SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression

Documenti analoghi

• Spike-driven Large Language Model
  di: Xu, Han, et al.
  Pubblicazione: (2026)
• SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network
  di: Wang, Kexin, et al.
  Pubblicazione: (2024)
• High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost
  di: Hu, JiaKui, et al.
  Pubblicazione: (2024)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation
  di: Dong, Yiting, et al.
  Pubblicazione: (2025)
• Parallel Training in Spiking Neural Networks
  di: Huang, Yanbin, et al.
  Pubblicazione: (2026)