Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
Paper
•
2311.02772
•
Published
•
8
Transformers
-
-
Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities
Paper • 2311.05698 • Published • 14 -
Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems
Paper • 2311.05884 • Published • 11 -
Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers
Paper • 2311.10642 • Published • 26