CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
arxiv.org·2d
TEFormer: Texture-Aware and Edge-Guided Transformer for Semantic Segmentation of Urban Remote Sensing Images
arxiv.org·3d
DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation
arxiv.org·1d
ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video
arxiv.org·11h
Loading...Loading more...