Xinyu Wang

Affiliations

ShanghaiTech University

papers

235

total citations

papers (14)

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

CVPR 2020arXiv

117

citations

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

ICLR 2025arXiv

citations

ModaVerse: Efficiently Transforming Modalities with LLMs

CVPR 2024arXiv

citations

Are Large Vision Language Models Good Game Players?

ICLR 2025arXiv

citations

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

ICCV 2023arXiv

citations

Unsupervised Object Interaction Learning with Counterfactual Dynamics Models

AAAI 2024

citations

MITracker: Multi-View Integration for Visual Object Tracking

CVPR 2025arXiv

citations

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

NEURIPS 2025arXiv

citations

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

ICCV 2025

citations

In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images

AAAI 2025

citations

CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation

AAAI 2024

citations

Xinyu Wang

Affiliations

papers (14)

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

ModaVerse: Efficiently Transforming Modalities with LLMs

Are Large Vision Language Models Good Game Players?

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

Unsupervised Object Interaction Learning with Counterfactual Dynamics Models

MITracker: Multi-View Integration for Visual Object Tracking

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images

Global Attribute-Association Pattern Aggregation for Graph Fraud Detection

DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection

Polyhedron Attention Module: Learning Adaptive-order Interactions

CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation

papers (14)

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

ModaVerse: Efficiently Transforming Modalities with LLMs

Are Large Vision Language Models Good Game Players?

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

Unsupervised Object Interaction Learning with Counterfactual Dynamics Models

MITracker: Multi-View Integration for Visual Object Tracking

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images

Global Attribute-Association Pattern Aggregation for Graph Fraud Detection

DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection

Polyhedron Attention Module: Learning Adaptive-order Interactions

CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation