Prafulla Dhariwal
E441105
Prafulla Dhariwal is an AI researcher and engineer known for his influential work at OpenAI on reinforcement learning and generative models, including contributions to systems like PPO and DALL·E.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Prafulla Dhariwal canonical | 4 |
Statements (41)
| Predicate | Object |
|---|---|
| instanceOf |
artificial intelligence researcher
ⓘ
computer scientist ⓘ person ⓘ software engineer ⓘ |
| affiliation | OpenAI research NERFINISHED ⓘ |
| coAuthorOf |
"Proximal Policy Optimization Algorithms"
NERFINISHED
ⓘ
research papers on diffusion models ⓘ research papers on large-scale generative models ⓘ |
| contributedTo |
development of DALL·E 2 at OpenAI
ⓘ
development of DALL·E at OpenAI ⓘ development of PPO at OpenAI ⓘ development of diffusion-based generative image models at OpenAI ⓘ |
| employer | OpenAI NERFINISHED ⓘ |
| fieldOfWork |
artificial intelligence
ⓘ
deep learning ⓘ diffusion models ⓘ generative modeling ⓘ machine learning ⓘ reinforcement learning ⓘ |
| knownFor |
contributions to DALL·E
ⓘ
contributions to Proximal Policy Optimization (PPO) ⓘ work in artificial intelligence ⓘ work in generative models ⓘ work in machine learning ⓘ work in reinforcement learning ⓘ |
| notableFor |
advancing diffusion models for image synthesis
ⓘ
helping popularize PPO in reinforcement learning ⓘ |
| notableWork |
DALL·E
NERFINISHED
ⓘ
DALL·E 2 NERFINISHED ⓘ Proximal Policy Optimization Algorithms NERFINISHED ⓘ diffusion-based image generation models at OpenAI ⓘ |
| researchInterest |
deep reinforcement learning
ⓘ
policy gradient methods ⓘ reinforcement learning algorithms ⓘ scalable generative models ⓘ text-to-image generation ⓘ |
| role |
machine learning engineer
ⓘ
research scientist ⓘ |
| worksOn |
applications of reinforcement learning to control tasks
ⓘ
large-scale neural networks ⓘ training algorithms for generative models ⓘ |
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Tom B. Brown
subject surface form:
Language Models are Few-Shot Learners