A unified RWKV-based model compresses both images and text losslessly with a shared vocabulary, modality-specific contextual layers, and mixture-of-experts routing, matching or improving on much larger SOTA compressors at a fraction of the size.
ts_zip: Text Compression using Large Language Models
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
-
DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor
A unified RWKV-based model compresses both images and text losslessly with a shared vocabulary, modality-specific contextual layers, and mixture-of-experts routing, matching or improving on much larger SOTA compressors at a fraction of the size.