Representative papers are highlighted.

2026

IMS³: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation
CVPR
IMS³: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation

Chenru Wang*; Yunyi Chen*; Zijun Yang; Joey Tianyi Zhou; Chi Zhang#. (* equal contribution, # corresponding author)

IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

Developed Inversion-Matching (IM) to align denoising and inversion trajectories, broadening distributional coverage of distilled samples. Designed Selective Subgroup Sampling (S³) to improve inter-class separability and boundary coverage, achieving state-of-the-art performance among diffusion-based distillation methods.

[arXiv]

IMS³: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation

Chenru Wang*; Yunyi Chen*; Zijun Yang; Joey Tianyi Zhou; Chi Zhang#. (* equal contribution, # corresponding author)

IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

Developed Inversion-Matching (IM) to align denoising and inversion trajectories, broadening distributional coverage of distilled samples. Designed Selective Subgroup Sampling (S³) to improve inter-class separability and boundary coverage, achieving state-of-the-art performance among diffusion-based distillation methods.

[arXiv]

CVPR
MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation
ECCV
MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation

Yunyi Chen*; Chenru Wang*; Xinyi Ye; Zexin Zheng; Chi Zhang#. (* equal contribution, # corresponding author)

European Conference on Computer Vision 2026 (Under Review)

Proposed Manifold-Guided Policy Optimization (MGPO), formulating diffusion-based dataset distillation as a multi-objective reinforcement learning problem. Combined pixel-space discriminative rewards with latent-space manifold rewards guided by class-wise MST skeletons, improving downstream classification, detection, and segmentation performance.

[arXiv]

MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation

Yunyi Chen*; Chenru Wang*; Xinyi Ye; Zexin Zheng; Chi Zhang#. (* equal contribution, # corresponding author)

European Conference on Computer Vision 2026 (Under Review)

Proposed Manifold-Guided Policy Optimization (MGPO), formulating diffusion-based dataset distillation as a multi-objective reinforcement learning problem. Combined pixel-space discriminative rewards with latent-space manifold rewards guided by class-wise MST skeletons, improving downstream classification, detection, and segmentation performance.

[arXiv]

ECCV