Wei Zhao

17

Papers

332

Total Citations

Papers (17)

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Reliable Conflictive Multi-View Learning

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

NodeMixup: Tackling Under-Reaching for Graph Neural Networks

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction

Local Conditional Controlling for Text-to-Image Diffusion Models

Entropy Induced Pruning Framework for Convolutional Neural Networks

Democratic Training Against Universal Adversarial Perturbations

AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification

Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation

Biased Incomplete Multi-View Learning

Correlation-Guided Attention for Corner Detection Based Visual Tracking

Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses

Learning Quality-Aware Dynamic Memory for Video Object Segmentation

Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering