Li Zhang

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on major benchmarks.

This paper proposes a novel data-driven image encryption framework that learns the chaotic map dynamics directly from the image data, enhancing security beyond traditional fixed-map schemes.

The paper proposes a novel Retrieval-Augmented Generation (RAG) framework utilizing Large Language Models (LLMs) for real-time, intelligent detection and mitigation of evasive Carpet-Bombing DDoS attacks in Software-Defined Networking (SDN).

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-the-art performance on benchmark tasks.

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge to the optimal Pareto frontier.

The paper introduces new benchmarks for complex asynchronous planning and demonstrates that general constraint satisfaction formalizers (like CP-SAT) significantly outperform direct LLM planning or traditional domain-specific formalizers (like PDDL2.1) when handling large, complex, and time-sensitive tasks.