A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Fanfei Li, Jana Zeller, Manuel Prada-Corral, et al.
Introduces LittleLearner, a 5B-parameter LLM trained on an 88B-token curriculum of U.S. elementary school material, providing a controlled sandbox to study knowledge acquisition and capability boundaries.
Unknown
This paper introduces a Graph RAG approach for automated short answer grading that provides fine-grained, explainable feedback by returning explicitly linked facts, contrasting with coarse Vector-RAG passages.
Yunfan Li, Bingbing Xu, Xueyun Tian, et al.
Proposes Task-Decoupled Planning (TDP), a training-free framework that decomposes long-horizon tasks into a DAG of sub-goals, isolating reasoning to reduce error propagation and token consumption.
Unknown
LearnLM enhances Gemini for pedagogical instruction by co-training SFT and RLHF, outperforming leading LLMs in tutoring scenarios.