Zhenyu Chen
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
DuCodeMark introduces a robust, dual-purpose watermarking technique that embeds ownership signals into code datasets, ensuring protection across both source-code generation and decompilation tasks.
FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the code's functionality.
The paper proposes a novel test-driven pipeline that simulates realistic code generation scenarios to detect privacy leaks in LLMs, achieving a 2.56x increase in detected leakage compared to existing methods.
This paper presents OneCanvas, a method for 3D scene understanding in Vision-Language Models that aggregates patch features onto a single panoramic canvas.
This paper reviews 336 GUI-agent papers from 2018 to 2026, examining the research landscape, architectures, evaluation, software lifecycle concerns, and future opportunities.
This paper introduces FlowMuT, a mutation-based testing method for deep learning frameworks that captures runtime tensor states and operator input requirements to identify bugs.
Papers
Grounding Deep Learning Framework Testing in Data Flow
Jiatao Ge, Yanzhou Mu, Yinglong Zou, Yibo Hu +2 more
This paper introduces FlowMuT, a mutation-based testing method for deep learning frameworks that captures runtime tensor states and operator input requirements to identify bugs.