The DOI matches its Crossref record; 154 of the 154 references it cites were found in a registry or an index.
Flamingo: A Visual Language Model for Few-Shot Learning
Abstract
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of our models, exploring and measuring their ability to rapidly adapt to a variety of image and video tasks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer, captioning tasks, which evaluate the ability to describe a scene or an event, and close-ended tasks such as multiple-choice visual question-answering. For tasks lying anywhere on this spectrum, a single Flamingo model can achieve a new state of the art with few-shot learning, simply by prompting the model with task-specific examples. On numerous benchmarks, Flamingo outperforms models fine-tuned on thousands of times more task-specific data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“vision-language models (VLMs) such as VilBERT 19 and Flamingo 2 combine a language model with an image encoder and are trained on a multi-modal corpus of text-image pairs.This enables them to predict how a given sequence of words will continue in the context of a given image.”
From Talking about Large Language Models (2024) · cites this paper as [2]
In the citing paper
“the latest generation of language models are multimodal, allowing interleaved image and text input (OpenAI, 2023a; Alayrac et al., 2022; Team et al., 2023; Li et al., 2023b)”
From Cognitive Architectures for Language Agents (2023) · cites this paper as Alayrac et al., 2022
In the citing paper
“The Switch Transformer [201] was one of the first MoE-based Transformers, activating experts selectively in each layer, reducing computational overhead while outperforming dense Transformers in NLP tasks.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [201]
In the citing paper
“The dominant architectural paradigm connects specialized, external multimodal encoders-such as CLIP for vision or CLAP for audio-to the LLM backbone via alignment modules like Q-Former or simple MLPs [19, 86, 615, 1139], a modular design that allows for independent encoder updates without retraining the entire model [624].”
From A Survey of Context Engineering for Large Language Models (2025) · cites this paper as [19]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“Language modelling has recently made substantial progress following the introduction of Transformers [115].”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“To ensure that at initialization, the conditioned model yields the same results as the original language model, we use a tanh-gating mechanism [41].”
MethodBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 4×
“In particular, BERT [23] inspired a large body of vision-language work [16, 28, 29, 38, 59, 61, 66, 101, 106, 107, 109, 118, 121, 142, 143, 151].”
BackgroundMethodInfluentialAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“Im ag e ImageNet-1k [94] 3 Object classification Val Top-1 acc.”
BackgroundSwin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 12×
“We evaluate the ability of our models to rapidly adapt to new tasks using in-context learning , analogously to GPT-3 [11], by interleaving support example pairs in the form of ( 𝑖𝑚𝑎𝑔𝑒, 𝑡𝑒𝑥𝑡 ) or ( 𝑣𝑖𝑑𝑒𝑜, 𝑡𝑒𝑥𝑡 ) , followed by the query visual input, to build a prompt (details in Method FT Shot OKVQA ( I )”
BackgroundMethodResultInfluentialEnd-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · cited 2×
“[13] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko.”
BackgroundMethodLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 12×
“[85] we use “prompt-ensembling” in which we embed multiple texts using templates such as “A photo of a {class_name}” and average the resulting embedding.”
BackgroundMethodInfluentialExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 3×
“To measure the importance of text pretraining, we compare the performance of using a frozen decoder-only Transformer either pretrained on MassiveText (our main model) or pretrained on the C4 dataset [87] (row (iv) of Table 10).”
BackgroundMethod
Cited by
Sorted by citations
Items 501–600 of 860
Jiang, S., Yuan, Z., & Zhao, N. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810869
Zhenpeng, Z., Wu, X., Wang, X., Yu, Q., Wang, Y., & Liu, Z. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810669
SEEDCAP: SEMANTIC EXPANSION AND ENTITY-DRIVEN ZERO-SHOT IMAGE CAPTIONING
Li, B., Xiao, S., Wu, D., et al. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810851
Jing, G., Gao, P. F., Lee, Y., & Zhang, H. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810768
Unlocking In-Context Learning for Natural Datasets Across Modalities
Bratulić, J., Mittal, S., Hoffmann, D. T., Böhm, S., Schirrmeister, R. T., Ball, T., Rupprecht, C., & Brox, T. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02913-0
“In-context learning, initially observed as an emerging ability in LLMs (Garg et al., 2022), but also reported in VLMs (Alayrac et al., 2022; Sun et al., 2023) and vision-only models (Wang et al., 2023; Bai et al., 2024; Bar et al., 2022) enables fast adaptation to various new tasks without gradient…”
InfluentialSCORE: Soccer Curriculum for Ordinal Affect Recognition with Evidence
Shen, X., Rong, Z., Qin, H., et al. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810674
Li, Z., & Li, L. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810830
Structure-Induced Safety Gaps in Multimodal Reasoning Systems
Yang, M., Liang, P., Wu, Z. W., & Liao, Y. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810575
Hu, C., Chen, Y., Liang, T., Wei, Y., Li, A., Shi, H., Bian, L., & Shi, X. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810757
VAR-3D: View-aware Auto-Regressive Model for Text-to-3D Generation via a 3D Tokenizer
Han, Z., Hong, Y., Sun, H., & Cao, D. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810588 · Cited by 2
OpenImplicit: Benchmarking Implicit Reasoning in MLLMs via Open-Ended Evaluation
Li, J., Yin, X., Guo, Y., Zhou, S., Tu, Y., Zhao, H., Duan, S., Liu, G., & Zhu, H. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810855
XOV-Action: Toward Generalizable Open-Vocabulary Action Recognition
Lin, K.-Y., Ding, H., Du, J.-R., Zhou, J., Peng, Y.-X., Tang, Y.-M., Zhao, Z., Loy, C. C., & Zheng, W.-S. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3704589 · Cited by 13
“In recent years, research on image-text foundation models has made great progress [3], [93], [94], [95], [96], [97], [98], [99], [100], [101], e.g. , CLIP [3], SigLIP [99], CoCa [97].”
Wang, D., Liang, S., & Luo, H. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11543137
“LLaVA [4], [11] established visual instruction tuning by pairing a vision encoder with an LLM; BLIP-2 [12] and InstructBLIP [13] leveraged frozen encoders and LLMs; and Flamingo [14] enabled few-shot video understanding.”
Zero-shot referring expression comprehension via guidance of Multimodal Large Language Models
Li, R., Zhuo, W., Zheng, S., Wu, Z., & Shen, L. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114223
Li, J., & Peng, J. (2026) · Applied Acoustics · doi:10.1016/j.apacoust.2026.111442
Zero-Shot Temporal Action Localization Through Textual Guidance
Liberatori, B., Conti, A., Vaquero, L., Rota, P., Wang, Y.-M., & Ricci, E. (2026) · IEEE International Conference on Automatic Face & Gesture Recognition · doi:10.1109/fg67764.2026.11557050
“However, advancements in Vision and Language models (VLMs) [31], [14], [1], [42] have led to an increased interest in tackling TAL from a zero-shot perspective (ZS-TAL), where models aim to generalize to new actions without prior specific training on them.”
Khan, S., Zhou, S., Fu, C., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6957336
Training-Free Semantic Multi-Object Tracking with Vision-Language Models
Bonat, L., Tonini, F., Ricci, E., & Vaquero, L. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557055
“More recent MLLMs, including Flamingo [2], BLIP-2 [15], MiniGPT-4 [48], LLaVA [19], and InternVideo2.”
EncodeStep: A Hybrid Deep Learning Model for AI-Driven Test Step Generator
Thanawala, D., Irani, K., Kapoor, A., Daniel, M., Bhandarkar, R., Jain, M., & Rao, A. (2026) · International Conference on Innovations in Computational Intelligence (ICICI) · doi:10.1109/icici68867.2026.11564871
“The field of complex reasoning, using a visual input, began to receive more attention with models like Flamingo [4] .”
A hierarchical multi-modal injection architecture for synergistic music understanding and generation
Zhang, Y., & Du, G. (2026) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-026-00410-1
Energy and Carbon Footprint of Vision-Language-Action Model Inference for Edge Robotic Systems
Eslami, A., Ardakani, M., Roostaee, A., Zanganeh, H., & Zand, R. (2026) · International Green and Sustainable Computing Conference · doi:10.1145/3797248.3815411
Unified Multimodal AI Engine for Real-Time Summarization of Text, Images, and Documents
Rakshitha, G., Rajamani, T., Bhardwaj, M., et al. (2026) · doi:10.1109/icici68867.2026.11564932
“The Flamingo vision-language model (few-shot) was able to demonstrate very good contextual video tagging and summarization, but its heavy reliance on pre-trained models limited its applicability in real-time settings [9].”
Frame Skipping Architecture for Video-Language Model Acceleration
Shan, H., Wei, C., Guo, C., et al. (2026) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3787109.3816385
Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2
Feng, Y., Snoussi, H., Teng, J., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0229-4_17
Navigating maritime emergencies with large models: A lifecycle-oriented review
Xu, J., Yang, Q., Yang, Z., Gao, Y., Yang, K., & Jiang, J. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115411 · Cited by 2
Multi-task adaptive CLIP for enhanced person re-identification across domains
Li, Y., Jia, S., Li, R., et al. (2026) · The Visual Computer · doi:10.1007/s00371-026-04514-x
“For example, CLIP enables image classification across arbitrary categories using simple text prompts without task-specific training [1, 20, 21, 26, 31, 41].”
Vision-language model guided image restoration
Yang, C., Dong, R., & Lam, K. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106091
Video Object Segmentation-Aware Audio Generation
Viertola, I., Iashin, V., & Rahtu, E. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02911-2
“This weight sharing encourages alignment and reuse of representations across global and local views: To allow focal features to condition on the global visual context, we adopt gated cross-attention adapters [1,26].”
Zhang, Z. X., & Feng, Q. (2026) · Plants · doi:10.3390/plants15131932
A Scalar per Patch from Pre-Trained ViTs Enables Fast Moving Navigation in the Real World
Janny, S., Antsfeld, L., & Wolf, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_13
CVSBench: A Comprehensive Benchmark for Cross-View Spatial Reasoning and Dreaming
Liu, R., Zhang, L., Xue, L., Li, K., Fu, B., & Cao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37369-4_27
Retrieval-augmented large multimodal models for pathology
Chu, X., Sun, Y., Zhou, B., & Sun, L. J. (2026) · Discover Computing · doi:10.1007/s10791-026-10263-1 · Cited by 1
Resource-Efficient Multilingual RAG: English-Only and Multilingual Embeddings for Indian Languages
Bilvitha, D., Isravel, D. P., & Dhas, J. P. M. (2026) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca69024.2026.11570391
“Large-scale multimodal representation learning with noisy supervision further extends embedding alignment across different data [10].”
Zhu, M., Wilson, R., Dizon-Paradis, R. N., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6981462
Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery
Roodabeh, S. H. R., Li, Z., & Alemzadeh, H. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3726373
“RecentVision-Language Models (VLMs) like CLIP [13] and Flamingo [14] have been adapted for surgical question answering [15] and gesture recognition [16], but not explicitly for error detection.”
Benchmarking Vision-Language Models for Microscopic Plant Image Understanding
Wei, T., Yu, X., Chen, Z., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37432-5_14
Guan, T., Wang, H., Shen, W., & Yang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_37 · Cited by 1
Shi, F., & Zhang, D. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567367
TimeNLP: Efficient Time Series Captioning via Decoupled Latent Semantic Alignment
Zhu, K., Wang, Y. M., & Zhang, L. (2026) · International Conference on Smart Grid and Artificial Intelligence (SGAI) · doi:10.1109/sgai69026.2026.11565826
“Flamingo [17] and LLaVA [18] demonstrate that inserting lightweight adapter layers (e.g., cross-attention) between a frozen vision encoder and a frozen LLM can enable robust visual understanding.”
A Neighborhood Attention-Based Adapter for Parameter-Efficient Vision-Language Model Tuning
Guo, H., & Min, H. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559649
“Instruction fine-tuning has been instrumental in enhancing the performance and adaptability of large language models on specific tasks, including a variety of NLP tasks [11], [18], [19].”
Agentic Collaborative Cognition for Zero-Shot 3D Understanding
Wang, W., Zhang, B., Chen, F., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37041-9_20
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.6996371
Improving Remote Sensing Segmentation with Adaptive Tokenization in Vision-Language Models
Le, N.-T., Hoang, T.-N., & Bui, C. V. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-1635-2_9
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
Zhang, S., Naseer, M., Xie, B., Suryanto, N., Qiu, S., Bentahar, J., Akhtar, N., & Shah, M. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_12
Benchmarking Multimodal Mathematical Reasoning: Prompt Effects, Modality Gaps, and Failure Modes
Görer, G., Osipenko, M., & Knispel, T. (2026) · Metrics · doi:10.3390/metrics3030011
“Second, cross-attention architectures preserve the language model’s token stream while introducing dedicated layers that allow textual representations to attend selectively to visual tokens (e.g., Flamingo, Alayrac et al. [15]).”
PhysRAG: Enhancing Physics-Awareness in Video Generation Via Retrieval-Augmented Generation
Cheng, K., Liu, Z., Gao, M., Song, C., & Tang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37429-5_32 · Cited by 3
Parallel energy storage: new systems with new AI beyond LLMs
Yang, J., Lin, F., & Wang, F. (2026) · Elsevier eBooks · doi:10.1016/b978-0-32-395419-8.00016-7
Dual-granularity image-text alignment for zero-shot composed image retrieval
Peng, W., Huang, S., Hu, Y., et al. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133463
Consciousness Emergent from Information Networks
Bi, Q. (2026) · Journal of Quantum Information Science · doi:10.4236/jqis.2026.162011
An AI Tutor System with a Virtual Whiteboard for Statistics Learning
Tran, T., Boussé, M., & Härmä, A. (2026) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon67543.2026.11574422
“Early systems such as BLIP-2 [29] and Flamingo [30] consisted of separate vision encoders combined with language models.”
REAP: Relevance-Guided Evidence-Unit Keyframe Extraction for Long Video Question Answering
Yang, M., Qu, H., & Zhao, J. Z. (2026) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis70043.2026.11572599
“Flamingo supports interleaved visual and textual inputs [10], BLIP-2 bridges frozen image encoders and large language models through a lightweight querying transformer [11], and LLaVA demonstrates the effectiveness of visual instruction tuning [12].”
Accelerating Multi-modal LLM Training with Adaptive Model Placement and Parallelization
Yin, Y., Shi, S., Wang, Q., et al. (2026) · doi:10.1109/infocom59046.2026.11571650
“Over the past few years, numerous MLLMs, such as GPT-4o, LLaVa, Flamingo, BLIP, Qwen2-VL, and DeepSeek-VL, have emerged [3,6,7,17]–[21].”
Cher, D., Iqbal, H., Xing, E., Wei, B., & Jacobs, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_25 · Cited by 2
Itahara, S., Suzuki, M., & Nishio, T. (2026) · doi:10.1109/infocom59046.2026.11571299
“As a preliminary to EP-VLMI, we provide a brief explanation of Flamingo [1], which consists of a vision encoder, i.e., ViT, and a language decoder comprising multiple language model (LM) layers and gated cross-attention-dense (XATT) layers.”
VideoEvent: Hierarchical and adaptive event modelling for complex video understanding
Zhang, F., Sun, X., Zhao, J., & Shang, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116502
MIRROR: Aligning Semantic Relations from Language to Image via Gromov–Wasserstein
Wang, H.-H., Wang, Y., & Ding, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_12 · Cited by 1
SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation
Asasi, S., Sincan, Ö. M., & Bowden, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_1
Personalizing MLLMs via Reinforced Multimodal Reference Game
Das, D., Talon, D., Wang, Y., Mancini, M., & Ricci, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37023-5_34
Enhancing domain adaptation of LLM via model composition in solving medical exam questions
Liang, Y., Zou, D., Xie, H., & Wang, F. L. (2026) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2026.100638
A Comprehensive Survey on Diffusion Model-Driven 3D Reconstruction: Methods, Datasets, and Prospects
Yao, Q., Liu, C., Liang, J., Li, H., Wu, X., & Teng, X. (2026) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi15070293
Yu, J., Zhuge, Y., Zhang, L., Huang, Z., Zhou, W., Wang, D., Lu, H., He, Y., & Chen, L. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02930-z
“Early efforts such as Flamingo (Alayrac et al., 2022) lay the groundwork for few-shot vision-language learning by integrating frozen vision encoders with autoregressive language models, demonstrating strong cross-modal language reasoning with minimal supervision.”
MemLearner: Learning to Query Context Memory for Video World Models
Yu, J., Gao, Bai, J., Qin, Y., Huang, K., Liu, Q., Wang, X., Wan, P., Gai, K., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37595-7_6 · Cited by 6
Information-Regularized Attention for Visual-Centric Reasoning
Sun, G. X., Wang, X., Patel, Y., Liu, M. Y., Tao, Z., & Krishnan, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37321-2_30
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
Jang, J. H., Kim, H., 이철원Lee, C., Kim, J. J., & Chun, S. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_28
A Lightweight Vision-Language Model for Disaster Image Summarization
Yoshizaki, H., Uchiyama, A., Hiromori, A., et al. (2026) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops68308.2026.11585419
Yuan, J., Li, Z., & Zhang, T. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109308
QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding
Peng, J., Song, B., Li, J., Li, H., Zhou, Y., Ji, R., & Tian, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37321-2_2 · Cited by 3
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
Yuan, B., Wang, Z., Luo, Y., Wang, S., & Huang, Z. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_20
Kim, S., & Kim, H. Y. (2026) · Finance research letters · doi:10.1016/j.frl.2026.110453
A Biologically Inspired Vision–Language Pipeline for Explainable Scene Reconstruction from RGB Data
Rodic, A. D. (2026) · Mechanisms and machine science · doi:10.1007/978-3-032-29127-1_34
A Spatial–Channel Aware Adaptive Connector for Multimodal Multi-Layer Feature Fusion
Zhang, H., Zhao, C., Wang, F., Wu, X., Ma, K., Zhu, H., Liang, S., & Zhang, P. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582221
“Driven by these advances, Multimodal Large Language Models (MLLMs) have rapidly evolved, achieving efficient vision-language alignment through the paradigm of ”frozen visual backbone + lightweight connector” [4]–[6].”
Issaoui, S., Alzakari, S. A., Saidi, I., Ejbali, R., & Serir, A. (2026) · Applied Sciences · doi:10.3390/app16136792 · Cited by 1
Progress in Neural NLP: Modeling, Learning, and Reasoning in the Era of Large-Scale Pretraining
Phonsa, G., Shanker, R., Rai, S., Tiwari, S. P., & Raju, M. V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23297-7_42
Nguyen, Q. H., Nguyen, L. T. O., Truong, P. B. K., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23297-7_19
Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation
He, Y., Kang, Z., Zhao, B., Wu, Z., Peng, J., & Wang, J. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582198
“…blocks; (b) Gato [46] uses a decoder-only architecture that processes observation and action subse-quences with prompting; (c) Flamingo [47] encodes a variable number of prompt images into a fixed number of tokens, similar to the Perceiver architecture, and includes robot action heads;…”
Hierarchical Emotion Recognition in Dialogue via RoBERTa with Agent Collaboration
Wu, W. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582423
“With the rise of large language models (LLMs), GPT-based agents have become widely used [20]–[22].”
Multi-Modal Diffusion Network for Medical Image Classification via Imaging and Clinical Data Fusion
Kolla, M., & Goud, K. S. (2026) · International Conference on Computing Theory and Wireless Communications (ICCTWC) · doi:10.1109/icctwc68241.2026.11583530
“Alayrac et al. [6] have introduced a vision-language model called Flamingo that is a large scale model that incorporates images and text through gated cross attention.”
DP-MSD: Dual-Perspective Multimodal Sarcasm Detection with Large Language Models
Sun, N., Gao, J., Tong, C., et al. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581744
“Flamingo [2] uses gated cross-attention to combine vision and language, while BLIP-2 [11] employs a Q-Former for efficient mapping.”
Yang, Q., Li, W., Guo, X., Harwood, M. C., Woo, P. Y. M., Zhang, J., Chen, Y., Zhang, K., & Yuan, Y. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3710717 · Cited by 1
Brain-inspired large model mindreading
Jin, J., Hu, Y., Wang, Z., Pan, Y., Ma, B., Dong, B., Dong, J., & Pei, G. (2026) · NeuroImage · doi:10.1016/j.neuroimage.2026.122108 · Cited by 2
Lavanya, S. R., Prabhavathi, M., Nafisa, F., et al. (2026) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan66520.2026.11588360
“6) LLM-enhanced narration : Replacing template engines with instruction-tuned large language models [21] to generate more fluent, contextually rich, and domain-adaptive narrations capable of describing novel or unusual events not covered by predefined templates.”
Learning Fine-Grained Video Anomaly Detection from Normal Videos
Wang, R., Tamura, Y., & Yamamoto, M. (2026) · Sensors · doi:10.3390/s26134314
“Layout-guided frameworks [23,24] further enhance spatial consistency by conditioning generation on segmentation masks or bounding boxes, while vision–language pretraining allows for stronger alignment between textual and visual content [17,18].”
Cognitive parsing network for action quality assessment
Li, J., Tian, Y., Huang, K., Jin, Y., & Huang, Z. (2026) · Neurocomputing · doi:10.2139/ssrn.7077838
CMDR: Contextual Multimodal Document Retrieval
Tanaka, R., Hasegawa, T., & Nishida, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37035-8_5
Generative Artificial Intelligence in Geography: Structure and Evolution of an Emerging Field
Ng, S. L., & Chu, C.-M. (2026) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi15070312
Feng, H., Wei, H., Wang, H., Li, S., Li, C., & Wu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_33
Li, Y., Liu, Y., Chen, Z., Chen, T., Chen, Z., Liu, L., Wang, L., & Zhou, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_12 · Cited by 1
Fang, T., Wang, Y., Kong, Z., Su, Z., Wang, J., Yu, C., & Wang, W. W. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01723-x · Cited by 1
“Representative works include BLIP-2 [3], Flamingo [13], OpenFlamingo [14], and MiniGPT-4 [15].”
LLM-Enhanced Topical Trend Detection at Snapchat
Zhao, H., Li, J., Bhattacharya, A., Ni, C., Yeung, J., Ye, J., Yang, K., Malu, A., & Malik, M. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808475
AraHarMeme: A Multimodal Benchmark for Harmful Meme Detection in Arabic
El-Amrany, S., Khaiari, A. E., Bekkali, A. E., et al. (2026) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse68839.2026.11597005
“Lin et al. [15] propose explainable multimodal models that expose conflicting visual and textual evidence, while evaluations of large vision–language models such as Flamingo and LLaVA show mixed results for harmful meme classification despite strong performance on general multimodal tasks [5], [6].”
Composable Multimodal Semantic Communication: A Lightweight Large AI Model Approach
Zhao, T., Li, F., Huang, X., et al. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3707756
Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning
Chen, J., Li, D., Zhang, H., Cai, Y., Su, L., Guo, J., Shi, D., Yin, D., & Bi, K. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809695 · Cited by 2
A survey of transformers based on their input modalities
Sharma, P., & Jain, S. K. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07378-9 · Cited by 1
Fu, X., Fan, C., & Yu, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2852-2_38
EcoSurve: AI-Powered Surveillance Video Summarization and Retrieval for Sustainable Smart Cities
Saboo, S., Boni, L., Arora, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-26217-2_6
PFMamba: A Lightweight Multimodal Fusion Framework for Robust Encrypted Traffic Classification
Zhang, J., Cheng, G., Chen, Z., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2859-1_42
PhD Forum 2025 - Development of Interpretable and Efficient Visual Question Answering Models
Chowdhury, S., & Soni, B. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-26269-1_16
SelCo: Efficient Distributed Multimodal LLM Training with Selective Co-location
Hao, Y. W., Wu, X., Peng, J., Wang, T., & Gu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3447-9_42
CoRa-Web: Hierarchical Visual Planning for Robust and Efficient Web Agents
Wang, Y., Wu, J., & Li, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3438-7_48
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Chen, Y., Li, Y., Shen, Y., Liu, M., Zheng, T., Fu, B., Lin, Q., Yu, Z., & Shi, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37032-7_19
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
