3 accepted papers
Vision-Language Models (VLMs), exemplified by CLIP, have emerged as foundational for multimodal intelligence. However, their capacity for logical understanding remains significantly underexplored, resulting in critical **
Unlocking the spatial intelligence of multimodal large language models (MLLMs) is crucial for understanding and interacting with the 3D world. Prevailing approaches typically inject spatial priors via external tools, which impose significant inference overhead, or rely on latent feature distillation
Modeling task-driven attention in driving is a fundamental challenge for both autonomous vehicles and cognitive science. Existing methods primarily predict where drivers look by generating spatial heatmaps, but fail to capture the cognitive motivations behind attention allocation in specific context…