Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory proposes a framework for AI alignment that treats the representation of...
Clinical decision support systems are increasingly designed as committees of language-model agents that deliberate on shared workspaces.
CARE-Bench is a new benchmark designed to evaluate how well patient-facing medical LLMs perform triage—the process of determining the next appropriate action...
Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition explores whether the "temporal horizon"—the preference for short-term versus l...
ContinualSkillBench is a dynamic evaluation framework designed to determine if large language model (LLM) agents can autonomously evolve their capabilities b...
Oilbird is a training-free speculative decoding method designed to improve the speed of large language models by using semantic information to draft future t...
KnowHal is a benchmark designed to evaluate how Multimodal Large Language Models (MLLMs) handle hallucinations across four distinct dimensions: entity, attri...
Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies addresses the challenge of decision-making under model uncertainty.
Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation addresses the risk of attackers using multiple, isolated AI agent sessions to assem...
The paper Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions argues that the field of Natural Language Processing (NLP) mu...
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.
