Xulei Yang

9

Papers

38

Total Citations

Papers (9)

Text-to-Image Rectified Flow as Plug-and-Play Priors

Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching

Global-Aware Monocular Semantic Scene Completion with State Space Models

FIND: Few-Shot Anomaly Inspection with Normal-Only Multi-Modal Data

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Future-Aware Interaction Network For Motion Forecasting

Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations

Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification