2 papers
cs.LG2026
DBES: A Systematic Benchmark and Metric Suite for Evaluating Expert Specialization in Large-Scale MoEs
Jing Wang, Hongxuan Lu, Jazze Young +2
Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balancing with functional specializat…
cs.CL2026
TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning
Dabiao Ma, Ziming Dai, Zhimin Xin +3
Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes…