2 papers
cs.LG2026
InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search
Qinqin Zhou, Fuhai Chen, Jipeng Wu +3
Training-free neural architecture search promises efficient discovery of high-performance networks without costly training. However, existing zero-cost proxies rely on fragmented h…
cs.CV2024
Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency
Yuhong Chen, Ailin Song, Huifeng Yin +5
The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are ta…