Yifei Zhang

papers

541

total citations

papers (20)

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

ICML 2025arXiv

citations

Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition

CVPR 2025arXiv

citations

Learning Visual Generative Priors without Text

CVPR 2025arXiv

citations

BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning

CVPR 2025

citations

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

NEURIPS 2023

citations

pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation

CVPR 2025

citations

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning

ICCV 2025arXiv

citations

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

NEURIPS 2023

citations

Robustifying Zero-Shot Vision Language Models by Subspaces Alignment

ICCV 2025

citations

LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D Generation

ICCV 2025

citations

MAGI: Multi-Annotated Explanation-Guided Learning

ICCV 2023

citations

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective

NEURIPS 2023

citations

Yifei Zhang

papers (20)

Continuous 3D Perception Model with Persistent State

Customizable Image Synthesis with Multiple Subjects

Language-Image Pre-training with Long Captions

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Lipschitz Singularities in Diffusion Models

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Dimensionality-Varying Diffusion Process

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition

Learning Visual Generative Priors without Text

BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

Robustifying Zero-Shot Vision Language Models by Subspaces Alignment

LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D Generation

MAGI: Multi-Annotated Explanation-Guided Learning

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective

papers (20)

Continuous 3D Perception Model with Persistent State

Customizable Image Synthesis with Multiple Subjects

Language-Image Pre-training with Long Captions

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Lipschitz Singularities in Diffusion Models

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Dimensionality-Varying Diffusion Process

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition

Learning Visual Generative Priors without Text

BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

Robustifying Zero-Shot Vision Language Models by Subspaces Alignment

LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D Generation

MAGI: Multi-Annotated Explanation-Guided Learning

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective