Weishi Shi

Mixing Expertise with Confidence: A Mixture of Expert Framework for Robust Multi-Modal Continual Learner

Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption

Label-Wise uncertainty decomposition for Multi-label Classification by Maximizing Type II Likelihood

Learning to Compose: Continual Visual QA through a Dual-Purpose Mixture-of-Experts Framework

Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity