Kai Zhao

The paper proposes LiveFuzz, a directed greybox fuzzing technique that detects the exploitability of third-party library vulnerabilities from client programs without requiring pre-existing proof-of-concepts.

The paper introduces Semantic Compliance Hijacking (SCH), a novel payload-less attack that exploits LLM agent supply chains by manipulating compliance rules to force unauthorized code generation, achieving high success rates against current security tools.

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step reasoning.

OmniOPD introduces a logit-free, chunk-level distillation framework that improves on standard On-Policy Distillation by using semantic similarity and peak-entropy scheduling, achieving state-of-the-art performance even with black-box teachers.

The paper introduces ClinEnv, a novel interactive, multi-stage benchmark designed to evaluate LLMs' decision-making and information-gathering process during longitudinal inpatient medical simulations.

The paper introduces CASTER, a new human-centric task for evaluating User-Generated Content (UGC) resonance, and proposes MEDEA, an architecture that uses a Social Chain-of-Thought mechanism to simulate community reactions for quality assessment.