Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Instruction Modeling: Instruction Tuning With Loss Over Instructions
An accurate and rapidly calibrating speech neuroprosthesis
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
Neural Spline Fields for Burst Image Fusion and Layer Separation
Test-time Adaptation of Discriminative Models via Diffusion Generative Feedback
In-Context Pretraining (ICP): Language Modeling Beyond Document Boundaries
TTT-NN: Test-Time Training on Nearest Neighbors for Large Language Models
Don’t stop the training: continuously-updating self-supervised algorithms best account for auditory responses in the cortex
Reconsidering the Past: Optimizing Hidden States in Language Models
Mind the Gap: Assessing Temporal Generalization in Neural Language Models § Scaling
Mind the Gap: Assessing Temporal Generalization in Neural Language Models § Dynamic Evaluation
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Continuous Learning in a Hierarchical Multiscale Neural Network
Learning Simpler Language Models with the Differential State Framework
Recurrent Neural Network Based Language Model § Dynamic Evaluation
2023-12-31-gwern-mentalgymnasticsmeme-dynamicevaluationvsalternativeapproaches.jpg
2023-hardt-figure5-bitsperbytegpt2performanceimprovementwhentrainingon50nearestneighborexamples.jpg
2023-hardt-figure6-perplexitiesdecreasewhentrainingonincreasinglymoreneighborsusinggpt2onthepile.jpg
2023-hardt-figure9-trainingcostofdynamicevaluationonnearestneighborlookups.jpg
2022-clark-figure2-fwldynamicevaluationimprovesmostonrareorrepeatedtokens.jpg
2017-krause-figure2-dynamicevaluationrnnpredictionofwikipediaandspanishtextshowingtesttimeadaptation.png
2b42979ae6f5f70c53a29c1350667ad5d50118d4.pdf#page=18&=deepmind
https://benkrause.github.io/blog/human-level-text-prediction/
https://www.latent.space/p/fastai#%C2%A7replacing-fine-tuning-with-continued-pre-training
1b54d898ad24b02d0faeab34ab6e834adec475d7.html#%C2%A7replacing-fine-tuning-with-continued-pre-training
Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification
https%253A%252F%252Flab42.global%252Fcommunity-interview-jack-cole%252F.html
TTT-NN: Test-Time Training on Nearest Neighbors for Large Language Models
https%253A%252F%252Farxiv.org%252Fabs%252F2212.02475%2523google.html
Reconsidering the Past: Optimizing Hidden States in Language Models
Mind the Gap: Assessing Temporal Generalization in Neural Language Models § Scaling
https%253A%252F%252Farxiv.org%252Fabs%252F2102.01951%2523scaling%2526org%253Ddeepmind.html
Mind the Gap: Assessing Temporal Generalization in Neural Language Models § Dynamic Evaluation
https%253A%252F%252Farxiv.org%252Fpdf%252F2102.01951%2523page%253D7%2526org%253Ddeepmind.html
https%253A%252F%252Farxiv.org%252Fabs%252F1909.01792%2523deepmind.html
Wikipedia Bibliography:
