Qi Zhu

papers

750

total citations

papers (21)

Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator

ICCV 2021arXiv

citations

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

ICCV 2025arXiv

citations

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

NEURIPS 2023arXiv

citations

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

ICCV 2025arXiv

citations

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

ICML 2024arXiv

citations

Split Adaptation for Pre-trained Vision Transformers

CVPR 2025arXiv

citations

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

CVPR 2025arXiv

citations

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

CVPR 2024

citations

SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling

CVPR 2025

citations

Exploring Temporal Frequency Spectrum in Deep Video Deblurring

ICCV 2023

citations

Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction

ICCV 2023

citations

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

NEURIPS 2023

citations

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

NEURIPS 2021arXiv

citations

Qi Zhu

papers (21)

Federated Class-Incremental Learning

Leapfrog Diffusion Model for Stochastic Trajectory Prediction

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data

On Large Language Model Continual Unlearning

Parallelizing non-linear sequential models over the sequence length

Delta Decompression for MoE-based LLMs Compression

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Where am I? Cross-View Geo-localization with Natural Language Descriptions

Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Split Adaptation for Pre-trained Vision Transformers

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling

Exploring Temporal Frequency Spectrum in Deep Video Deblurring

Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

papers (21)

Federated Class-Incremental Learning

Leapfrog Diffusion Model for Stochastic Trajectory Prediction

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data

On Large Language Model Continual Unlearning

Parallelizing non-linear sequential models over the sequence length

Delta Decompression for MoE-based LLMs Compression

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Where am I? Cross-View Geo-localization with Natural Language Descriptions

Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Split Adaptation for Pre-trained Vision Transformers

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling

Exploring Temporal Frequency Spectrum in Deep Video Deblurring

Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization