Cites: TransformerFAM: Feedback attention is working memory

7 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• Scaling Laws for Neural Language Models
  arxiv:2001.08361 · evidence: title
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
  arxiv:2006.16236 · evidence: title
• Memorizing Transformers
  arxiv:2203.08913 · evidence: title
• TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
  arxiv:2304.01433 · evidence: title
• Learning to Compress Prompts with Gist Tokens
  arxiv:2304.08467 · evidence: title
• Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
  arxiv:2404.07143 · evidence: title
• Overcoming catastrophic forgetting in neural networks
  doi:10.1073/pnas.1611835114 · evidence: title