DocVLM compresses OCR text and layout into 64 learned queries that are injected into frozen VLMs, boosting DocVQA accuracy at low image-token budgets across three model families.
Clipter: Looking at the bigger picture in scene text recogni- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DocVLM: Make Your VLM an Efficient Reader
DocVLM compresses OCR text and layout into 64 learned queries that are injected into frozen VLMs, boosting DocVQA accuracy at low image-token budgets across three model families.