pith. sign in

Opportunistic expert activation: Batch-aware expert routing for faster decode without retraining.arXiv preprint arXiv:2511.02237, 2025

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.DC 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

dMoE: dLLMs with Learnable Block Experts

cs.CL · 2026-05-29 · unverdicted · novelty 6.0

dMoE aggregates token expert distributions to block level in dLLMs, cutting unique experts from 69.5 to 14.6, memory by 76-80%, and latency by 1.14-1.66x while retaining 99.11% performance.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving cs.DC · 2026-07-01 · unverdicted · none · ref 28 · 2 links

    ELDR reduces median TPOT by 5.9-13.9% in PD-disaggregated MoE serving via expert signatures from prefill, K-means partitioning, and locality-band routing with KV-co-indexed signature cache.

  • dMoE: dLLMs with Learnable Block Experts cs.CL · 2026-05-29 · unverdicted · none · ref 30

    dMoE aggregates token expert distributions to block level in dLLMs, cutting unique experts from 69.5 to 14.6, memory by 76-80%, and latency by 1.14-1.66x while retaining 99.11% performance.