phase space
PulseAugur coverage of phase space — every cluster mentioning phase space across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Nemotron architecture tackles Transformer vs. State-Space model efficiency tradeoff
Nemotron, a novel architecture, addresses the inherent trade-offs between Transformer and State-Space models. It aims to achieve the efficiency of State-Space models while retaining the performance capabilities of Trans…
-
Lightweight GenAI models offer efficient network traffic generation
Researchers have developed lightweight Generative Artificial Intelligence (GenAI) models for network traffic generation, addressing limitations of current methods in modeling complex temporal dynamics and high computati…
-
New framework evaluates adversarial robustness in remote sensing change detection
Researchers have developed a new framework to evaluate the adversarial robustness of semantic change detection (SCD) models used in remote sensing. This framework addresses the unique challenges of SCD, which involves a…
-
Second-Order Drifting Models accelerate generative AI training dynamics
Researchers have introduced Second-Order Drifting Models, an advancement in one-step generative models that evolve distributions during training. By incorporating artificial velocity variables into generated samples, th…
-
New framework uses AI for comprehensive cardiac CT analysis · 2 sources tracked
Researchers have developed a unified framework for cardiac CT segmentation and phenotyping, combining a human-in-the-loop annotation process with a self-supervised foundation model. This approach, pre-trained on 60,000 …
-
New 'Forking-Sequences' architecture boosts time series forecast accuracy and stability
A new research paper introduces "Forking-Sequences," a novel neural network architecture designed to improve the efficiency and reduce the volatility of multi-horizon time series forecasting. This approach processes the…