Jun Zhao

Artificial Intelligence · with Dou · 2023

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 23 citations into it

Whom Jun Zhao trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton

Papers from Jun Zhao's perspective

Ordered by how strongly the researchers Jun Zhao trusts endorse each paper. Same corpus, a different order for every researcher.

1. Proximal Policy Optimization Algorithms (arXiv.org)
2. Training Products of Experts by Minimizing Contrastive Divergence
3. Scaling Laws for Neural Language Models (arXiv.org)
4. Learning to summarize from human feedback
5. Fine-Tuning Language Models from Human Preferences
6. Scalable agent alignment via reward modeling: a research direction (arXiv.org)
7. Constitutional AI: Harmlessness from AI Feedback (arXiv.org)
8. Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback
9. LLaMA: Open and Efficient Foundation Language Models (arXiv.org)
10. Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models

Their papers

• Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback (2023) — 90 citations