Jun 5, 2026
Benchmark Everything Everywhere All at Once
Benchmark Everything Everywhere All at Once introduces "Benchmark Agent," a fully autonomous system designed to solve the growing crisis in AI evaluation.
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Jun 5, 2026
ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity
ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity ProSarc is an audio-only artificial intelligence framework designed to...
Jun 5, 2026
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
Goedel-Architect is an agentic framework designed to streamline formal theorem proving in Lean 4.
Jun 5, 2026
Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment
Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment This research addresses a...
Jun 5, 2026
Unsupervised Skill Discovery for Agentic Data Analysis
Unsupervised Skill Discovery for Agentic Data Analysis Data-analytic agents—AI systems designed to process data, write code, and generate reports—often strug...
Jun 5, 2026
Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation
Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation Brain-to-image decoding—the process of reconstructing or identifying images based on a perso...
Jun 5, 2026
AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks
AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networks Accurate prediction of where a ship will be in the future is vital for maritime...
Jun 5, 2026
LLM Self-Recognition: Steering and Retrieving Activation Signatures
LLM Self-Recognition: Steering and Retrieving Activation Signatures explores how large language models (LLMs) naturally encode their own identity into the te...
Jun 5, 2026
Multi-ResNets for Subspace Preconditioning in Constrained Optimization
Multi-ResNets for Subspace Preconditioning in Constrained Optimization introduces MResOpt, a new neural network architecture designed to solve complex constr...
Jun 5, 2026
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads explores the growing need for LLM agents to maintain persistent, lo...
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.