Bac Le

CONGA: Continual Neural Gated Architecture for Long-History Sequential Recommendation

Existing sequential recommendation models rely on absolute positional encodings and fixed context windows, producing two structural failure modes: out-of-distribution degradation on histories longer than the training window, and hard context limits that discard long-range interactions. We present CONGA (COntinual Neura...

U-NetL2O: An explainable model for low-dose CT image reconstruction

Counterfactual Reasoning for Robust Visual Question Answering

A novel training framework that enhances counterfactual contrastive learning for VQA and introduces a three-stage curriculum for stable multi-objective optimization, an enhanced Batch-Contrastive loss for more discriminative feature learning and two novel regularizers.

Learning curvature-aware multimodal representations with bicomplex embeddings