Sep 11, 2026
Characterizing Job Power Elasticity for Power-Flexible AI Training
Characterizing Job Power Elasticity for Power-Flexible AI Training Large language model (LLM) training is a major driver of electricity demand in modern data...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Sep 11, 2026
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN) The EXYGEN framework is designed to make large-scale knowledge g...
Sep 11, 2026
RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization
RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization Routing optimization is a...
Sep 10, 2026
Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System
Modern banking relies heavily on a small group of shared artificial intelligence vendors to handle critical tasks like fraud screening, credit decisioning, a...
Sep 10, 2026
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards This paper introduces a new method for training AI agents to perform complex...
Sep 10, 2026
JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition
JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition introduces a new benchmark designed to evaluate how well AI agents can perform tasks...
Sep 10, 2026
Kernel-Managed Shared Memory for System-Wide Personalization
AI systems are becoming increasingly useful as they learn to adapt to individual users.
Sep 10, 2026
Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection
This paper addresses a structural mismatch in how artificial intelligence models are trained to use external scientific tools.
Sep 10, 2026
ConvMem: Convolutional Memory for Long-Context Reasoning
ConvMem: Convolutional Memory for Long-Context Reasoning Large Language Models (LLMs) are powerful, but they often struggle to process extremely long documen...
Sep 10, 2026
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning This research addresses the challenge of solvin...
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.