Profiles2020-2024
Denny Zhou
Google DeepMind
20Papers
11Last author
35Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- Teaching Large Language Models to Self-DebugAuthor 4 of 6ICLR 2024 · 1,085 citations
- Large Language Models Cannot Self-Correct Reasoning YetAuthor 7 of 8ICLR 2024 · 858 citations
- Large Language Models as OptimizersAuthor 6 of 7ICLR 2024 · 817 citations
- Chain-of-Thought Reasoning Without PromptingAuthor 2 of 2NeurIPS 2024 · 305 citations
- Large Language Models as Analogical ReasonersAuthor 8 of 8ICLR 2024 · 155 citations
- Premise Order Matters in Reasoning with Large Language ModelsAuthor 4 of 4ICML 2024 · 59 citations
- Large Language Models Can Be Easily Distracted by Irrelevant ContextAuthor 8 of 8ICML 2023 · 970 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsAuthor 8 of 8ICLR 2023 · 681 citations
- Least-to-Most Prompting Enables Complex Reasoning in Large Language ModelsAuthor 1 of 11ICLR 2023 · 318 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAuthor 9 of 9NeurIPS 2022 · 22,562 citations
- Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm PerformanceAuthor 6 of 7ICML 2022 · 43 citations
- Auto-scaling Vision Transformers without TrainingAuthor 6 of 6ICLR 2022 · 27 citations
- Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified BackpropagationAuthor 5 of 6NeurIPS 2022 · 25 citations
- Fast WordPiece TokenizationAuthor 5 of 5EMNLP 2021
- MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited DevicesAuthor 6 of 6ACL 2020 · 660 citations
- Compositional Generalization via Neural-Symbolic Stack MachinesAuthor 5 of 5NeurIPS 2020 · 112 citations
- Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading ComprehensionAuthor 4 of 6ICLR 2020 · 109 citations
- Black-box Off-policy Estimation for Infinite-Horizon Reinforcement LearningAuthor 5 of 5ICLR 2020 · 33 citations
- Go Wide, Then Narrow: Efficient Training of Deep Thin NetworksAuthor 1 of 9ICML 2020 · 21 citations
- Deep State-Space Generative Model For Correlated Time-to-Event PredictionsAuthor 2 of 7KDD 2020 · 8 citations
