Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
arxiv.org·3d
Training Kindai OCR with parallel textline images and self-attention feature distance-based loss
arxiv.org·2d
DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
arxiv.org·1d
ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video
arxiv.org·1d
Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
arxiv.org·13h
ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation
arxiv.org·13h
Loading...Loading more...