May 28, 2026
OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol
OpenURMA is a research project that provides the first open-source, clean-room implementation of the Unified Bus (UB) protocol, a 2025 specification designed...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
May 28, 2026
Calibrating Conservatism for Scalable Oversight
Calibrating Conservatism for Scalable Oversight addresses the challenge of maintaining human control over advanced AI systems that may be more capable than t...
May 28, 2026
Multi-Adapter Representation Interventions via Energy Calibration
Multi-Adapter Representation Interventions via Energy Calibration (MARI) is a research framework designed to improve how we align Large Language Models (LLMs...
May 28, 2026
SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks
SwarmHarness is a decentralized protocol designed to turn idle computing power—such as unused GPU cycles on personal workstations or edge servers—into a prod...
May 28, 2026
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning Language models often struggle to improve their reasoning capabilities without massive a...
May 28, 2026
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
This paper investigates whether AI search agents are truly performing research or simply using the web to confirm information they already "know" from their...
May 28, 2026
AlphaTransit: Learning to Design City-scale Transit Routes
AlphaTransit: Learning to Design City-scale Transit Routes Designing a city-wide bus network is a complex puzzle where the success of a single route depends...
May 28, 2026
CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
CaMBRAIN is a new deep learning model designed to analyze electroencephalography (EEG) signals in real-time.
May 28, 2026
Utility-Aware Multimodal Contrastive Learning for Product Image Generation
Utility-Aware Multimodal Contrastive Learning for Product Image Generation This paper addresses a critical gap in current generative AI: while models are exc...
May 27, 2026
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
What the paper is about Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences...
Good to know
How do I use these AI research explainers?
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Can I suggest a research paper?
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.