From the 1 of 8 linked papers with an AI index.
8 papers
RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer
Jing Li, Yawei Luo, Xiangze Meng +3
RealSkin is a self‑supervised framework that transfers visual attributes from real photos onto synthetic 3D models by learning correspondences in a spectral domain and refining the…
Rectified Schrödinger Bridge Matching for Few-Step Visual Navigation
Wuyang Luan, Junhui Li, Weiguang Zhao +3
Visual navigation is a core challenge in Embodied AI, requiring autonomous agents to translate high-dimensional sensory observations into continuous, long-horizon action trajectori…
Physics-Aware 3D Gaussian Editing for Driving Scene Generation
Feng Zhou, Jian Zhang, Yuhang Sun +5
3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation.…
SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
Wuyang Luan, Junhui Li, Weiguang Zhao +3
Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoi…
ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
Lihong Wang, Liangqi Li, Weiwei Feng +6
CoT has significantly enhanced the reasoning ability of LLMs while it faces challenges when extended to multimodal domains, particularly in mathematical tasks. Existing MLLMs typic…
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
Tongyuan Bai, Wangyuanfan Bai, Dong Chen +3
Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but la…