Skip to content
Signalcrest
Back to entity feed
aientity · one source so far

moe

for LLM engineers

Steadyarxiv
Signal score
9
as of 4d ago
Live items
1
Trajectory
Too early
needs a few more snapshots

Why this scored 9

every term, weighted
Velocity+0.0 / 40

Its fastest-moving item, measured against the pace of its own source

Acceleration+11.1 / 25

Whether that velocity is itself speeding up, as a per-hour rate

Cross-source spread+0.0 / 25

How many independent communities its own items come from

Recency+0.0 / 10

Decays to zero over 14 days, counted from when we first saw it

Saturation penalty1.8 / 30

Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it

Composite9.3

Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On an entity's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology

Signal history

7-day window (free)
911

The evidence

The live items this entity's score aggregates — every community independently talking about it right now. This is the corroboration, shown, not claimed.

  1. 1
    19

    ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs

    ACE enables calibration-free expert skipping in MoE LLMs, cutting inference overhead. · for LLM engineers

    arxivSteadyai4d ago
  2. 2
    9

    MMOE: Modernizing Diffusion Transformers with Efficient Expert Design

    Diffusion transformers improved · for ai researchers, nlp devs

    arxivSteadyai45d ago
  3. 3
    7

    PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

    Efficient LLM serving method · for ai researchers

    arxivSteadyai53d ago