{
  "id": 11339940,
  "title": "ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models",
  "url": "https://urgent.news/2026/10/01/itc-moe-importance-guided-token-aware-compression-for-moe-diffusion",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-01T08:31:26.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.01296v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substantial computation and storage costs. Existing low-rank MoE compression methods largely rely on static factorization and fixed rank allocation, which overlook the distinctive properties of MoE DLMs. Specifically, we…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}