Peng Chen
14 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
FuzzAgent introduces a multi-agent, evolutionary system that significantly improves library fuzzing by iteratively refining the test suite based on runtime feedback, achieving superior coverage and bug detection compared to state-of-the-art methods.
The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a lightweight screening phase.
EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.
EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.
The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.
The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.
SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.
SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.
A new approach to generating proof-of-concept inputs for one-day vulnerabilities using a language model and an oracle.
This paper proposes Error-conditioned Neural Solvers (ENS) for neural surrogate models to iteratively correct predictions by using the PDE residual field as input, achieving higher accuracy than optimization-based methods.
The paper introduces DataGovBench, a benchmark for evaluating Large Language Models in real-world data analysis scenarios, revealing significant performance gaps with state-of-the-art models.
Aries is a full-stack experimentation framework for autonomous agents that separates task semantics from execution configurations, reconstructs agent trajectories, and exposes stateful tool execution.
The paper introduces the Last Secure Code Benchmark to evaluate secure code generation by coding agents.
HarnessMinimizer is a system for efficiently minimizing C/C++ library fuzzing harnesses to simplify crash investigation.