Xulei Yang

PIRN: Prototypical-based Intra-modal Reconstruction with Normality Communication for Multi-modal Anomaly Detection.

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion

Test-Time Optimization of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and Refinement

Mixture-of-Gaussian Evidential Learning for Uncertainty-Aware Stereo Matching

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning

Towards Few-Shot Adaptation for Dense Cross-Modality Image Matching

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation

Evidential Learning-based Certainty Estimation for Robust Dense Feature Matching

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

Distribution-Aware Diffusion Model Quantization via Distortion Minimization

Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation

Harmonious convergence for confidence estimation in depth estimation and completion

DM3D: Parameter-Efficient and Lossless 3D Object Detection via Distortion Minimization

MS$^3$M: Multi-Stage State Space Model for Motion Forecasting

Test-Time Training for Out-of-Distribution Industrial Anomaly Detection via Robust Distribution Alignment