pith. sign in

Dash: Dynamic audio-driven semantic chunking for efficient omnimodal token compression, 2026

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance

cs.AI · 2026-05-14 · unverdicted · novelty 6.0

OmniDrop is a training-free layer-wise token pruning framework for omni-modal LLMs that uses query guidance and temporal diversity to reduce prefill latency by up to 40% and memory by 14.7% while improving benchmark scores by up to 3.58 points.

citing papers explorer

Showing 1 of 1 citing paper.

  • OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance cs.AI · 2026-05-14 · unverdicted · none · ref 18

    OmniDrop is a training-free layer-wise token pruning framework for omni-modal LLMs that uses query guidance and temporal diversity to reduce prefill latency by up to 40% and memory by 14.7% while improving benchmark scores by up to 3.58 points.