Weijie Su

Affiliations

University of PennsylvaniaUniversity of Science and Technology of China

papers

2,644

total citations

papers (15)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

CVPR 2024arXiv

2,295

citations

Siamese Image Modeling for Self-Supervised Vision Representation Learning

CVPR 2023arXiv

110

citations

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

CVPR 2023arXiv

citations

The alignment property of SGD noise and how it helps select flat minima: A stability analysis

NEURIPS 2022arXiv

citations

You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism

NEURIPS 2021arXiv

citations

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

NEURIPS 2020arXiv

citations

A Central Limit Theorem for Differentially Private Query Answering

NEURIPS 2021arXiv

citations

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

NEURIPS 2023arXiv

citations

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

CVPR 2025arXiv

citations

Shifted Interpolation for Differential Privacy

ICML 2024arXiv

citations

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

NEURIPS 2021arXiv

citations

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

ICML 2024arXiv

citations

Weijie Su

Affiliations

papers (15)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

The alignment property of SGD noise and how it helps select flat minima: A stability analysis

You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

A Central Limit Theorem for Differentially Private Query Answering

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

Shifted Interpolation for Differential Privacy

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

Eliciting Honest Information from Authors Using Sequential Review

The Complete Lasso Tradeoff Diagram

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization

papers (15)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

The alignment property of SGD noise and how it helps select flat minima: A stability analysis

You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

A Central Limit Theorem for Differentially Private Query Answering

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

Shifted Interpolation for Differential Privacy

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning

Eliciting Honest Information from Authors Using Sequential Review

The Complete Lasso Tradeoff Diagram

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization