Microsoft CEO Satya Nadella criticized AI labs like Anthropic for what he called hypocrisy in model training, arguing that they benefit from using public data while restricting distillation practices.…
LDPKiT, a privacy-preserving AI framework using local differential privacy, achieves near-identical accuracy at a stringent privacy level of ε=1.25 compared to ε=2.0 on the SVHN dataset, with less tha…
A new deep learning model, Inspectra CXR version 5, developed by researchers at Siriraj Hospital in Bangkok using 874,858 chest radiographs, achieved a mean AUROC of 0.994 on a test set and 0.970 on a…
A new planning framework called GATS (Graph-Augmented Tree Search) eliminates the need for LLM calls during inference, achieving a 100% success rate on synthetic planning tasks and outperforming LATS …
Researchers evaluating image disguising methods DisguisedNets and NeuraCrypt across four medical datasets found that while these techniques preserve utility for simple classification tasks, they falte…
SYNRARE, a synthetic data tool built on the Synthea framework, enables machine learning developers to test and benchmark rare disease diagnosis algorithms without compromising patient privacy. By gene…
A new study evaluating variational quantum circuits (VQCs) in diffusion models on MNIST and CIFAR-10 found that quantum cores matched classical Fréchet Inception Distance (FID) scores despite using 4.…
CoCoT, a contrastive-pretrained EEG model with multiscale temporal convolution layers and Transformer encoders, outperforms state-of-the-art reconstruction-pretrained models on benchmark tasks, challe…
A new study evaluating learning curve convergence rates across six datasets totaling 102.7 hours of inertial measurements suggests that deep learning in inertial sensor-based tasks may require far les…
Researchers have introduced LieBN, a novel Riemannian batch normalization framework that leverages Lie group properties to overcome limitations of existing methods, achieving applicability across nine…
AI researchers introduced Reward Transport, a novel approach that uses optimal transport coupling during training to steer molecular AI model outputs by adjusting a noise-space coordinate at inference…
Pattern-aware graph neural networks that encode missingness patterns improved balanced accuracy by 17% and F1-macro scores by 22% across seven UCI datasets, according to a study by researchers explori…
A new signed symmetric quantization method eliminates clipping errors in low-bit AI models without the runtime penalty of asymmetric quantization, achieving up to 2.45 times faster inference on AMD EP…
A new AI model called iLENS, developed by researchers, combines large language models with expert systems to predict Alzheimer's disease conversion faster and with interpretable, biologically grounded…
Prompt-Driven Exploration (PDE) offers a fresh take on reinforcement learning by using language prompts from large language models (LLMs) and vision-language-action models (VLA) to guide AI exploratio…
Researchers have cracked the code of knowledge distillation in large language models, revealing that its effectiveness stems from creating sparse interaction networks. They propose a new loss function…
Researchers introduced DaDaDa, the first dataset for data product pricing, containing metadata for 16,147 data products from 9 major data marketplaces including AWS Marketplace, Databricks, and Datara…
A new GPU inference method for large language models (LLMs) with moderate unstructured sparsity (around 50%) outperforms dense matrix multiplication on modern GPUs with high-bandwidth memory, achievin…
Researchers introduce KRONOS, a latent autoregressive diffusion framework that generates 3D molecules in the latent space of a pre-trained autoencoder, jointly modeling molecular graph topology and ge…
A new study from arXiv provides exact solutions for how linear representations emerge in neural networks during training, a process called abstraction. The researchers found that data and target geome…