“Multimodal Neurons in Artificial Neural Networks”
E1313833
UNEXPLORED
“Multimodal Neurons in Artificial Neural Networks” is a research paper that investigates how individual units in large vision-language models respond to both visual and textual concepts, revealing neuron-level representations that link images and words.
All labels observed (1)
| Label | Occurrences |
|---|---|
| “Multimodal Neurons in Artificial Neural Networks” canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T18255511 — 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: “Multimodal Neurons in Artificial Neural Networks” Context triple: [Gabriel Goh, coAuthorOf, “Multimodal Neurons in Artificial Neural Networks”]
-
A.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
B.
Neural Filters
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
A Neurocomputational Perspective
A Neurocomputational Perspective is a philosophical and scientific work by Paul Churchland that advances a connectionist, brain-based account of cognition and challenges traditional symbolic and folk-psychological views of the mind.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- 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: “Multimodal Neurons in Artificial Neural Networks” Target entity description: “Multimodal Neurons in Artificial Neural Networks” is a research paper that investigates how individual units in large vision-language models respond to both visual and textual concepts, revealing neuron-level representations that link images and words.
-
A.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
B.
Neural Filters
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
A Neurocomputational Perspective
A Neurocomputational Perspective is a philosophical and scientific work by Paul Churchland that advances a connectionist, brain-based account of cognition and challenges traditional symbolic and folk-psychological views of the mind.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- F. None of above. chosen
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.