5 papers
On the Adversarial Transferability of Generalized "Skip Connections"
Yisen Wang, Yichuan Mo, Dongxian Wu +3
Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification pe…
Language Ranker: A Lightweight Ranking framework for LLM Decoding
Chenheng Zhang, Tianqi Du, Jizhe Zhang +4
Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms th…
Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
Yisen Wang, Yichuan Mo, Hongjun Wang +2
Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. W…
A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
Qingyan Meng, Mingqing Xiao, Zhengyu Ma +3
Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging bec…
Incorporating Arbitrary Matrix Group Equivariance into KANs
Lexiang Hu, Yisen Wang, Zhouchen Lin
Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains thanks to spline activation functions, becoming an alternative to Multi-Layer Perceptrons (MLPs). Ho…