LLM Digest

Story

arxiv_cs_lg · Oct 27, 2026 · paper

Source brief

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

arxiv.orgOct 27, 2026
original source linked

In brief

Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels in a routed expert contribute little t...

Read the original at arxiv.org →Open in live feed Read that day’s brief

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Earlier in this thread 4 items

ThinkNet: Compact Architecture Selection and Validation-Gated Ensembles for Subject-Independent MI-EEG Decoding

Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind

Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection

Understanding Jev-Style System One Models: Does Structure Reduce Selection Bias?