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

vlm

for ai researchers

Steadyarxiv
Signal score
2
as of 44d ago
Live items
1
Trajectory
Too early
needs a few more snapshots

Why this scored 2

every term, weighted
Velocity+0.0 / 40

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

Acceleration+0.0 / 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+3.6 / 10

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

Saturation penalty1.2 / 30

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

Composite2.4

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)
Not enough history yet — the trend line fills in as snapshots accrue (every 30 min).

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
    9

    Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs

    Image tampering detection · for computer vision devs

    arxivSteadyai52d ago
  2. 2
    9

    DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes

    Improves data recipe scalability · for ai researchers

    arxivSteadyai45d ago
  3. 3
    7

    More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe

    Scales remote sensing · for geospatial analysts

    arxivSteadyai53d ago