2 papers
cs.CV2025
View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs
Yuanyuan Liu, Haiyang Mei, Dongyang Zhan +4
3D visual grounding (3DVG) identifies objects in 3D scenes from language descriptions. Existing zero-shot approaches leverage 2D vision-language models (VLMs) by converting 3D spat…
cs.NE2025
Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis
Yunduo Zhou, Bo Dong, Chang Li +4
Homeostatic mechanisms play a crucial role in maintaining optimal functionality within the neural circuits of the brain. By regulating physiological and biochemical processes, thes…