{"work":{"id":"a110f764-38dc-41b2-a802-53744ecea1fc","openalex_id":null,"doi":null,"arxiv_id":"2204.14198","raw_key":null,"title":"Flamingo: a Visual Language Model for Few-Shot Learning","authors":null,"authors_text":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson","year":2022,"venue":"cs.CV","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.","external_url":"https://arxiv.org/abs/2204.14198","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T11:09:22.382438+00:00","pith_arxiv_id":"2204.14198","created_at":"2026-05-08T18:44:01.899843+00:00","updated_at":"2026-05-24T11:09:22.382438+00:00","title_quality_ok":true,"display_title":"Flamingo: a Visual Language Model for Few-Shot Learning","render_title":"Flamingo: a Visual Language Model for Few-Shot Learning"},"hub":{"state":{"work_id":"a110f764-38dc-41b2-a802-53744ecea1fc","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":53,"external_cited_by_count":null,"distinct_field_count":11,"first_pith_cited_at":"2022-05-12T16:03:26+00:00","last_pith_cited_at":"2026-05-19T13:58:24+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-26T01:26:06.194709+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":16},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":15},{"context_polarity":"baseline","n":1},{"context_polarity":"unclear","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:19:33.573899+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","work_id":"63d03f4d-15f4-4583-8286-913c19f02294","shared_citers":10},{"title":"Learning Transferable Visual Models From Natural Language Supervision","work_id":"6de86bb5-27bd-4d5c-8b89-967ebfc52659","shared_citers":10},{"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","shared_citers":9},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":8},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":7},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":7},{"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","shared_citers":7},{"title":"Training Compute-Optimal Large Language Models","work_id":"b2faf28d-86b7-429c-bc42-469458efc246","shared_citers":7},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":6},{"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","shared_citers":6},{"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","shared_citers":6},{"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","shared_citers":6},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":6},{"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","shared_citers":5},{"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","shared_citers":5},{"title":"Finetuned Language Models Are Zero-Shot Learners","work_id":"7ed6cdaa-ed67-4db4-aceb-b7e1b0e6e7c4","shared_citers":5},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":5},{"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","shared_citers":5},{"title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","work_id":"47ce8be9-e500-407d-af41-ac2d132215eb","shared_citers":5},{"title":"Coca: Con- trastive captioners are image-text foundation models","work_id":"5dd5bf10-d548-40ff-9b6c-6735129b27ee","shared_citers":4},{"title":"Combined scaling for zero-shot transfer learning","work_id":"38fb2f70-f077-4765-8cb7-088bca890892","shared_citers":4},{"title":"Florence: A new foundation model for computer vision","work_id":"99823072-36a8-4b10-9ef5-a7f91da74650","shared_citers":4},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":4},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":4}],"time_series":[{"n":7,"year":2022},{"n":7,"year":2023},{"n":3,"year":2024},{"n":16,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:19:25.115297+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:20:14.426577+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Flamingo: a Visual Language Model for Few-Shot Learning","claims":[{"claim_text":"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","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Flamingo: a Visual Language Model for Few-Shot Learning because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:20:19.194471+00:00"}},"summary":{"title":"Flamingo: a Visual Language Model for Few-Shot Learning","claims":[{"claim_text":"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","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Flamingo: a Visual Language Model for Few-Shot Learning because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","work_id":"63d03f4d-15f4-4583-8286-913c19f02294","shared_citers":10},{"title":"Learning Transferable Visual Models From Natural Language Supervision","work_id":"6de86bb5-27bd-4d5c-8b89-967ebfc52659","shared_citers":10},{"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","shared_citers":9},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":8},{"title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","shared_citers":7},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":7},{"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","shared_citers":7},{"title":"Training Compute-Optimal Large Language Models","work_id":"b2faf28d-86b7-429c-bc42-469458efc246","shared_citers":7},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":6},{"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","shared_citers":6},{"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","shared_citers":6},{"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","shared_citers":6},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":6},{"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","shared_citers":5},{"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","shared_citers":5},{"title":"Finetuned Language Models Are Zero-Shot Learners","work_id":"7ed6cdaa-ed67-4db4-aceb-b7e1b0e6e7c4","shared_citers":5},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":5},{"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","shared_citers":5},{"title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","work_id":"47ce8be9-e500-407d-af41-ac2d132215eb","shared_citers":5},{"title":"Coca: Con- trastive captioners are image-text foundation models","work_id":"5dd5bf10-d548-40ff-9b6c-6735129b27ee","shared_citers":4},{"title":"Combined scaling for zero-shot transfer learning","work_id":"38fb2f70-f077-4765-8cb7-088bca890892","shared_citers":4},{"title":"Florence: A new foundation model for computer vision","work_id":"99823072-36a8-4b10-9ef5-a7f91da74650","shared_citers":4},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":4},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":4}],"time_series":[{"n":7,"year":2022},{"n":7,"year":2023},{"n":3,"year":2024},{"n":16,"year":2026}],"dependency_candidates":[]},"authors":[]}}