3 papers
cs.NE2026
Large Language Model-Guided Evolutionary Discovery of Native Neural Architectures for Spiking Sequence Modeling
Ruoyu Zhao, Jiaqi Wu, Chenyu Zhu +1
Spiking neural networks (SNNs) offer low-energy sequence modeling through sparse, event-driven computation. However, interactions among spike encoding, neuronal dynamics, and infor…
cs.LG2026
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Chenyu Zhu, Ruoyu Zhao, Zhichao Lu
Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size and compute…
cs.AI2026
Mamba with Hierarchical Memory: Solving Representation Bottleneck in Long Sequence Modeling
Qinwen Wang, Jieping Luo, Aoxiang Qin +5
Recurrent linear attention models (RLAs) such as Mamba offer efficient linear-time sequence modeling as an alternative to Transformers, yet their fixed-capacity recurrent states li…