Research and engineering
Projects
Selected work from AI safety, LLM agents, software security, computer vision, and climate research.
International Organization Internship: UNDP-administered UNV Mangrove Research
A UNDP-administered UNV research internship output on sea-level rise, nutrient loading, coastal squeeze, and blue carbon mitigation.
XSafeClaw: Agent Runtime Safety Governance
An open-source agent safety platform for runtime session discovery, controlled tool calls, human approval, and risk auditing.
SafeCodeRL: Safety-Constrained LLM Code Generation
A multi-agent reinforcement learning framework for dynamic security constraints in LLM code generation.
VulnSeeker: CodeQL and LLM Security Analysis
An automated security analysis pipeline that combines CodeQL static analysis and LLM-based vulnerability judgement.
Robust Deep-Learning Watermark Mobile Application
A cross-platform image copyright and identity authentication system with a neural watermarking model and mobile image processing.
SFMambaNet: Spectral-Frequency Correspondence Pruning
A spectral-frequency enhanced selective state space model for efficient visual correspondence pruning.