Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

More in Research

Research

The promise and peril of using visual AI to study cities MIT News - Artificial intelligence · 2h ago

Research

Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse cs.AI updates on arXiv.org · 2h ago

Research

Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity cs.AI updates on arXiv.org · 2h ago

Research

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents cs.AI updates on arXiv.org · 2h ago

Research

Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations cs.AI updates on arXiv.org · 2h ago

Research

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment cs.AI updates on arXiv.org · 2h ago