Marco Cuturi
PulseAugur coverage of Marco Cuturi — every cluster mentioning Marco Cuturi across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Apple researchers unveil faster optimal transport method
Apple Machine Learning Research has published a paper detailing a new semismooth Newton method for kernel-based optimal transport. This method aims to overcome the computational limitations of existing estimators, which…
-
Apple ML Research scales flow maps for faster language generation
Apple Machine Learning Research has published a paper detailing advancements in scaling Categorical Flow Maps (CFMs) for language modeling. The research team successfully trained a 1.7 billion parameter flow model on 2.…
-
Apple unveils DLR-Lock to protect LLM weights from unauthorized use
Apple Machine Learning Research has introduced DLR-Lock, a novel method to protect pretrained language model weights from unauthorized modifications. This technique involves replacing each multilayer perceptron (MLP) wi…
-
Apple ML Research proposes amortized MIPS using neural networks
Apple Machine Learning Research has published a paper detailing a new approach to Maximum Inner Product Search (MIPS) called amortized MIPS. This method utilizes neural networks, specifically SupportNet and KeyNet, to d…
-
Apple researchers advance diffusion language models with new decoding techniques
Apple's Machine Learning Research division has published several papers detailing advancements in diffusion language models (dLLMs). These models offer potential for faster inference compared to autoregressive models by…
-
Apple researchers propose cache sharing to reduce LLM serving costs
Apple Machine Learning Research has published a paper detailing a new method called Stochastic KV Routing to reduce the memory footprint of transformer language models. This technique focuses on optimizing the depth dim…