Yuan Hua — accepted AI-conference papers

2026

Cannistraci-Hebb Training on Ultra-Sparse Spiking Neural Networks

Yuan Hua, Jilin Zhang, Yingtao Zhang, Leyi You, Baobo Xiong, Carlo Vittorio Cannistraci +1

ICLR 2026poster

Inspired by the brain's spike-based computation, spiking neural networks (SNNs) inherently possess temporal activation sparsity. However, when it comes to the sparse training of SNNs in the structural connection domain, existing methods fail to achieve ultra-sparse network structures without signifi…

Cited by 0 Source ↗Scholar ↗

2024

Improving Generalization of Alignment with Human Preferences through Group Invariant Learning

Rui Zheng, Wei Shen, Yuan Hua, Wenbin Lai, Shihan Dou, Yuhao Zhou +6

ICLR 2024spotlight

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants, there's a growing expectation for them to perform consistent…

Cited by 5 Source ↗PDF ↗Scholar ↗