Aojun Zhou

papers

1,144

total citations

papers (13)

Incorporating Convolution Designs Into Visual Transformers

ICCV 2021arXiv

568

citations

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

ICLR 2024arXiv

198

citations

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

CVPR 2025arXiv

citations

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

ICML 2024arXiv

citations

Chimera: Improving Generalist Model with Domain-Specific Experts

ICCV 2025arXiv

citations

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

CVPR 2025arXiv

citations

Differentiable Dynamic Wirings for Neural Networks

ICCV 2021

citations

GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices

ICCV 2025arXiv

citations

SparseMAE: Sparse Training Meets Masked Autoencoders

ICCV 2023

citations

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

NEURIPS 2021

citations

Aojun Zhou

papers (13)

Incorporating Convolution Designs Into Visual Transformers

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

JourneyDB: A Benchmark for Generative Image Understanding

Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

Group R-CNN for Weakly Semi-Supervised Object Detection With Points

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

Chimera: Improving Generalist Model with Domain-Specific Experts

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

Differentiable Dynamic Wirings for Neural Networks

GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices

SparseMAE: Sparse Training Meets Masked Autoencoders

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

papers (13)

Incorporating Convolution Designs Into Visual Transformers

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

JourneyDB: A Benchmark for Generative Image Understanding

Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

Group R-CNN for Weakly Semi-Supervised Object Detection With Points

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

Chimera: Improving Generalist Model with Domain-Specific Experts

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

Differentiable Dynamic Wirings for Neural Networks

GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices

SparseMAE: Sparse Training Meets Masked Autoencoders

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks