Xinyun Chen
Google DeepMind (United Kingdom) · 106 works · 7,558 citations · h-index 30
Top works
- Competition-level code generation with AlphaCode
- Delving into Transferable Adversarial Examples and Black-box Attacks
- Scaling Instruction-Finetuned Language Models
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Gemini: A Family of Highly Capable Multimodal Models
- Adversarial Example Defense: Ensembles of Weak Defenses are not Strong
- Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong
- Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
- Learning to Perform Local Rewriting for Combinatorial Optimization
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Large Language Models as Optimizers
- Tree-to-tree Neural Networks for Program Translation
- Natural SQL: Making SQL Easier to Infer from Natural Language Specifications
- Fooling Vision and Language Models Despite Localization and Attention Mechanism
- Towards Robustness of Text-to-SQL Models against Synonym Substitution
- Learning to Perform Local Rewriting for Combinatorial Optimization
- Teaching Large Language Models to Self-Debug
- Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization
- Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension
- Larger language models do in-context learning differently