Sparsely-gated Mixture of Expert (MoE), an emerging deep model architect...
Recently, bi-level optimization (BLO) has taken center stage in some ver...
Despite the record-breaking performance in Text-to-Image (T2I) generatio...
Lifelong learning (LL) aims to improve a predictive model as the data so...
Invariant risk minimization (IRM) has received increasing attention as a...
We revisit and advance visual prompting (VP), an input prompting techniq...
The deployment constraints in practical applications necessitate the pru...
Current deep neural networks (DNNs) are vulnerable to adversarial attack...
Trojan attacks threaten deep neural networks (DNNs) by poisoning them to...
Adversarial training (AT) has become a widely recognized defense mechani...