3 papers
cs.CL2026
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
Jingyuan Wang, Yankai Chen, Zhonghang Li +1
Large language models (LLMs) have demonstrated remarkable progress in reasoning, often through supervised fine-tuning (SFT). However, SFT is resource-intensive, relying on large cu…
cs.AI2025
MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
Tianyu Fan, Jingyuan Wang, Xubin Ren +1
The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in…
cs.AI2025
Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction
Jiahao Ji, Wentao Zhang, Jingyuan Wang +1
Traffic prediction is essential for intelligent transportation systems and urban computing. It aims to establish a relationship between historical traffic data X and future traffic…