Explore Franklin AI

AI Research Papers

Understand new AI research with readable explanations and links to the original papers.

Aug 18, 2026

AI Evaluation Large Language Models Reasoning

GRIP: Grounded Reasoning via Information-Restricted Premises

GRIP (Grounded Reasoning via Information-Restricted Premises) is a method designed to improve how language models use retrieved evidence in retrieval-augment...

Aug 18, 2026

Large Language Models Reasoning AI Evaluation

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

LAVA (Logic-Aware Validation and Augmentation) is a modular framework designed to automate the auditing of complex financial documents, such as tax forms, ba...

Aug 18, 2026

Computer Vision Reasoning Large Language Models

Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment

Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment addresses the scarcity of recognition resources for the wor...

Aug 18, 2026

AI Evaluation Large Language Models AI Safety

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

This paper investigates whether language model compliance detectors actually evaluate specific regulatory rules or if they simply react to the general conten...

Aug 18, 2026

AI Evaluation AI Systems AI Agents

Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

Chronocooked is a reinforcement learning (RL) benchmark suite designed to evaluate how artificial agents develop an internal sense of time.

Aug 18, 2026

Large Language Models Healthcare AI AI Evaluation

Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

Policy Iteration with Human Feedback (PIHF) is a framework designed to improve the diagnostic accuracy of language models in rare-disease cases by using a hu...

Aug 18, 2026

AI Evaluation AI Systems AI Agents

Quipu: A Governed Bitemporal Knowledge Graph Store

Quipu is an embeddable knowledge graph store designed to manage data written by software agents.

Aug 18, 2026

AI Evaluation Large Language Models Robotics

FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy

FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy introduces a framework for Vision-Language-Action (VLA) models t...

Aug 18, 2026

AI Agents Large Language Models Reasoning

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding investigates how teams of AI coding agents interact while completing programming task...

Aug 18, 2026

AI Evaluation Large Language Models AI Agents

Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

Reconstruction is a blind benchmark designed to test whether large language models (LLMs) can accurately recover the core research idea of a published paper...

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.