🏢 University at Buffalo

ProxyFusion, a novel face feature fusion method, achieves real-time performance by using sparse experts to weight features without relying on intermediate representations or metadata, substantially im…

First-order policy optimization for robust average-cost MDPs achieves linear convergence with increasing step size and 0(1/ε) complexity with constant step size, solving a critical gap in existing res…

Two novel first-order algorithms, FOSL and MemCS, efficiently solve multi-block minimax bilevel optimization problems, significantly improving performance in deep AUC maximization and robust meta-lear…

A novel probability-based contrastive learning framework significantly improves 3D molecular representation learning by mitigating false pairs, achieving state-of-the-art results.