Xinyi Liu

4

Papers

98

Total Citations

Papers (4)

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance