Xinbo Xu

Artificial Intelligence · 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 — 42 citations into it
• Large Language Models — 14 citations into it
• Safety, Robustness & Interpretability — 11 citations into it
• Health Informatics — 6 citations into it

Whom Xinbo Xu trusts

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

1. Iason Gabriel (in Artificial Intelligence)

Papers from Xinbo Xu's perspective

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

1. Language Models are Few-Shot Learners (Neural Information Processing Systems)
2. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (Journal of machine learning research)
3. Deep Reinforcement Learning from Human Preferences (Neural Information Processing Systems)
4. Training language models to follow instructions with human feedback (Neural Information Processing Systems)
5. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (arXiv.org)
6. A General Language Assistant as a Laboratory for Alignment
7. Multitask Prompted Training Enables Zero-Shot Task Generalization
8. AI safety via debate
9. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor (International Conference on Machine Learning)
10. PaLM 2 Technical Report

Their papers

• Safe RLHF: Safe Reinforcement Learning from Human Feedback (2023) — 750 citations