Retrieval-augmented generation (RAG) allows AI systems to provide additional information and context to a large language model (LLM) when generating a response to a user query. However, traditional RAG-based methods can struggle to retrieve information that requires high-level knowledge of…
Overview of PocketGen Unlike previous methods focusing on protein sequence or structure generation, we aim to co-design both residue types (sequences) and three-dimensional (3D) structures of the protein pocket that can fit and bind with the target ligand molecules. Inspired…
Researchers at ETH Zurich are utilising artificial intelligence to analyse the behaviour of laboratory mice more efficiently and reduce the number of animals in experiments. There is one specific task that stress researchers who conduct animal experiments need to be…
Maroun Khoury emphasizes the need to draw on personal interactions and experiences when writing letters of recommendation.Credit: Damircudic/Getty As a principal investigator in a research laboratory that specializes in advanced therapies, I am routinely asked to write recommendation letters for…
Promptim is an experimental prompt optimization library to help you systematically improve your AI systems. Promptim automates the process of improving prompts on specific tasks. You provide initial prompt, a dataset, and custom evaluators (and optional human feedback), and promptim runs an optimization loop…
Datasets All studies were performed under the regulation of the SickKids Research Ethics Board (Study: #1000080135). Upon completion of required data access agreements, datasets were downloaded from the The European Genome-phenome Archive (EGA) for EGAS0000100476384, and from the NIMH Repository…
ChatGPT and the Future of AI: The Deep Language Revolution Terrence J. Sejnowski The MIT Press (2024) Some of the surprise winners of this year’s Nobel prizes were the developers of AlphaFold, an artificial intelligence (AI) model that can accurately…
Imagine using artificial intelligence to compare two seemingly unrelated creations — biological tissue and Beethoven’s “Symphony No. 9.” At first glance, a living system and a musical masterpiece might appear to have no connection. However, a novel AI method developed…
In the race to develop robust perception systems for robots, one persistent challenge has been operating in bad weather and harsh conditions. For example, traditional, light-based vision sensors such as cameras or LiDAR (Light Detection And Ranging) fail in heavy…
What it means to “build” applications is changing. When building AI applications, you are not just writing code – you’re also writing prompts. Tooling has evolved over the years to make software engineering more accessible – like code editors, code…
The process of computational design in mechanical engineering often begins with a problem or a goal, followed by an assessment of literature, resources, and systems available to address the issue. The Design Computation and Digital Engineering (DeCoDE) Lab at MIT…
We introduce Anthology, a method for conditioning LLMs to representative, consistent, and diverse virtual personas by generating and utilizing naturalistic backstories with rich details of individual values and experience. What does it mean for large language models (LLMs) to be…