Explore Franklin AI

AI Research Papers

Understand new AI research with readable explanations and links to the original papers.

Oct 14, 2026

AI Research Model Training Reasoning

P2T derives token rewards from an existing process reward model

A gradient estimator attributes a sequence-level reward to individual tokens without training another reward model.

Oct 13, 2026

AI Research Multimodal AI AI Evaluation

PRISM combines numerical features, ECG history and population representations, while its reported comparisons expose different input conditions.

Oct 13, 2026

AI Research Reasoning Model Training

A research framework diagnoses failed trajectories and gives targeted instruction during verifiable-reward training.

Oct 13, 2026

AI Research Constraint Programming

A research prototype learns constraints from accepted and rejected solutions, then generalizes them across problem sizes.

Oct 13, 2026

AI Research Causal Inference

A theoretical study asks what can be identified when several causal graphs remain compatible with the available information.

Oct 13, 2026

AI Research Robotics AI Evaluation

A benchmark separates task planning from robot control and tests failures, interruptions and coordination over longer missions.

Oct 13, 2026

AI Research Model Training Reasoning

Selective branches reuse a shared prefix so a student model can receive teacher feedback on more possible paths.

Oct 13, 2026

AI Research AI Agents AI Evaluation

Two agents share a workspace while session limits and context resets help test a workflow for extended engineering tasks.

Oct 13, 2026

AI Research Reasoning AI Evaluation

Step-wise Truncation Probing compares answers from prefixes of the same reasoning trajectory to characterize overthinking.

Oct 13, 2026

AI Research Model Training Large Language Models

Cross-teacher feedback and gradient controls aim to reduce interference when a model learns several domains at once.

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.