Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Exp

arXiv:2604.00421v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely

arXiv:2604.09780v1 Announce Type: new Abstract: Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their "expert specialization"

arXiv:2605.01327v1 Announce Type: new Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of

arXiv:2604.10152v1 Announce Type: new Abstract: The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large

arXiv:2606.20544v1 Announce Type: new Abstract: Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for

arXiv:2609.06403v1 Announce Type: new Abstract: Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal

arXiv:2605.11603v1 Announce Type: new Abstract: The growing deployment of large language models (LLMs) makes per-request routing essential for balancing response quality and

arXiv:2603.29206v1 Announce Type: new Abstract: Routing is widely used to scale large language models, from Mixture-of-Experts gating to multi-model/tool selection. A common