pith. sign in

Blockffn: Towards end-side acceleration-friendly mixture-of-experts with chunk-level activation sparsity.arXiv preprint arXiv:2507.08771, 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

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 1 of 1 citing paper.

  • dMoE: dLLMs with Learnable Block Experts cs.CL · 2026-05-29 · unverdicted · none · ref 21

    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.