Sotabase

Career

· PostDoc, UC Berkeley2024–

Publications (30)

Learning to Fuzz from Symbolic Execution with Application to Smart Contracts
Conference on Computer and Communications Security · 2019
273
cited
Large Language Models for Code: Security Hardening and Adversarial Testing
Conference on Computer and Communications Security · 2023
209
cited
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
International Conference on Learning Representations · 2023
161
cited
Debin: Predicting Debug Information in Stripped Binaries
Conference on Computer and Communications Security · 2018
136
cited
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
International Conference on Machine Learning · 2021
135
cited
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
Neural Information Processing Systems · 2024
81
cited
Formal Mathematical Reasoning: A New Frontier in AI
arXiv.org · 2024
72
cited
Instruction Tuning for Secure Code Generation
International Conference on Machine Learning · 2024
53
cited
Exploiting LLM Quantization
Neural Information Processing Systems · 2024
52
cited
Learning to Explore Paths for Symbolic Execution
Conference on Computer and Communications Security · 2021
47
cited
Progent: Programmable Privilege Control for LLM Agents
arXiv.org · 2025
34
cited
Type-Constrained Code Generation with Language Models
Proc. ACM Program. Lang. · 2025
26
cited
Learning fast and precise numerical analysis
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2020
22
cited
BaxBench: Can LLMs Generate Correct and Secure Backends?
International Conference on Machine Learning · 2025
20
cited
On Distribution Shift in Learning-based Bug Detectors
International Conference on Machine Learning · 2022
20
cited
Controlling Large Language Models to Generate Secure and Vulnerable Code
arXiv.org · 2023
18
cited
Black-Box Adversarial Attacks on LLM-Based Code Completion
International Conference on Machine Learning · 2024
12
cited
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2023
11
cited
Efficient high-utility occupancy itemset mining algorithm on massive data
Expert systems with applications · 2022
10
cited
Learning to find naming issues with big code and small supervision
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2021
10
cited
Sotabase
Jingxuan He | Researcher Profile | Sotabase | Sotabase