Bibliography (29):

  1. ​ β€˜dynamic evaluation (NN)’ directory

  2. Dynamic Evaluation of Neural Sequence Models

  3. Dynamic Evaluation of Transformer Language Models

  4. Compressive Transformers for Long-Range Sequence Modeling

  5. T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

  6. 2024-rannentriki-figure1-dynamicevaluationbeatsstaticllmsonlanguagemodelingofconcatenatedprojectgutenbergbooks.png

  7. https://arxiv.org/pdf/2403.01518#page=9&org=deepmind

  8. 2024-rannentriki-figure5-dynamicevaluationstillhelpsevenwithfinetuning.png

  9. ​ Nenex: A Neural Personal Wiki Idea

  10. ​ dynamic-evaluation#scaling-laws

    [Transclude the forward-link's context]

  11. https://openai.com/index/gpt-4-research/

  12. The Forward-Forward Algorithm: Some Preliminary Investigations

  13. PES: Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

  14. Mind the Gap: Assessing Temporal Generalization in Neural Language Models Β§ Dynamic Evaluation

  15. Recurrent Neural Network Based Language Model Β§ Dynamic Evaluation

  16. On the generalization of language models from in-context learning and finetuning: a controlled study

  17. Just read twice: closing the recall gap for recurrent language models

  18. Current Limitations of Language Models: What You Need is Retrieval

  19. Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

  20. Where does In-context Learning Happen in Large Language Models?

  21. Simple and Scalable Strategies to Continually Pre-train Large Language Models