Feihong Yan — accepted AI-conference papers

2026

Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling

Feihong Yan, Yao Zhu, Peiru Wang, Pang Kaiyu, Qingyan Wei, Huiqi Li +1

ICLR 2026poster

Masked Autoregressive (MAR) models promise better efficiency in visual generation than continuous autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of spatially correlated visual tokens in a single step.…

Cited by 0 Source ↗code ↗Scholar ↗

2025

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching

Feihong Yan, Qingyan Wei, Jiayi Tang, Jiajun Li, Yulin Wang, Xuming Hu +2

ICCV 2025poster

Masked Autoregressive (MAR) models have emerged as a promising approach in image generation, expected to surpass traditional autoregressive models in computational efficiency by leveraging the capability of parallel decoding. However, their dependence on bidirectional self-attention inherently confl…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗