Sotabase

Career

· Assistant Professor, Department of Computer Science, University of California, Los Angeles (UCLA)2026–
· Research Intern, Google DeepMind2024–
· Experience, Amazon AWS AI Labs
· Amazon AWS AI Labs
· Postdoctoral Scientist, AWS Agentic AI
· PhD in Computer Science, Columbia University
· Experience, IBM Research
· IBM Research

Publications (22)

Deep Learning Based Vulnerability Detection: Are We There Yet?
IEEE Transactions on Software Engineering · 2020
666
cited
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Neural Information Processing Systems · 2023
202
cited
Vulnerability Detection with Code Language Models: How Far are We?
International Conference on Software Engineering · 2024
163
cited
NatGen: generative pre-training by “naturalizing” source code
ESEC/SIGSOFT FSE · 2022
146
cited
CODIT: Code Editing With Tree-Based Neural Models
IEEE Transactions on Software Engineering · 2018
124
cited
CoCoMIC: Code Completion by Jointly Modeling In-file and Cross-file Context
International Conference on Language Resources and Evaluation · 2022
95
cited
Patching as Translation: the Data and the Metaphor
International Conference on Automated Software Engineering · 2020
74
cited
CYCLE: Learning to Self-Refine the Code Generation
Proc. ACM Program. Lang. · 2024
65
cited
VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements
IEEE International Conference on Software Analysis, Evolution, and Reengineering · 2021
65
cited
TRACED: Execution-Aware Pre-Training for Source Code
International Conference on Software Engineering · 2023
55
cited
SemCoder: Training Code Language Models with Comprehensive Semantics
Neural Information Processing Systems · 2024
36
cited
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
Annual Meeting of the Association for Computational Linguistics · 2021
36
cited
Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
International Conference on Learning Representations · 2023
34
cited
Contrastive Learning for Source Code with Structural and Functional Properties
arXiv.org · 2021
24
cited
Automated Code Editing With Search-Generate-Modify
IEEE Transactions on Software Engineering · 2023
15
cited
CONCORD: Clone-Aware Contrastive Learning for Source Code
International Symposium on Software Testing and Analysis · 2023
15
cited
TraceFixer: Execution Trace-Driven Program Repair
2023
5
cited
Automatic Code Annotation Generation Based on Heterogeneous Graph Structure
IEEE International Conference on Software Analysis, Evolution, and Reengineering · 2023
3
cited
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
2026
Semantic-aware Source Code Modeling
International Conference on Automated Software Engineering · 2024
Sotabase
Yangruibo Ding | Researcher Profile | Sotabase | Sotabase