mllm
for NLP researchers
Why this scored 10
every term, weightedIts fastest-moving item, measured against the pace of its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities its own items come from
Decays to zero over 14 days, counted from when we first saw it
Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it
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)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.
- 120
When MLLMs miss what humans read: diagnosing and learning to read squint text
Diagnoses why multimodal LLMs miss human-read text. · for NLP researchers
arxivSteadyai16d ago - 219
One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints
Efficient zero-shot navigation using spatial waypoints with a single multimodal LLM call. · for robotics developers, multimodal AI teams
arxivSteadyai49d ago - 316
Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
Combines sparse anchors with dense adaptation to break self-referential loops in test-time adaptation. · for LLM engineers
arxivSteadyai42d ago - 40
moonshotai/PerceptionBench (dataset)
New multimodal dataset released · for ai researchers
huggingfaceSteadyai−9 saturated92d ago