One Model To Learn Them All
E899035
"One Model To Learn Them All" is a research paper that introduces a unified neural network architecture capable of handling multiple tasks and modalities within a single model.
All labels observed (1)
| Label | Occurrences |
|---|---|
| One Model To Learn Them All canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003398 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: One Model To Learn Them All Context triple: [Łukasz Kaiser, coAuthorOf, One Model To Learn Them All]
-
A.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
B.
Language Models are Few-Shot Learners
"Language Models are Few-Shot Learners" is a landmark research paper that demonstrated large-scale transformer-based language models can perform diverse tasks from just a few examples without task-specific training.
-
C.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
D.
Attention Is All You Need
"Attention Is All You Need" is the landmark 2017 research paper that introduced the Transformer architecture and revolutionized modern natural language processing and sequence modeling.
-
E.
Neural Discrete Representation Learning
Neural Discrete Representation Learning is a machine learning framework that introduces Vector Quantized Variational Autoencoders (VQ-VAE) to learn discrete latent representations for high-dimensional data such as images, audio, and video.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: One Model To Learn Them All Target entity description: "One Model To Learn Them All" is a research paper that introduces a unified neural network architecture capable of handling multiple tasks and modalities within a single model.
-
A.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
B.
Language Models are Few-Shot Learners
"Language Models are Few-Shot Learners" is a landmark research paper that demonstrated large-scale transformer-based language models can perform diverse tasks from just a few examples without task-specific training.
-
C.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
D.
Attention Is All You Need
"Attention Is All You Need" is the landmark 2017 research paper that introduced the Transformer architecture and revolutionized modern natural language processing and sequence modeling.
-
E.
Neural Discrete Representation Learning
Neural Discrete Representation Learning is a machine learning framework that introduces Vector Quantized Variational Autoencoders (VQ-VAE) to learn discrete latent representations for high-dimensional data such as images, audio, and video.
- F. None of above. chosen
Statements (37)
| Predicate | Object |
|---|---|
| instanceOf |
machine learning paper
ⓘ
research paper ⓘ scientific publication ⓘ |
| addresses |
handling multiple tasks in one model
ⓘ
scaling neural networks to diverse domains ⓘ |
| aimsTo |
improve generalization across tasks
ⓘ
reduce need for task-specific architectures ⓘ unify vision, language, and other modalities ⓘ |
| contributesTo |
research on general-purpose models
ⓘ
research on unified architectures ⓘ |
| describes |
neural network that can process different modalities
ⓘ
training a single model on diverse tasks ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ multimodal learning ⓘ multitask learning ⓘ |
| focusesOn |
multi-modal learning
ⓘ
multi-task learning ⓘ single model for multiple tasks ⓘ unified neural network architecture ⓘ |
| goal |
handle multiple modalities within a single model
ⓘ
handle multiple tasks within a single model ⓘ |
| hasModality |
language
ⓘ
other data modalities ⓘ vision ⓘ |
| hasTitle | One Model To Learn Them All NERFINISHED ⓘ |
| proposes |
shared architecture across tasks and modalities
ⓘ
single neural network handling multiple tasks ⓘ |
| relatedTo |
multi-domain learning
ⓘ
multitask neural networks ⓘ representation learning ⓘ transfer learning ⓘ |
| typeOfArchitecture |
multi-task neural network
GENERATED
ⓘ
unified model GENERATED ⓘ |
| uses |
deep neural networks
ⓘ
shared parameters across tasks ⓘ task-specific output heads ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: One Model To Learn Them All Description of subject: "One Model To Learn Them All" is a research paper that introduces a unified neural network architecture capable of handling multiple tasks and modalities within a single model.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Łukasz Kaiser