Grammatical error correction (GEC) is a key task in natural language processing (NLP), widely applied in education, news, and publishing. Traditional methods mainly rely on sequence-to-sequence (Seq2Seq) and sequence-to-edit (Seq2Edit) models, while large language models (LLMs) have recently shown strong performance in this area.

 

 

Researchers have developed a novel generative AI model, called Collaborative Competitive Agents (CCA), that significantly improves the ability to handle complex image editing tasks. This new approach utilizes multiple Large Language Model (LLM)-based agents that work both collaboratively and competitively, resulting in a more robust and accurate editing process compared to existing methods. This breakthrough allows for a more transparent and iterative approach to image manipulation, enabling a level of precision previously unattainable. The findings were published on 15 November 2025 in Frontiers of Computer Science, co-published by Higher Education Press and Springer Nature.

Lockdowns isolated teenagers from friends, disrupted their routines, and kept them at home with daily reports of bad news. So most people assume teenagers felt worse during COVID-19 lockdowns, but a Tokyo study shows the opposite. Scientists at Nagoya University and their collaborators tracked Tokyo teens through the pandemic and found they experienced depression less often during lockdowns than during normal school life. Published in PLOS Medicine, the study found two groups that experienced depression differently. Both felt better during lockdown, but brain scans showed biological differences between them. 

 

Researchers from Tianjin University have introduced the Emergency Medical Procedures 3D Dataset (EMP3D), a pioneering resource that captures the intricate movements of medical professionals during life-saving interventions with unprecedented precision. Published on 15 November 2025 in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature, this dataset leverages synchronized multi-camera systems, advanced AI algorithms, and rigorous human validation to create the first 3D digital blueprint of emergency medical workflows. The innovation holds the potential to fundamentally transform emergency medical training and enhance robotic support in healthcare settings.

A record-setting $55 million commitment from a Binghamton University, State University of New York alumnus and New York state will establish the Center for AI Responsibility and Research, the first-ever independent AI research center at a public university in the United States. Research conducted via the new center will build upon Binghamton research that advances AI for the public good. 

The microbiome of infants is shaped by social relationships from an early age and not only by family sources. This was confirmed by a study conducted by researchers of the Department of Cellular, Computational and Integrative Biology of the University of Trento (Cibio) and published in Nature. In particular, the Computational Metagenomics research group investigated microbiome transmission in contexts and age groups never before explored. To do this, they worked in collaboration with the Childhood Services and Education Office of the Municipality of Trento and three daycare centres in the city. 

What if the earliest signs of skin cancer could be identified sooner — before a dermatology appointment?

Researchers at the University of Missouri are exploring how artificial intelligence could help detect melanoma — the most dangerous form of skin cancer — by evaluating images of suspicious skin abnormalities.