Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs Neurosymbolic systems, such as DeepProbLog, combine the perceptual power of ne...
SoftSkill: Behavioral Compression for Contextual Adaptation This paper introduces SoftSkill, a method for improving how AI agents adapt to specific tasks.
Process-Verified Reinforcement Learning for Theorem Proving via Lean This research introduces a new way to train AI models for mathematical theorem proving b...
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe Training Large Language Models (LLMs) at 4-bit precision...
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling introduces a new way to test how well artificial intelligence can mo...
Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining explores whether we can automatically create "skill libraries"—col...
Context-Aware Hierarchical Bayesian Modeling of IVF Laboratory Environmental Conditions This research addresses a significant gap in fertility treatment: whi...
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research Open-ended deep research involves using AI to gather information thro...
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact This research investigates whether the psychological profiles ass...
Multi-Agent Transactive Memory (MATM) is a framework designed to help decentralized populations of AI agents share knowledge and learn from one another.
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.
