Research has changed.

• Physics Does a physics-informed loss help a neural network extrapolate a damped pendulum beyond its training window?
• CS + ML Can a small transformer learn modular arithmetic faster with a curriculum on operand size?
• Bio Do protein language model embeddings predict the effect of point mutations better than a substitution matrix?
• Chemistry Does a small graph neural network beat fingerprints with a random forest at predicting molecule solubility?

Browse the library or see how papers are reviewed