- TabPFN is a novel foundation model designed for small- to medium-sized tabular datasets, with up to 10,000 samples and 500 features.
- It uses a transformer-based architecture and in-context learning (ICL) to outperform traditional gradient-boosted decision trees on these datasets.
Scientists are exploring the capabilities of the DeepSeek-R1 AI model, released by a Chinese firm. This open and cost-effective model performs comparably to industry leaders in solving mathematical and scientific problems. Researchers are leveraging its accessibility to create custom models for specific disciplines, although it still struggles with some tasks.
Large language models (LLMs) are traditionally used online, but open-weights versions and smaller models are changing that, enabling researchers to run powerful AI tools locally for privacy, reproducibility, and cost-effectiveness.
The article provides examples of researchers using local models for various tasks, including:
- Summarizing scientific data and publications
- Generating training data for other models
- Transcribing and summarizing patient interviews
- Designing novel proteins
