Summary of Language Model Developers Should Report Train-test Overlap, by Andy K Zhang et al.
Language model developers should report train-test overlapby Andy K Zhang, Kevin Klyman, Yifan Mai, Yoav…
Language model developers should report train-test overlapby Andy K Zhang, Kevin Klyman, Yifan Mai, Yoav…
Identifying Money Laundering Subgraphs on the Blockchainby Kiwhan Song, Mohamed Ali Dhraief, Muhua Xu, Locke…
Heating Up Quasi-Monte Carlo Graph Random Features: A Diffusion Kernel Perspectiveby Brooke Feinberg, Aiwen LiFirst…
Bilinear MLPs enable weight-based mechanistic interpretabilityby Michael T. Pearce, Thomas Dooms, Alice Rigg, Jose M.…
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Biasby Aida Mohammadshahi, Yani…
A phase transition in sampling from Restricted Boltzmann Machinesby Youngwoo Kwon, Qian Qin, Guanyang Wang,…
MYCROFT: Towards Effective and Efficient External Data Augmentationby Zain Sarwar, Van Tran, Arjun Nitin Bhagoji,…
Generalizable autoregressive modeling of time series through functional narrativesby Ran Liu, Wenrui Ma, Ellen Zippi,…
Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamicsby Josiah C. Kratz, Jacob AdamczykFirst submitted…
JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensemblesby Dom NasrabadiFirst submitted to…