Bo Xu

9

Papers

35

Total Citations

Papers (9)

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

Efficient 3D Recognition with Event-driven Spike Sparse Convolution

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs

Incomplete and Unpaired Multi-View Graph Clustering with Cross-View Feature Fusion

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection

GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

NeurIPS 2025arXiv

Privileged Prior Information Distillation for Image Matting