AISafetyHot
An open-source project I participated in during the National Day holiday. It brings together AI safety news, research, and events, with an MCP interface for agents.
Demo credit: AI Safety HOT · README Explore the website ↗
Selected work from AI safety, LLM agents, software security, computer vision, and climate research.
An open-source project I participated in during the National Day holiday. It brings together AI safety news, research, and events, with an MCP interface for agents.
Demo credit: AI Safety HOT · README Explore the website ↗
A UNDP-administered UNV research internship output on sea-level rise, nutrient loading, coastal squeeze, and blue carbon mitigation.
An open-source agent safety platform for runtime session discovery, controlled tool calls, human approval, and risk auditing.
A multi-agent reinforcement learning framework for dynamic security constraints in LLM code generation.
An automated security analysis pipeline developed at the Fudan Software Engineering (CodeWisdom) Lab, combining CodeQL static analysis and LLM-based vulnerability judgement.
A cross-platform image copyright and identity authentication system with a neural watermarking model and mobile image processing.
A spectral-frequency enhanced selective state space model for efficient visual correspondence pruning.