Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Asking like Socrates: Socrates helps VLMs understand remote sensing images
Run Shao, Ziyu Li, Zhaoyang Zhang +9
Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (RS) tasks, we observe widespread pseud…
cs.CV2024
Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
Run Shao, Zhaoyang Zhang, Chao Tao +3
The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power…