Chen-Yu Wang — accepted AI-conference papers

2025

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps

Bingnan Li, Chen-Yu Wang, Haiyang Xu, Xiang Zhang, Ethan J. Armand, Divyansh Srivastava +4

NeurIPS 2025poster

Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary challenges: (1) large overlapping regions and (2) overlapping instances with minimal semantic distinction. Through both qu…

Cited by 0 Source ↗code ↗Scholar ↗

2024

When Green Learning Meets Federated Learning: Toward Distributed Learning with Low Complexity and Model Heterogeneity

Yi-Cheng Lai, Chen-Yu Wang, Feng-Tsun Chien

ICASSP 2024accepted

In this paper, we study the problem of aggregating heterogeneous models with low-complexity consideration in federated learning (FL). A green heterogeneous federated learning (GHFL) system, the marriage of the green learning (GL) methodology and FL, is proposed to simultaneously account for model he…

Cited by 0 Source ↗Scholar ↗