RAGOCR renders retrieved documents as images and uses a GRPO-trained compressor to allocate query-dependent resolution, reporting accuracy gains over RAG at reduced token counts, though the evidence in the preprint is inconsistent.
InSecond Conference on Language Modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation
RAGOCR renders retrieved documents as images and uses a GRPO-trained compressor to allocate query-dependent resolution, reporting accuracy gains over RAG at reduced token counts, though the evidence in the preprint is inconsistent.