Jun-Yan Zhu
E326792
Jun-Yan Zhu is a computer scientist and researcher known for his influential work in computer vision and generative models, particularly in image-to-image translation.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Jun-Yan Zhu canonical | 3 |
How this entity was disambiguated
This entity first appeared as the object of triple T3094218 — 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: Jun-Yan Zhu Context triple: [Alexei Efros, notableStudent, Jun-Yan Zhu]
-
A.
Langche Zeng
Langche Zeng is a political scientist and quantitative methodologist known for his collaborative work with Gary King on statistical methods in social science research.
-
B.
Yuhuai Wu
Yuhuai Wu is an AI researcher and entrepreneur known for his work on large language models and as a member of Elon Musk’s xAI team.
-
C.
Yanluo Wang
Yanluo Wang is the Chinese deity who presides over the underworld and judges the souls of the dead.
-
D.
Liwen Shao
Liwen Shao is a brilliant and ambitious Chinese businesswoman and technologist in the Pacific Rim universe, known for her pivotal role in developing advanced Jaeger drone technology.
-
E.
Xiaodong Chen
Xiaodong Chen is a prominent materials scientist and nanotechnology researcher who serves as editor-in-chief of the journal ACS Nano.
- 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: Jun-Yan Zhu Target entity description: Jun-Yan Zhu is a computer scientist and researcher known for his influential work in computer vision and generative models, particularly in image-to-image translation.
-
A.
Langche Zeng
Langche Zeng is a political scientist and quantitative methodologist known for his collaborative work with Gary King on statistical methods in social science research.
-
B.
Yuhuai Wu
Yuhuai Wu is an AI researcher and entrepreneur known for his work on large language models and as a member of Elon Musk’s xAI team.
-
C.
Yanluo Wang
Yanluo Wang is the Chinese deity who presides over the underworld and judges the souls of the dead.
-
D.
Liwen Shao
Liwen Shao is a brilliant and ambitious Chinese businesswoman and technologist in the Pacific Rim universe, known for her pivotal role in developing advanced Jaeger drone technology.
-
E.
Xiaodong Chen
Xiaodong Chen is a prominent materials scientist and nanotechnology researcher who serves as editor-in-chief of the journal ACS Nano.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
academic
ⓘ
computer scientist ⓘ researcher ⓘ |
| awardReceived | best paper awards at major vision or graphics conferences ⓘ |
| citations | highly cited in computer vision and generative modeling literature ⓘ |
| coAuthorOf | CycleGAN paper ⓘ |
| contributedTo |
GAN-based image manipulation
ⓘ
controllable image generation ⓘ methods for unpaired image-to-image translation ⓘ |
| degree | PhD in computer science ⓘ |
| educatedAt |
CMU
ⓘ
surface form:
Carnegie Mellon University
Massachusetts Institute of Technology ⓘ |
| fieldOfWork |
computer vision
ⓘ
generative models ⓘ image synthesis ⓘ image-to-image translation ⓘ machine learning ⓘ |
| givesTalkAt | major AI and vision conferences ⓘ |
| hasAcademicAdvisor | Antonio Torralba ⓘ |
| hasAcademicPublicationType |
conference papers
ⓘ
journal articles ⓘ preprints ⓘ |
| hasAffiliation |
Adobe Research
ⓘ
Meta AI ⓘ
surface form:
Facebook AI Research
Computer Science and Artificial Intelligence Laboratory (CSAIL) ⓘ
surface form:
MIT Computer Science and Artificial Intelligence Laboratory
OpenAI ⓘ Robotics Institute, Carnegie Mellon University ⓘ
surface form:
Robotics Institute at Carnegie Mellon University
School of Computer Science at Carnegie Mellon University ⓘ |
| hasEmployer |
CMU
ⓘ
surface form:
Carnegie Mellon University
|
| hasRole | university faculty member ⓘ |
| knownFor |
CycleGAN
ⓘ
surface form:
Cycle-consistent adversarial networks (CycleGAN)
|
| nationality | Chinese ⓘ |
| notableFor |
generative adversarial networks applications
ⓘ
image-to-image translation research ⓘ |
| occupation |
computer science researcher
ⓘ
professor ⓘ |
| positionHeld |
assistant professor
ⓘ
associate professor ⓘ |
| publishedIn |
IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ⓘ
surface form:
CVPR
European Conference on Computer Vision ⓘ
surface form:
ECCV
IEEE International Conference on Computer Vision ⓘ
surface form:
ICCV
ICLR ⓘ NeurIPS ⓘ ACM SIGGRAPH ⓘ
surface form:
SIGGRAPH
|
| researchInterest |
3D vision
ⓘ
creative AI ⓘ unsupervised learning for images ⓘ visual recognition ⓘ |
| supervises | PhD students in computer vision and machine learning ⓘ |
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: Jun-Yan Zhu Description of subject: Jun-Yan Zhu is a computer scientist and researcher known for his influential work in computer vision and generative models, particularly in image-to-image translation.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.