Spade
PulseAugur coverage of Spade — every cluster mentioning Spade across labs, papers, and developer communities, ranked by signal.
- 2026-05-22 research_milestone Publication of a new framework for offline black-box optimization. source
2 day(s) with sentiment data
-
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…
-
New SPADE framework improves scientific ML with adaptive structure priors
Researchers have developed SPADE, a novel framework for scientific machine learning that adaptively incorporates physical structure priors. This method treats the problem as shrinkage of the structure-violating block of…
-
SPADE transformer advances high-granularity calorimeter simulation
Researchers have developed SPADE, a novel autoregressive transformer model designed for simulating high-granularity calorimeter data in particle physics. Unlike previous methods that embed multiple features jointly, SPA…
-
SPADE framework enhances robot path planning with diffusion models
Researchers have developed SPADE, a new framework for robot path planning that uses diffusion models to improve generalization and robustness. This approach integrates diffusion-based augmentation into existing behavior…
-
New SPADE framework enhances offline black-box optimization with diffusion models
Researchers have introduced SPADE, a new framework for offline black-box optimization that uses conditional generative modeling with diffusion models. This approach enhances forward surrogate modeling by incorporating a…
-
SPADE AI model accelerates drug discovery, outperforming competitors
Researchers have developed SPADE, a novel algorithm designed to accelerate drug discovery by efficiently identifying high-quality drug candidates. SPADE requires an average of only 40 tests to find 10 suitable ligands, …