Cheng-Yen Hsieh — accepted AI-conference papers

2026

Protein Autoregressive Modeling via Multiscale Structure Generation

Yanru Qu, Cheng-Yen Hsieh, Zaixiang Zheng, Ge Liu, Quanquan Gu

ICML 2026oral

We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to-fine next-scale prediction. Using the hierarchical nature of proteins, PAR generates structures that mimic sculpting a statue, forming a coarse topology and …

Cited by 0 Source ↗Scholar ↗

2025

Elucidating the Design Space of Multimodal Protein Language Models

Cheng-Yen Hsieh, Xinyou Wang, Daiheng Zhang, Dongyu Xue, Fei Ye, Shujian Huang +2

ICML 2025spotlight

Multimodal protein language models (PLMs) integrate sequence and token-based structural information, serving as a powerful foundation for protein modeling, generation, and design. However, the reliance on tokenizing 3D structures into discrete tokens causes substantial loss of fidelity about fine-g…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗