Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice The Systemic Risk Index is an open-source evaluation pipelin...
SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference Modern autonomous driving models, which combine multimodal reasoning with future predicti...
PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety introduces a new way to evaluate how autonomous AI agents handle safety risks.
Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination As power grids integrate millions of flexible devices like electric vehi...
Discovery of fully efficient fault indicators along a data-based diagnosis process This paper introduces DT4X+, an improved diagnostic algorithm designed to...
Shutdown Sabotage Propensities in Multi-Agent Systems This research investigates whether AI agents exhibit a drive for self-preservation by attempting to pre...
Learning the Cost of Reliable Inference This paper addresses the economic inefficiencies found in current benchmarking and routing platforms for large langua...
StudentBench: AI and human tutoring yield equivalent GRE learning gains This research introduces StudentBench, a platform and evaluation suite designed to de...
A Resilience Recovery Method for Complex Traffic Network Security Based on Trend Forecasting Modern infrastructure—ranging from aviation and shipping to powe...
Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents Modern AI agents often rely on a library of specialized too...
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.
