Bo Xu

papers

462

total citations

papers (16)

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

NEURIPS 2020arXiv

citations

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

NEURIPS 2023arXiv

citations

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

AAAI 2025arXiv

citations

Efficient 3D Recognition with Event-driven Spike Sparse Convolution

AAAI 2025arXiv

citations

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

ICCV 2021arXiv

citations

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

AAAI 2025

citations

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs

AAAI 2025

citations

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

CVPR 2025arXiv

citations

Privileged Prior Information Distillation for Image Matting

AAAI 2024arXiv

citations

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

NEURIPS 2025arXiv

citations

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

AAAI 2025

citations

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

AAAI 2025

citations

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization

CVPR 2023

citations

Bo Xu

papers (16)

Spike-driven Transformer

Discriminative Multi-Modality Speech Recognition

Inherent Redundancy in Spiking Neural Networks

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

Efficient 3D Recognition with Event-driven Spike Sparse Convolution

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

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

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

Privileged Prior Information Distillation for Image Matting

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

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

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization

papers (16)

Spike-driven Transformer

Discriminative Multi-Modality Speech Recognition

Inherent Redundancy in Spiking Neural Networks

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

Efficient 3D Recognition with Event-driven Spike Sparse Convolution

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

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

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

Privileged Prior Information Distillation for Image Matting

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

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

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization