3 papers
cs.AR2026
SPICE: Speculative Prefetching with Low-Rank Expert Surrogates and Heterogeneous Orchestration for MoE Inference Acceleration
Yongxiang Lyu, Ning Li, Bonian Jia
Mixture-of-Experts (MoE) models are increasingly used in LLMs because sparse activation decouples model capacity from compute cost. However, the large expert parameter footprint of…
physics.flu-dyn2026
Lattice Boltzmann Method for Compressible Navier-Stokes-Fourier Equations
Fedor Bukreev, Adrian Kummerländer, Mathias J. Krause
A lattice Boltzmann scheme for the three-dimensional compressible Navier--Stokes--Fourier equations, derived automatically from the declared system by a symbolic compiler, is valid…
cs.CL2024
LLM-Driven Multimodal Opinion Expression Identification
Bonian Jia, Huiyao Chen, Yueheng Sun +2
Opinion Expression Identification (OEI) is essential in NLP for applications ranging from voice assistants to depression diagnosis. This study extends OEI to encompass multimodal i…