most citedMulti-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling

Mingyuan Zhang, Yue Bai, Zhongruo Wang +5

Sparsely activated Mixture-of-Experts (MoE) models increase model capacity without a proportional increase in per-token computation. Dense-to-MoE upcycling reuses pretrained dense…

cs.LG2026

SCI-Defense: Detecting Persuasion-Structured Manipulation of LLM-Based Ranking in Generative Engines

Xucheng Yu, Haibo Jin, Huimin Zeng +1

Generative engine optimization (GEO) has reshaped how sellers compete for visibility in LLM-generated rankings. By embedding persuasive arguments in the content they control, selle…