Published in arXiv preprint, 2026
A lightweight, learning-based multi-step solver that learns unconstrained time-varying parameters to adaptively aggregate historical gradients for efficient diffusion sampling.
Recommended citation: T Zhao, M Lei, L Yuan, Y Yang, C Song, Y Wang, B Zhu, C Zhang. (2026). "DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling." arXiv preprint arXiv:2603.11607.
Download Paper
Published in IEEE Journal of Selected Topics in Signal Processing (J-STSP), 2026
A method for generating high-quality, stylized 3D avatars using pre-trained image-text diffusion models and GAN-based 3D generation.
Recommended citation: C Zhang, Y Chen, Y Fu, W Cheng, Z Zhou, W Jiang, Z Wang, B Fu, T Chen, G Yu, G Lin, C Song. (2026). "StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation." IEEE J-STSP.
Download Paper
Published in CVPR 2026, 2026
A training-free, layer-adaptive framework for long video generation that addresses out-of-distribution issues in pre-trained video diffusion models.
Recommended citation: J Tian, C Song, W Cheng, C Zhang. (2026). "Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction." CVPR 2026.
Download Paper
Published in CVPR 2026, 2026
A training-free framework for multi-event video generation that steers frame-level attention to align with relevant event prompts.
Recommended citation: Q Xu, C Song, Y Cai, C Zhang. (2026). "SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls." CVPR 2026.
Download Paper
Published in CVPR 2026, 2025
A training-free geometry-aware caching framework that accelerates 3D diffusion inference while preserving geometric fidelity.
Recommended citation: M Yang, Y Yang, C Xu, C Song, Y Zuo, T Zhao, R Li, C Zhang. (2025). "Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration." arXiv preprint arXiv:2511.22533.
Download Paper
Published in CVPR 2026, 2025
A lightweight world model project focused on controllable generation of 3D & 4D scenes and objects.
Recommended citation: C Song, Y Yang, T Zhao, R Li, C Zhang. (2025). "Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control. " arXiv preprint arXiv:2509.15130.
Download Paper
Published in arXiv preprint, 2025
A novel evolutionary framework for GUI agents that enhances operational efficiency through action evolution.
Recommended citation: W Jiang, Y Zhuang, C Song, X Yang, JT Zhou, C Zhang. (2025). "Appagentx: Evolving gui agents as proficient smartphone users." arXiv preprint arXiv:2503.02268.
Download Paper
Published in CVPR 2026, 2025
Training-free flow steering approach for precise text-to-video editing applications.
Recommended citation: G Li, Y Yang, C Song, C Zhang. (2025). "FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing." arXiv preprint arXiv:2506.05046.
Download Paper
Published in IEEE Transactions on Circuits and Systems for Video Technology, 2024
An efficient few-shot view synthesis network that uses trend regularization for improved performance.
Recommended citation: C Song, S Wang, J Wei, Y Zhao. (2024). "FewarNet: An efficient few-shot view synthesis network based on trend regularization." IEEE Transactions on Circuits and Systems for Video Technology. 34 (10), 9264-9278.
Download Paper
Published in Displays, 2024
Novel approach for elemental image array generation using BVH structure with spatial partition and display optimization.
Recommended citation: T Li, S Wang, J Wei, Y Zhao, C Song, R Zhang. (2024). "Elemental image array generation based on BVH structure combined with spatial partition and display optimization." Displays. 84, 102784.
Download Paper
Published in Displays, 2023
Wide-baseline view synthesis approach for light-field display using plane-depth-fused sweep volume technique.
Recommended citation: C Song, S Wang, J Wei, Y Zhao, R Zhang. (2023). "Wide-baseline view synthesis for light-field display based on plane-depth-fused sweep volume." Displays. 79, 102503.
Download Paper
Published in Applied Optics, 2020
Method for efficiently enhancing co-occurring details while avoiding artifacts in light field display systems.
Recommended citation: J Wei, S Wang, Y Zhao, M Piao, C Song. (2020). "Efficiently enhancing co-occurring details while avoiding artifacts for light field display." Applied Optics. 59 (21), 6315-6326.
Download Paper