Tag: Vision-Language Models
Browse our exclusive articles!
ExtrinSplat: Advanced 3D Gaussian Splatting for Open-Vocab AI
Discover ExtrinSplat, a novel 3D Gaussian Splatting method that decouples geometry and semantics for faster, efficient open-vocabulary AI understanding.
Enhancing Autonomous Driving Safety with Vision-Language Models
Discover how vision-language models improve hazard detection and edge-case evaluation to boost autonomous driving safety and reliability.
Enhancing VLMs with Spatial Symbols for Better Gameplay
Improve Vision-Language Models' gameplay by grounding them with spatial and symbolic scene representations for more accurate actions in interactive environ...
Enhance Spatial Reasoning with GeoSR Geometry Model
Discover how GeoSR boosts spatial reasoning in vision-language models by integrating 3D geometric data for superior image and video analysis.
Boost Vision-Language Fine-Tuning with Adaptive Depth Aggregation
Improve vision-language model fine-tuning by mitigating reasoning tax using Input-Adaptive Depth Aggregation for better reasoning and perception.