Researchers present a training algorithm that reduces optimization variance in small neural networks used for real-time neural shading, improving convergence reliability. The method uses an ensemble o…
Jialiang Wang, a researcher in Artificial Intelligence and Machine Learning, Computer Vision, and Generative AI, has published his work on Google Scholar, with his profile accessible at https://schola…
A new diagnostic framework called Spatial-IQ, introduced by researchers using NVIDIA Isaac Sim, decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks to evaluat…
Researchers at an unnamed institution have developed a multimodal AI pipeline to analyze emergent non-verbal communication in the competitive video game Delta Force, marking a shift from prior studies…
Researchers introduced The AI Telco Engineer (AITE), a large language model-driven evolutionary search framework that autonomously designs wireless communications algorithms, outperforming best-known …
CTRL-G (Controllable Generative Graphics for Games) brings together experts from artificial intelligence, graphics/VFX, and ethics to explore how generative systems can be made controllable, responsiv…
Haithem Turki, a Ph.D. graduate in Computer Science from Carnegie Mellon University, focuses his research on reconstructing, simulating, and generating dynamic 3D worlds, spanning scalable neural scen…
Igor Markov, a researcher in algorithms, AI, circuits, and quantum computing, has updated his Google Scholar profile. His work spans multiple technical domains including machine learning and VLSI desi…
NVIDIA researchers introduced ARDY, an autoregressive diffusion model for interactive human motion generation that supports online text prompting and flexible long-horizon kinematic constraints with r…
Researchers introduced AI-based pre-decoders for triangular color codes, using a novel neural-network architecture to improve logical failure rates and runtimes. At code distance d=31 and physical err…
Researchers introduced SuperCollider, a scalable data race detector for CUDA programs that tracks only thread-level state and introduces no memory-footprint overhead. The tool found over 90 data races…
NVIDIA researchers introduced IR-FRestormer, a novel method combining iterative refinement with Fourier-based restormer for accelerated MRI reconstruction, achieving state-of-the-art results. The work…
Researchers from Duke University and NVIDIA introduced FedBPT, a method for efficient federated black-box prompt tuning of large language models, presented at ICML 2024. The approach enables collabora…
NVIDIA researchers and collaborators from Duke University introduced a communication-efficient vertical federated learning method that handles limited overlapping samples, presented at CVPR 2023. The …
NVIDIA researchers introduced VILA-M3, a vision-language model enhanced with medical expert knowledge, at CVPR 2025. The model aims to improve AI understanding of medical images by incorporating domai…
NVIDIA researchers and collaborators published a review in the Annual Review of Biomedical Engineering detailing the transition of federated learning in healthcare from research to real-world deployme…
NVIDIA researchers published a study in IEEE Transactions of Medical Imaging investigating whether gradient inversion attacks compromise federated learning safety, finding that such attacks can recons…
Researchers at NVIDIA and Harvard Medical School used federated learning to predict clinical outcomes in COVID-19 patients, enabling collaborative model training across institutions without sharing se…
NVIDIA researchers published a study in Nature Digital Medicine on September 14, 2020, exploring the use of federated learning to advance digital health while preserving patient data privacy. The appr…
Shuchen Xue, a researcher specializing in artificial intelligence and machine learning with a focus on generative AI, has published work accessible via Google Scholar. Her research contributes to adva…