Haste
PulseAugur coverage of Haste — every cluster mentioning Haste across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New methods enhance generative recommendation systems with improved training and performance · 4 sources tracked
Researchers have developed new methods to improve generative recommendation systems, which represent items as semantic IDs and generate them autoregressively. One approach, HASTE, incorporates hierarchical and attribute…
-
New HASTE framework evolves AI agent defenses against emerging cyber threats
Researchers have developed HASTE, a novel multi-agent framework designed to automatically evolve agent harnesses against emerging cyber threats. This system addresses the challenge of adapting safety constraints when fa…
-
HASTE platform enables rapid post-disaster building damage assessment
Researchers have developed HASTE, a no-code web platform designed for rapid post-disaster building damage assessment. HASTE enables non-machine learning experts to create damage maps from satellite imagery within hours …
-
HASTE system improves ML engineering agent efficiency with hierarchical skill transfer
Researchers have developed HASTE, a hierarchical multi-agent system designed to improve the efficiency of ML engineering agents. By organizing knowledge into global, domain, and competition-specific tiers, HASTE allows …
-
HASTE framework enables training-free compression of CNNs
Researchers have developed HASTE, a novel framework designed to compress large pre-trained convolutional neural networks (CNNs) without requiring additional training or data access. This plug-and-play module utilizes lo…
-
HASTE method optimizes extreme multi-label classification models
Researchers have developed HASTE, a novel method for optimizing extreme multi-label classification (XMC) models. HASTE addresses the bottleneck in XMC by introducing group-shared fixed fan-in sparsity, which allows sema…