Kaiyu Song

According to our database, Kaiyu Song authored at least 14 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency.

Kaiyu Song, Hanjiang Lai

CoRR, June, 2025

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization.

Baoshun Tong, Kaiyu Song, Hanjiang Lai

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Test-time Alignment-Enhanced Adapter for Vision-Language Models.

Baoshun Tong, Kaiyu Song, Hanjiang Lai

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion.

Kaiyu Song, Hanjiang Lai

CoRR, 2024

Unraveling the Connections between Flow Matching and Diffusion Probabilistic Models in Training-free Conditional Generation.

Kaiyu Song, Hanjiang Lai

CoRR, 2024

Fisher Information Improved Training-Free Conditional Diffusion Model.

Kaiyu Song, Hanjiang Lai

CoRR, 2024

DNAF: Diffusion with Noise-Aware Feature for Pose-Guided Person Image Synthesis.

Liyan Guo, Kaiyu Song, Mengying Xu, Hanjiang Lai

Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

MALIP: Improving Few-Shot Image Classification with Multimodal Fusion Enhancement.

Kaifen Cai, Kaiyu Song, Yan Pan, Hanjiang Lai

Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model.

Kaiyu Song, Hanjiang Lai, Yan Pan, Jian Yin

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Target to Source: Guidance-Based Diffusion Model for Test-Time Adaptation.

Kaiyu Song, Hanjiang Lai

CoRR, 2023

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model.

Kaiyu Song, Hanjiang Lai

CoRR, 2023

2022

Monocular Visual-Inertial Odometry for Agricultural Environments.

Kaiyu Song, Jingtao Li, Run Qiu, Gaidi Yang

IEEE Access, 2022

Mutual information based Bayesian graph neural network for few-shot learning.

Kaiyu Song, Kun Yue, Liang Duan, Mingze Yang, Angsheng Li

Proceedings of the Uncertainty in Artificial Intelligence, 2022

2020

An Efficient Approach for Parameters Learning of Bayesian Network with Multiple Latent Variables Using Neural Networks and P-EM.

Kaiyu Song, Kun Yue, Xinran Wu, Jia Hao

Proceedings of the Collaborative Computing: Networking, Applications and Worksharing, 2020