fr (ABES) · doi:10.70675/ec0311a0zb6a4z4249zb9fbz01bf51a02c7c
Beyond Factual Queries: A Novel Predictive Retrieval-Augmented Generation
Cheng, D., Deng, J., Chen, Q., Jie, J., & Gan, J. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792364
Multimodal Graph Conditioned Diffusion Model for Video Captioning
Zhang, B., Gao, J., & Yuan, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792087
Kim, G. B., Lee, G., Kim, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6547402
AI Architectures for Intelligent Shopping Agents
Al-E’mari, S., Sanjalawe, Y. K., & Hajjaj, R. Y. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7330-0.ch004
Artificial Intelligence for Multimodal ESG Report Analysis: Detecting Corporate GreenwashingPreprint
Feng, W., Siau, K. L., & Chen, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6561557
Lim, J., Kwak, Y., Lee, J., Kim, T.-Y., & Jeong, J. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00572-2 · Cited by 2
“Recent multimodal LLMs, including Flamingo, BLIP-2, and LLaVA, have demonstrated strong reasoning capabilities and the ability to integrate visual and linguistic information for open-ended interpretation.”
InfluentialTAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
Li, A., Ling, Y., Lin, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_11
Yanhuo, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6570820 · Cited by 1
Wang, Z., Ma, T., & Wang, H. (2026) · Die Radiologie · doi:10.1007/s00117-026-01608-4 · Cited by 2
Online Reasoning Video Object Segmentation
Liu, J., Wang, Y., Zhao, Z., Li, W., Wang, S., & Han, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37550-6_31
Multimodal progressive fusion and enhancement network for multimodal sentiment analysis
Qin, J., Yang, Z., Zhou, Q., et al. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132475
Li, Z., Zhou, D., Shao, R., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6581885
Baid, A., Xue, Z., & Grauman, K. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_4 · Cited by 4
From Assistants to Competitors
Smith, M., Houghton, L., Riverola, C., & Intezari, A. H. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/406748
MAS-LLaVA: Motion-Aware Adaptive Sampling for Training-Free Video Large Language Models
Tang, J., & Bai, Y. (2026) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa67686.2026.11468028
“Recent advances in large multimodal models have significantly improved performance on visual–language understanding tasks such as captioning, retrieval, and question answering [1], [2].”
Chu, J., Chen, K., Tang, D., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6585575
Symptom-Aware Adaptation of CLIP for Few-Shot Medical Image Classification
Li, Z., Wang, W., Liu, C., He, J., Zhao, Y., Zhai, Y., & Tang, R. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3685174
Why Do Vision Language Models Struggle To Recognize Human Emotions?
Agarwal, M., Tsaftaris, S. A., Sevilla-Lara, L., & McDonagh, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37020-4_9 · Cited by 2
Multi-View Images Suffice 3D Reasoning Through Chain-of-Thought Selection and Question-Guided Fusion
Xu, B., Wu, J., Zhang, W., Su, C., Liang, J., Sun, Z. X., & Lei, Z. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3683282
A multi-path fusion with knowledge augmentation framework for multimodal NER in Chinese painting
Wan, J., Chen, S., Zeng, Q., & Wang, R. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02528-1 · Cited by 1
Parameter-Efficient Fine-Tuning of BLIP2 for Arabic Question-Answering on Real-World Images
Khenchouch, M., Ounachad, W., Boudchiche, M., et al. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-97825-8_84
Transferable Adversarial Attacks Against Visual Language Models via Staged Semantic Reframing
Li, A., 邱春林, Ge, Y., Zhao, L., & Wang, Q. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463487
MCI-OTFusion: A Multimodal Model for MCI Detection and Cognitive Score Prediction
Lin, Y., Zhang, J., Wei, X., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462707
Xie, H., Qiao, Z., Zheng, X., & Luo, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462727 · Cited by 1
EEG Motor Imagery Classification with Three-Branch Fusion and Multi-Axis Positional Encoding
Fukushima, T., & Miyamoto, R. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462420
Li, Y., Wu, T., Gao, J., Zhu, W., & Ouyang, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462821
Badtail: Exploiting Rationale Tails for Stealthy Multimodal Backdoor Attacks
Jin, H., Li, Y., Fan, H., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462625
HILO: Hierarchical Feature Fusion via Local-Global Attention for Multimodal Embeddings
Zuo, X., Liu, J., Gong, T., He, Z., Zhang, W. T., Chen, J., & Sun, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460711
MMFast: Rethinking Vision-Language Interaction in Efficient MLLMs
Xiong, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464900
Eom, T. S., & Song, B. C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464520
SUSTAIN-VLM: Coordinated Data and Compute for Low-Carbon Vision Language Model Fine-Tuning
Khan, H., Iftikhar, S., Davy, S., & Breslin, J. G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461984
Knowledge Transmission and Fusion in Large Models: Research Advances and ChallengesPreprint
Fan, Y., Wang, Y., Yang, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6624797
Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
Wan, G., Zhang, W., Zhang, J.-X., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462353
Keeping Models Listening: Segment- and time-aware attention rescaling at decoding time
Du, H., & Zhong, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460793
Discrete Vision Tokenization for Vision-Language Alignment in Autonomous Driving
Zhao, H., Xu, J., Xiao, Y., Guo, S., Chen, J., Liang, Y., Hua, X., & Xi, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464555
Enhancing Zero-Shot Personalized Image Aesthetics Assessment With Profile-Aware Multimodal LLM
Wang, C., Wei, C., Liu, C., et al. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630354
Noise-Robust AV-ASR Using Visual Features both in the Whisper Encoder and Decoder
Li, Z., Graave, T., Möller, B., Wu, Z., Franz, M., & Fingscheidt, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463167
Video Quality Anomaly Detection Based on Multimodal Large Language Models
Liu, Z., Qin, P., Dong, Y., Yuan, X., Yu, D. D., Zhang, L., & Chen, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461389
ECM: Enhancing Compressibility of Quantized Vision Encoder and LLM for Large Vision-Language Models
Wang, W., Mao, Y., Tang, D., Guan, N., & Xue, C. J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460785
Principle-Guided Multimodal Reasoning with Minimal Human Demonstrations
Ji, C., Huang, X. S., Jiang, H., Wang, Z., Zhang, Y., Cheng, Y., Feng, R., & Zhang, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464430
Geometry-Aware Reconstruction of Large Vision-Language Models from Dense into Mixture-of-Experts
Zhang, H., Hu, H., Gan, L., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463650
DetailCLIP: Injecting Image Details into Clip’s Feature Space
Zhang, Z., Shen, C., Shen, Y., Sun, Y., Zhou, X., Xiong, H., Zhao, T., & Yin, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462474 · Cited by 1
Feature Projection Learning for Better Vision-Language Reasoning
Zhang, Y., Lin, W., & Zhang, L.-J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463230
Hu, R., Guan, R., Di, Y., Bao, J., & Liu, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462754
“The advancement of sophisticated vision-language models (VLMs) is fundamentally tied to the availability of large-scale, high-quality datasets that provide fine-grained supervision [1, 2, 3].”
HMD: Enhancing Vision Transformer Distillation via Mask Reconstruction
Shi, X., Pu, K., Yan, J., Zheng, B., & Cheng, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463444
Multimodal Fusion-Based IPCLIP Network for Mixed Reality Surgical Assistance
Sun, J., Xu, T., Yang, X., Si, T., & Liu, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462313
Lin, Z., Bai, L., Xi, P., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465047
Ji, Z., Zhang, C., Huang, J., et al. (2026) · Applied Sciences · doi:10.3390/app16084017
Du, Z., Zhou, N., Zhou, M., Zhang, C., Shi, W., Wang, J., Zhou, Q., & 眭海刚 (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.04.024
FineG-RAG: Fine-Grained Retrieval-Augmented Generation for Multimodal Large Language Models
Jin, L., Lin, C., Xiang, X., Sun, Y., Li, Z., & Tang, J. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3686876 · Cited by 2
“Recently, the development of Multimodal Large Language Models (MLLMs) has advanced rapidly, with the emergence of powerful models, including proprietary systems such as GPT-4o [1], Gemini [2], and Flamingo [21], as well as open-source models like BLIP-2 [22] and InternVL [17].”
Integrating Aesthetic-Driven Hierarchical Semantics for Image Quality Assessment
Xiong, R., Chen, L., Feng, Z., Liu, J., & Feng, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3687045
EARS4SEE: A multimodal audio description system dedicated to blind and visually impaired users
Țapu, R., & Mocanu, B. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104772
Using hierarchical syntactic transformer and speech act identification for visual question answering
Yeh, J., & Lin, K.-M. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21551-9
APT: A Two-Stage Image-Video Transfer Learning for Video Retrieval
Kang, S.-M., & Cho, Y.-S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3687737
Aruna Gladys, A., Aishwarya, R., Vetriselvi, V., Daphne, S., Baskar, P. N., & Rajan, A. A. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10598-4 · Cited by 1
“As a result, performance improvements in such models arise mainly from knowledge distilled from large multimodal teacher models [157], rather than from increasing the architectural complexity.”
Sapience without sentience: an inferentialist approach to LLMs
Simonelli, R. (2026) · Asian Journal of Philosophy · doi:10.1007/s44204-026-00400-4 · Cited by 2
Hu, J., Zhang, J., Zhan, F., & Huang, Y. (2026) · Electronics · doi:10.3390/electronics15091837
“Flamingo [20] (80B) achieves strong few-shot multi-modal learning by interleaving cross-attention layers into a pretrained large language model to process visual inputs.”
Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models
Zohdi, S., & Wang, L. (2026) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3805621.3807641
Deep multimodal fusion for aquaculture: a comprehensive review
Li, D., Ji, S., Xu, W., Du, Z., Liu, S., Li, X., & Wang, G. (2026) · Aquaculture International · doi:10.1007/s10499-026-02539-6
“Early models such as ViLBERT (Lu et al. 2019) and LXMERT (Tan and Bansal 2019) established this approach, while later unified frameworks like METER (Dou et al. 2022) and Flamingo (Alayrac et al. 2022) enable more robust and general-purpose cross-modal understanding.”
Intelligent Tools and Visual Expression: How AI Reshapes the Application of Illustration
Li, Y. (2026) · International Journal of Education and Social Development · doi:10.54097/rqvm4184
Vision by Proxy: Modular Descriptors Steering Frozen LMs for Zero-/Few-Shot Image Understanding
Khan, A., & Rajagopalan, S. (2026) · International Conference on Computing, Electronics & Communications Engineering (iCCECE) · doi:10.1109/iccece69715.2026.11492999
“We compare MVP against strong baselines including CLIP [2], BLIP-2 [29], and Flamingo [14].”
InfluentialDesign of an Automated Framework for Evaluating the Performance of Multimodal Rag Models
Kim, K., Jung, J., Park, J.-B., & Kim, J. (2026) · International Conference on Information Networking · doi:10.1109/icoin68469.2026.11480474
Enhancing Multimodal Reasoning via Visual Semantic Summarization
Lin, J., Wang, Q., Ding, K., Wang, B., Song, X., Lü, W., Xu, R., & Zhang, M. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3688409
MetaFusion: Instance-Aware Meta-Prompting and Token Refinement for VLMs Generalization
Liu, M., Wu, F., Lu, Z., Wang, Z., Yu, Y., Han, J., & Zhang, Z. M. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3686093
“Vision-language models (VLMs) [1], [2], [15] have emerged by integrating computer vision and natural language understanding into a unified framework.”
Photolithography Overlay Map Generation with Implicit Knowledge Distillation Diffusion Transformer
Yang, Y.-F., & Hsiao, H.-H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01418
“𝑄𝑄 𝐾𝐾 𝑉𝑉 The Multi-Head Cross Attention module establishes cross-modal alignment, and the tanh gating mechanism [25] refines cross-modal signals by multiplying the output with , where is a learnable scalar initialized to zero [26].”
Xu, W., Chen, K., Qiu, J., Zhang, Y.-Y., Wang, R., Mao, J., Zhang, T.-W., & Wang, L. (2025) · IEEE International Conference on Computer Vision · doi:10.1109/iccv51701.2025.01726 · Cited by 4
Enhanced EVCap: Retrieval-Augmented Image Captioning with Additional Caption Memory
Thanh, L. T., Hieu, N. H., Long, C. K., & Pham, H. V. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-18974-5_5
Fang, L., Wang, X., Wang, D., Wu, Z., Guo, Y., Zhu, H., Zhang, Z., & Liu, G. H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00239
“Alayrac et al. [1] introduced an innovative method employing a query-based cross-attention mechanism, resulting in a robust vision-language interaction module.”
$\mathcal{D}$-Attn: Decomposed Attention for Large Vision-and-Language Models
Kuo, C.-W., Zhu, S., Chen, F., Shen, X., & Wen, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02219
“However, these architectural or operational changes could break the integrity of pre-trained LLMs and lead to inferior VL performance [2].”
Multimodal Fusion Architectures for Clinical Vision Language Models
Ghosh, S., & Raj, D. R. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7315-7.ch003
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images
Deng, B., Peng, S., Genova, K., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01186 · Cited by 1
“The advent of large-scale VLMs, from Flamingo [2], PaLI [7], and BLIP-2 [30], to powerful new models like Gemini [47, 48] and ChatGPT [1], affords new opportunities for visual analysis.”
Chen, S., & Song, B. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00165
“Visual language models (VLMs) [2, 4, 27, 28, 45] sig-nificantly extend the capabilities of large language models (LLMs) by incorporating visual information — typically images – into the step-by-step reasoning process for problem solving.”
From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning
Jiao, P., Zhu, B., Chen, J., Ngo, C., & Jiang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00262
“Early works, such as Flamingo [1], resam-2729 ple visual features and integrate them into attention-based adapter layers within the LLM. BLIP-2 [18] introduces a Q-Former, which simultaneously handles cross-modal representation learning and generative learning.”
LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs
Zhou, H., & Lee, G. H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02070
“In contrast, the versatility and reasoning power of LLMs [14] have inspired the development of LMMs such as LLaVA [4] and Flamingo [1].”
OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding
Xu, T. L., Chen, G. L., Li, Y., Xi, Y., Mu, Z., Wang, R., Zhang, T., Gao, H., & Chen, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01695
“Early models like CLIP [52] leveraged contrastive learning for image-text alignment, while subsequent models such as Flamingo [3] and BLIP [33] introduced improved attention mechanisms to enhance cross-modal understanding.”
Semantic clustering under resource constraints via Bayesian low-rank adaptation
Yu, M., & Ye, X. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109021
One Trajectory, One Token: Grounded Video Tokenization Via Panoptic Sub-Object Trajectory
Zheng, C., Zhang, J., Salehi, M., Gao, Z., Iyengar, V., Kobori, N., Kong, Q., & Krishna, R. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02150 · Cited by 4
“This is commonly accomplished via learnable components such as perceiver resampler [1, 22] or through instruction conditioned token pruning [29, 30, 33, 49].”
SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models
Wang, S., Zhang, Y., Zhu, Y., liu, E., Li, J., Liu, Y., & Ji, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00347
“Consequently, MLLMs are enabled to understand and generate multimodal information with impressive accuracy and versatility across diverse applications [1, 7, 8, 13, 18].”
Analyzing Fine-Tuning Representation Shift for Multimodal LLMs Steering
Khayatan, P., Shukor, M., Parekh, J., Dapogny, A., & Cord, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00213
“Following initial unimodal pretrain-ing—and, in many cases, multimodal pretraining on large datasets—these models can be further specialized by training on multimodal datasets [1, 33].”
InfluentialLayer-Wise Vision Injection With Disentangled Attention for Efficient LVLMs
Zhang, X., Li, D., Liu, B., Bao, Z., Zhou, Y., Yang, B., Liu, Z., Zhong, Y., & Yuan, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00658
Vision Language Models for Medical Imaging
Tyagi, V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7315-7.ch008
Zeng, K., Zhong, G., Cheng, J., Yuan, J., & Li, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00221 · Cited by 3
“Existing visual redundancy filtering approaches encounter three major challenges when applied to MVQA: First, learning-based approaches [2, 4, 7, 13, 24], represented by those utilizing learnable queries to extract specific deep-level visual features akin to using a mold for forging, often require…”
Sun, X., Zhao, Z., Lang, C., Li, B., & Wang, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00048
“We give a detailed introduction to the evaluation metrics of the downstream tasks involved in the manuscript, including mAP, SSIM, PSNR, etc.”
Text2Outfit: Controllable Outfit Generation With Multimodal Language Models
Zhai, Y., Lin, Y.-L., Peng, M., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01500
“Later works (e.g., Flamingo [1], BLIP [16] and BLIP-2 [17]) learned a unified vision-language representation space and translated visual features into LLM to generate captions for images.”
Sharma, R., Chen, C., Chang, F.-J., Yun, S., Xie, X., Meng, R., Xu, D., Mottini, A., & Cui, Q. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02115
“Their applications range from generating contextual image-based dialogues [2, 38, 44] to video understanding [17] and object segmentation [30].”
Lu, W. (2026) · Journal of Computer Science and Artificial Intelligence · doi:10.54097/ge4cjn12
“…at several Processing Stages so as to enable conditioned output based on Visual Context whilst retaining Language Model's previous learned Features [3] The above-mentioned architecture exhibited robust few-shot performance in multi-modal task learning through integrating pre-training advantages of…”
iMotion-LLM: Instruction-Conditioned Trajectory Generation
Felemban, A., Hroub, N., Ding, J., Abdelrahman, E., Shen, X., Mohamed, A., & Elhoseiny, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00266 · Cited by 5
“Notable works include VisualGPT [8], Flamingo [3], MiniGPT-4 [9, 66], LLaVA [37, 38], and InstructBLIP [15].”
Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos
Oo, Y. M., Hwang, Y., Robbani, M. A., Chao, V., Jamsrandorj, A., Nguyen, H. Q., Mun, K.-R., & Kim, J. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00436
“A generative VLM [1, 30, 47] is prompted with natural language queries over cropped player images to jointly predict multiple identity attributes.”
Grid-Based Spatial Encoding for Multimodal LLMs in Facility Management
Crescitelli, V., Maeda, K., & Ikuta, M. (2025) · Artificial Intelligence for Business (AIxB) · doi:10.1109/aixb65684.2025.00020
MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction
Sharma, A., & Patil, P. W. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00741
“Building on these, Flamingo [8] pioneered few-shot learning, while the BLIP series [17, 18] and LLaVA [20] advanced encoder–decoder and instruction-tuned designs.”
von Klinski, M., & Schall, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00245 · Cited by 1
“Subsequent architectures, such as BLIP-2 [14] and Flamingo [3], improved efficiency and few-shot learning by intelligently connecting powerful pretrained vision encoders with frozen Large Language Models (LLMs).”
VisualNav : Visually Grounded Natural Language Crawler Robot Navigation
Gamage, L., Weerathunga, H., Geeganage, V., et al. (2026) · International Conference on Image Processing and Robotics (ICIPRoB) · doi:10.1109/iciprob69625.2026.11497828
“Models such as CLIP (Contrastive Language-Image Pre-training) [3] and Flamingo [12] demonstrated that training on web-scale image-text pairs could yield robust semantic understanding and zero-shot capabilities.”
MAFM 3 : Modular Adaptation of Foundation Models for Multi-Modal Medical AI
Qazi, M. A., Nwadike, M., Almakky, I., Yaqub, M. K., & Saeed, N. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00341 · Cited by 1
“Beyond medical imaging, the broader machine learning community has also developed general-purpose foundation models such as CLIP [23], Flamingo [2], and LLaVA [19], which align vision and language modalities for multi-task reasoning.”
brat : Aligned Multi-View Embeddings for Brain MRI Analysis
Kayser, M., Gridnev, M., Wang, W., Bain, M., Rangnekar, A., Chatterjee, A., Petrov, A., Veeraraghavan, H., & Swinburne, N. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00568 · Cited by 1
“VLP on large-scale datasets of paired images and captions is an effective way to learn image-representations for both vision [10, 35, 39] and VL tasks [1, 8, 43].”
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
