YIYANG FU — accepted AI-conference papers

2026

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

Yiyang Fu, Chubin Zhang, Shukai Gong, Yufan Deng, Kaiwei Sun, Qiyang Min +4

ICML 2026poster

It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models when encountering unseen real-world visual disturbances, particularly under imperfect visual conditions. In this work, …

Cited by 0 Source ↗Scholar ↗

2025

TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding

Shukai Gong, YIYANG FU, Fengyuan Ran, Quyu Kong, Feng Zhou

NeurIPS 2025poster

We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning algorithms for TPPs and speculative decoding for language models,…

Cited by 0 Source ↗Scholar ↗