AAAI

BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning

BOFA: 基于CLIP的类增量学习中的桥接层正交低秩融合

Lan Li, Tao Hu, Da-Wei Zhou, Jia-Qi Yang, Han-Jia Ye, De-Chuan Zhan

AI总结 提出BOFA框架，通过将适应限制在CLIP的跨模态桥接层并使用正交低秩融合防止遗忘，无需额外参数或数据回放，实现高效类增量学习。

Comments Accepted by AAAI 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(27): 22967-22975, 2026

I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks

I2E: 实时图像到事件转换用于高性能脉冲神经网络

Ruichen Ma, Liwei Meng, Guanchao Qiao, Ning Ning, Yang Liu, Shaogang Hu

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳先进研究院） 纠错

AI总结 本文提出I2E框架，通过高效卷积模拟微眼动实现图像到事件流的快速转换，提升SNN训练效率，并在大规模基准上验证有效性，达到92.5%的准确率。

Comments AAAI-26 Oral

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 2026, Vol. 40, No. 3, pp. 1982-1990