Pengyu An — accepted AI-conference papers

2026

Mitigating The Distribution Shift of Diffusion-based Dataset Distillation

Yue Xu, Chenyu Hu, Pengyu An, Yong-Lu Li

CVPR 2026

Dataset Distillation (DD) seeks to create small, synthetic datasets for efficient model training. While diffusion models are powerful generators, their use in DD is hampered by distribution shifts between synthetic and ideal distilled data, leading to suboptimal performance. We identify two critical

Cited by 0 Source ↗Scholar ↗

2025

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation

Yue Xu, Litao Wei, Pengyu An, Qingyu Zhang, Yong-Lu Li

CoRL 2025poster

Tactile-aware robot learning faces critical challenges in data collection and representation due to data scarcity and sparsity, and the absence of force feedback in existing systems. To address these limitations, we introduce a tactile robot learning system with both hardware and algorithm innovatio…

Cited by 0 Source ↗Scholar ↗