1d
Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding
Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...
AZoLifeSciences on MSN
Machine learning enhances manufacturing of complex protein drugs
Industrial yeasts are a powerhouse of protein production, used to manufacture vaccines, biopharmaceuticals, and other useful compounds.
Industrial yeasts are a powerhouse of protein production, used to manufacture vaccines, biopharmaceuticals, and other useful ...
Abstract: Reliable and timely data collection poses a significant challenge for underwater wireless sensor networks (UWSNs), primarily due to the extremely low data rate of underwater communication ...
This project implements a Variational Autoencoder (VAE) for image generation. Unlike standard autoencoders, VAE learns a probabilistic latent space by encoding images to a distribution and sampling ...
This repository explores finetuning DINOv3 (Siméoni et al., 2025) or DINOv2 (Oquab et al., 2024) encoder weights using Low-Rank Adaptation (Hu et al., 2021) (LoRA) and a simple 1x1 convolution decoder ...
ABSTRACT: In this paper, a novel multilingual OCR (Optical Character Recognition) method for scanned papers is provided. Current open-source solutions, like Tesseract, offer extremely high accuracy ...
Successful test results of a new machine learning (ML) technique developed at Georgia Tech could help communities prepare for extreme weather and coastal flooding. The approach could also be applied ...
Ph.D. student Phillip Si and Assistant Professor Peng Chen developed Latent-EnSF, a technique that improves how ML models assimilate data to make predictions.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results