AI RESEARCH
Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception
arXiv CS.CV
•
ArXi:2605.21882v1 Announce Type: new Vision-language models (VLMs) often fail under low illumination because their visual grounding is learned predominantly from RGB imagery, whereas thermal infrared preserves complementary scene structure when visible cues degrade. We present Thermo-VL, a wavelength-aware VLM that augments a frozen Molmo-7B backbone with a trainable thermal encoder and a text-guided dual-attention fusion module.