Papers nuevos de IA y aprendizaje automático
En los últimos 3 días aparecieron 5 papers nuevos de IA y aprendizaje automático. Pipette los leyó todos y estos son los 5 con más interés, avance real y afirmaciones prudentes. Cada uno muestra la oración de su resumen que dice el resultado principal, tal como la escribieron sus autores.
Lo mejor de los últimos 3 días
Automating inequality? Gender bias in AI-mediated labor markets
We find that LLMs generate gender-stereotypical CVs and exhibit gender bias in screening scores and wage recommendations.
Revista con revisión por paresUso en el mundo realisSPA-vesicle: AI-assisted structure determination of membrane proteins on vesicles
Here, we present an AI-enabled, vesicle geometry-guided 3D reconstruction strategy based on untilted data.
Revista con revisión por paresKnowledge-guided machine learning deciphers spatiotemporal dynamics in chemical reactor systems
A physics-informed neural network embeds coking and heat transfer knowledge via an output integration layer and region-weighted loss to predict reactor spatiotemporal fields; it matches conventional simulation results, improves peak wall temperature accuracy, and runs about five orders of magnitude faster than conventional simulations.
Revista con revisión por paresAfirmaciones fuertes, leer con cuidadoUso en el mundo realLeveraging sequence purification for accurate prediction of multiple conformational states with AlphaFold2
Here, we introduce AF-ClaSeq, a systematic framework that enriches and purifies state-specific evolutionary signals through iterative sequence classification and selection.
Revista con revisión por paresImproving molecular property prediction with score-based diffusion models
Across diverse feature extractors and graph neural networks, diffusion-based training improves over conventional maximum-likelihood objectives on small-molecule regression benchmarks and matches or exceeds strong baselines on multitask regression and classification datasets.
Revista con revisión por pares