FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length by rendering text as images, but fixed-resolution rendering creates a compression-performance trade-off: low DPI saves tokens at the expense of legibility, whereas high DPI...
Fang-Zhi Zhong, Xue-Rui Qiu, Yu-Qi Pan et al.
· 0 citations