Newest papers

CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing

Qingyue Wang, Yudong Gao, Lixia Wang, Ruixuan Huang, Yuanyuan Yuan, Yangqiu Song, Shuai Wang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29395 · open-access PDF

Arabic

ويهدف الحد الأقصى إلى ضمان توقعات النماذج في ظل التغيرات المتنازع عليها.إن إطار الأدوات التشريعية الموجودة، التي تم تأليفها من قبل التفسير الإبداعي أو التنفيذ العنصري، عادة ما تشير إلى ورقة حسابية ثابتة، حيث تؤثر التغيرات أو التغيرات في الدخول فقط على النتائج النماذج وليس الطريق التنفيذي الأساسية.

Machine translation (Meta M2M100); the English original follows.

Abstract

Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under adversarial perturbations. Existing certification frameworks, inspired by abstract interpretation or symbolic execution, typically assume a fixed computation graph, where input perturbations or variations affect only model outputs but not the underlying execution path. This assumption, however, is violated in Mixture-of-Experts (MoE) Large Language Models (LLMs), whose input-dependent routing induces discrete and dynamic execution paths. Crucially, this dynamic computation changes

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29395, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange