Hao Yu

15

Papers

87

Total Citations

Papers (15)

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Domain Shifting: A Generalized Solution for Heterogeneous Cross-Modality Person Re-Identification

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures

Quantization without Tears

What Is a Good Question? Assessing Question Quality via Meta-Fact Checking

Treasures in Discarded Weights for LLM Quantization

Differentiable Auxiliary Learning for Sketch Re-identification

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

Efficient Federated Incomplete Multi-View Clustering

Memory-Efficient Generative Models via Product Quantization

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition