Yuntao Bai
Nuclear and High Energy Physics · arXiv.org · 2010–2024
A researcher in the Science corpus: 18 papers; trusts 17 researchers and is trusted by 1 researcher here, as inferred from the citation graph.
Subfields
- Nuclear and High Energy Physics — 49 citations into it
- Statistical and Nonlinear Physics — 21 citations into it
- Geometry and Topology — 16 citations into it; #7,339 of 7,422 by trust here, #5,748 by citations
- Atomic and Molecular Physics, and Optics — 9 citations into it
- Mathematical Physics — 9 citations into it; #8,459 of 8,562 by trust here, #6,594 by citations
- Algebra and Number Theory — 6 citations into it
- Discrete Mathematics and Combinatorics — 6 citations into it; #1,994 of 2,017 by trust here, #1,382 by citations
Whom Yuntao Bai trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- F. Cachazo
- N. Arkani-Hamed
- J. Bourjaily
- A. Hodges
- Paul Christiano
- Z. Bern
- Song He
- Joshua S. Scott
- Stanislav Fort
- Geoffrey E. Hinton
Who trusts Yuntao Bai overall
- Hanze Dong
- Wei Xiong
- Zhiqing Sun
- Tomasz Korbak
- Richard Ngo
- Kenneth Li
- Alexander Wei
- Harrison Lee
- Angelica Chen
- Zheng-Xin Yong
Papers from Yuntao Bai's perspective
Ordered by how strongly the researchers Yuntao Bai trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet: A large-scale hierarchical image database
- Language Models are Few-Shot Learners (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022) — 4,254 citations
- Constitutional AI: Harmlessness from AI Feedback (2022) — 3,377 citations
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022) — 837 citations
- Predictability and Surprise in Large Generative Models (2022) — 365 citations
- In-context Learning and Induction Heads (2022) — 942 citations
- Language Models (Mostly) Know What They Know (2022) — 1,782 citations
- Discovering Language Model Behaviors with Model-Written Evaluations (2022) — 917 citations
- The Capacity for Moral Self-Correction in Large Language Models (2023) — 214 citations
- Measuring Progress on Scalable Oversight for Large Language Models (2022) — 226 citations
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (2024) — 489 citations
- Many-shot Jailbreaking (2024) — 300 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- A General Language Assistant as a Laboratory for Alignment (2021) — 1,175 citations
- The Astronomical Journal (2019)
- Positive geometries and canonical forms (2017) — 249 citations
- Scattering forms and the positive geometry of kinematics, color and the worldsheet (2017) — 264 citations
- The ATLAS Simulation Infrastructure (2010) — 2,153 citations