A zero-shot learning framework for maize cob phenotyping

A new study presents a zero-shot learning (ZSL) framework for maize cob phenotyping, enabling the extraction of geometric ...
EurekAlert!

A federated anti-forgetting representation method based on hybrid model architecture and gradient truncation

Anti-forgetting representation learning method reduces the weight aggregation interference on model memory and augments the ...
Tech Xplore on MSN

Reinforcement learning accelerates model-free training of optical AI systems

Optical computing has emerged as a powerful approach for high-speed and energy-efficient information processing. Diffractive ...
VentureBeat

This new framework lets LLM agents learn from experience, no fine-tuning required

A new learning paradigm developed by University College London (UCL) and Huawei Noah’s Ark Lab enables large language model (LLM) agents to dynamically adapt to their environment without fine-tuning ...
EurekAlert!

A new AI-based method advances solid oxide cell modeling by improving physical consistency and computational efficiency

Researchers from the University of Chinese Academy of Sciences and collaborating institutions have developed a novel ...
VentureBeat

Google’s ‘Nested Learning’ paradigm could solve AI's memory and continual learning problem

Researchers at Google have developed a new AI paradigm aimed at solving one of the biggest limitations in today’s large language models: their inability to learn or update their knowledge after ...
eLife

A differentiable model for optimizing the genetic drivers of synaptogenesis

This study presents SynaptoGen, a differentiable extension of connectome models that links gene expression, protein-protein interaction probabilities, synaptic multiplicity, and synaptic weights, and ...
techtimes

Apple MLX: New AI Framework, Model Released as Open Source, Meant to Run on M-Series, Silicon Chips

In a surprising turn of events, another Big Tech company released its first take on everything AI, with Apple's MLX now available as open source, centering on its new framework and model. There were ...
Security Boulevard

NDSS 2025 – DLBox: New Model Training Framework For Protecting Training Data

Jaewon Hur (Seoul National University), Juheon Yi (Nokia Bell Labs, Cambridge, UK), Cheolwoo Myung (Seoul National University), Sangyun Kim (Seoul National University), Youngki Lee (Seoul National ...
AZoCleantech on MSN

New framework for predicting TAIs in hydrogen combustion

Researchers have developed a hybrid CFD-neural network model for predicting TAIs in hydrogen-fueled turbines, improving ...