Xiao Wang

53

Papers

536

Total Citations

1

Affiliations

Affiliations

Boston University

Papers (53)

On Scaling Up a Multilingual Vision and Language Model

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

A Generalized Neural Diffusion Framework on Graphs

On Large Language Model Continual Unlearning

Graph Contrastive Invariant Learning from the Causal Perspective

Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset

CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset

Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception

TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

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

Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries

LiT: Zero-Shot Transfer With Locked-Image Text Tuning

Federated Class-Incremental Learning

Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network

Curricular Object Manipulation in LiDAR-Based Object Detection

NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras

Learn To Match: Automatic Matching Network Design for Visual Tracking

Simple Open-Vocabulary Object Detection with Vision Transformers

On the Importance of Asymmetry for Siamese Representation Learning

Split Adaptation for Pre-trained Vision Transformers

EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching

Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework

TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification

Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective

Finding Visual Saliency in Continuous Spike Stream

Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg

Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity

Less is More: on the Over-Globalizing Problem in Graph Transformers

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Position: TrustLLM: Trustworthiness in Large Language Models

SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation

Towards More Flexible and Accurate Object Tracking With Natural Language: Algorithms and Benchmark

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units

First-order methods almost always avoid saddle points: The case of vanishing step-sizes

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Universal Graph Convolutional Networks

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration

Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

Uncovering the Structural Fairness in Graph Contrastive Learning

On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Robust and Actively Secure Serverless Collaborative Learning

Learning Invariant Representations of Graph Neural Networks via Cluster Generalization

Provable Training for Graph Contrastive Learning

Learning Invariant Molecular Representation in Latent Discrete Space

Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always