The SDE benchmark shows LLMs lag on scientific discovery tasks relative to general science tests, with diminishing scaling returns and shared weaknesses across models.
write newline
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
A monolithic FDSOI-FeFET platform natively supports ACAM and GRNG to enable efficient Bayesian decision tree inference with over 40% higher MNIST accuracy under noise and orders-of-magnitude gains in speed and energy.
THz-STM resolves femtosecond band bending dynamics at atomic scales on photoexcited GaAs(110) by tracking transient photocurrents near defects.
Introduces distributional random forests for joint posterior inference and an SMC update for the prior in ABC, claiming accurate posteriors across deterministic and stochastic models.
Autonomous coding agents translate plain-language clinical descriptions into working AI pipelines, producing competitive models across five tasks and reducing pneumothorax shortcut reliance on chest drains from 60% to 31% and 50% to 18% on two datasets.
citing papers explorer
-
Approximate Bayesian Computation sequential Monte Carlo via random forests
Introduces distributional random forests for joint posterior inference and an SMC update for the prior in ABC, claiming accurate posteriors across deterministic and stochastic models.