GRASP: GRouped Activation Shared Parameterization for Parameter-Efficient Fine-Tuning and Robust Inference of Transformers

Documenti analoghi

• SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation
  di: Bal, Malyaban, et al.
  Pubblicazione: (2023)
• P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
  di: Bal, Malyaban, et al.
  Pubblicazione: (2024)
• RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
  di: Mia, Md Zesun Ahmed, et al.
  Pubblicazione: (2026)
• Delving Deeper Into Astromorphic Transformers
  di: Mia, Md Zesun Ahmed, et al.
  Pubblicazione: (2023)
• Scaling SNNs Trained Using Equilibrium Propagation to Convolutional Architectures
  di: Lin, Jiaqi, et al.
  Pubblicazione: (2024)