2 papers
cs.CL2026
Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
Houyi Li, Ka Man Lo, Shijie Xuyang +7
Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense…
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…