Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

PEVLM: Parallel Encoding for Vision-Language Models

cs.CV · 2025-06-24 · conditional · novelty 6.0

A fine-tuning-free parallel encoding scheme for VLMs that partitions video frames into context blocks with a shared sink block and sequential position embeddings, reducing prefill attention from quadratic to linear while preserving accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • PEVLM: Parallel Encoding for Vision-Language Models cs.CV · 2025-06-24 · conditional · none · ref 1

    A fine-tuning-free parallel encoding scheme for VLMs that partitions video frames into context blocks with a shared sink block and sequential position embeddings, reducing prefill attention from quadratic to linear while preserving accuracy.