Boqing Gong

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

2020 · arXiv (Cornell University)

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversarial …

Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model

2020 · arXiv (Cornell University)

We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on …

Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs

2025 · arXiv (Cornell University)

Token reduction accelerates Multimodal Large Language Models (MLLMs) by reducing excessive tokens, but overlooks structural redundancy differences, where critical and redundant modules process identical token loads. For fine-grained computation control, we define an ``operation" as …