Jul 20, 2026
Harmonizing AI Safety Thresholds
Frontier AI companies currently use a fragmented set of safety thresholds to determine when a model is too dangerous to release or requires additional securi...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Jul 17, 2026
Pretraining Data Can Be Poisoned through Computational Propaganda
Pretraining Data Can Be Poisoned through Computational Propaganda This research investigates a significant security vulnerability in the development of large...
Jul 17, 2026
Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers
Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers Medical image classifiers often struggle w...
Jul 17, 2026
Can We Trust Item Response Theory for AI Evaluation?
Can We Trust Item Response Theory for AI Evaluation? This paper investigates whether Item Response Theory (IRT)—a statistical framework traditionally used fo...
Jul 17, 2026
InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring
InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring Modern intelligent vehicles rely on understanding the driver’s em...
Jul 17, 2026
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation Modern industrial processes rely on automated optimisat...
Jul 17, 2026
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
SearchOS-V1 addresses a critical bottleneck in AI-driven web research: the tendency for information-seeking agents to lose track of their progress, repeat fa...
Jul 17, 2026
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data Traffic agencies increasingly rely on large volumes of video data fro...
Jul 17, 2026
Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control Autonomous coding agents are inc...
Jul 17, 2026
Transcoders for Investigating Deception in Language Models
Transcoders for Investigating Deception in Language Models explores a new way to understand why language models sometimes act deceptively.
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.