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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PEVLM: Parallel Encoding for Vision-Language Models
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.