Kun Yuan

papers

1,203

total citations

papers (22)

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

NEURIPS 2022arXiv

citations

Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression

NEURIPS 2022arXiv

citations

Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization

NEURIPS 2022arXiv

citations

Quality-Aware Pre-Trained Models for Blind Image Quality Assessment

CVPR 2023arXiv

citations

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

NEURIPS 2023arXiv

citations

Self-Supervised Correlation Mining Network for Person Image Generation

CVPR 2022arXiv

citations

An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders

NEURIPS 2021arXiv

citations

PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild

CVPR 2024arXiv

citations

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

AAAI 2025arXiv

citations

KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

CVPR 2025arXiv

citations

Learning Connectivity of Neural Networks from a Topological Perspective

ECCV 2020arXiv

citations

Distributed Bilevel Optimization with Communication Compression

ICML 2024arXiv

citations

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

NEURIPS 2025arXiv

citations

Differentiable Dynamic Wirings for Neural Networks

ICCV 2021

citations

Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation

ECCV 2020

citations

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

NEURIPS 2025arXiv

citations

Kun Yuan

papers (22)

Incorporating Convolution Designs Into Visual Transformers

Exponential Graph is Provably Efficient for Decentralized Deep Training

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

CHEX: CHannel EXploration for CNN Model Compression

DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training

KVQ: Kwai Video Quality Assessment for Short-form Videos

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression

Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization

Quality-Aware Pre-Trained Models for Blind Image Quality Assessment

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Self-Supervised Correlation Mining Network for Person Image Generation

An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders

PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

Learning Connectivity of Neural Networks from a Topological Perspective

Distributed Bilevel Optimization with Communication Compression

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

Differentiable Dynamic Wirings for Neural Networks

Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

papers (22)

Incorporating Convolution Designs Into Visual Transformers

Exponential Graph is Provably Efficient for Decentralized Deep Training

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

CHEX: CHannel EXploration for CNN Model Compression

DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training

KVQ: Kwai Video Quality Assessment for Short-form Videos

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression

Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization

Quality-Aware Pre-Trained Models for Blind Image Quality Assessment

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Self-Supervised Correlation Mining Network for Person Image Generation

An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders

PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception

Learning Connectivity of Neural Networks from a Topological Perspective

Distributed Bilevel Optimization with Communication Compression

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

Differentiable Dynamic Wirings for Neural Networks

Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling