Showing 1–20 of 25 results
/ Date/ Name
Mar 26, 2026Voxtral TTSFeb 11, 2026Voxtral RealtimeJan 13, 2026Ministral 3May 20, 2025Scale-invariant AttentionMar 3, 2025Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred DatapointsFeb 24, 2025Function-Space Learning RatesJan 29, 2025Automated Interpretability Metrics Do Not Distinguish Trained and Random TransformersSep 6, 2023Signatures of Bayesian inference emerge from energy efficient synapsesAug 24, 2023Bayesian Low-rank Adaptation for Large Language ModelsMay 18, 2023Massively Parallel Reweighted Wake-SleepFeb 8, 2023Decision trees compensate for model misspecificationAug 23, 2022What deep reinforcement learning tells us about human motor learning and vice-versaAug 30, 2021A theory of representation learning gives a deep generalisation of kernel methodsJul 21, 2021A variational approximate posterior for the deep Wishart processFeb 27, 2021Variational Laplace for Bayesian neural networksFeb 12, 2021Bayesian Neural Network Priors RevisitedNov 20, 2020Variational Laplace for Bayesian neural networksSep 24, 2020Legally grounded fairness objectivesAug 13, 2020Semi-supervised learning objectives as log-likelihoods in a generative model of data curationAug 13, 2020A statistical theory of cold posteriors in deep neural networks