2 papers
cs.AI2026
Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering
Fengxian Chen, Zhilong Tao, Jiaxuan Li +2
Retrieval-augmented generation (RAG) promises grounded question answering, yet domain settings with multiple heterogeneous knowledge bases (KBs) remain challenging. In Chinese Tibe…
cs.LG2025
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…