Yizhen Yao — accepted AI-conference papers

2026

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding

Yanzheng Xiang, Lan Wei, Yizhen Yao, Qinglin Zhu, Hanqi Yan, Chen Jin +5

ICML 2026poster

Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we observe that existing verification schemes frequently trigger fl…

Cited by 0 Source ↗Scholar ↗

2025

AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference

Zhuomin He, Yizhen Yao, Pengfei Zuo, Bin Gao, Qinya Li, Zhenzhe Zheng +1

AAAI 2025technical

Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗