In recent years, the AI community has witnessed a significant surge in developing large language models (LLMs) such as ChatGPT, Bard, and Claude. These models have demonstrated exceptional capabilities, from enhancing dialogue systems to improving logical reasoning...

In the rapidly evolving field of protein structure prediction, researchers have made significant strides in understanding and modeling the complex three-dimensional shapes that proteins fold into. These shapes are crucial for understanding proteins’ functions in...

In the rapidly evolving field of artificial intelligence, the development and application of large language models (LLMs) stand at the forefront of innovation, offering unparalleled data processing and analysis capabilities. These sophisticated models, characterized...

Researchers from Microsoft attempt to solve the challenge faced in predicting molecular properties and simulating molecular dynamics by presenting a method, ViSNet, that results in more accurate predictions. Predicting molecular properties is crucial for understanding...

Engineering effective prompts for LLMs is crucial yet challenging due to their sensitivity to prompts and the ambiguity of task instructions. Recent studies propose using meta-prompts that learn from past trials to suggest improved prompts automatically. However,...

The recent success of large language models relies heavily on extensive text datasets for pre-training. However, indiscriminate use of all available data may not be optimal due to varying quality. Data selection methods are crucial for optimizing training datasets and...