collaborators

6 papers

cs.CV2026

InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion

Guangzhao Li, Qingyan Wei, Huayu Zheng +7

We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from cross-category…

cs.CV2026

STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models

Qingyan Wei, Guangzhao Li, Xiaobing Tu +5

On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD metho…

cs.CL2026

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles

Qingyan Wei, Yaojie Zhang, Zhiyuan Liu +5

Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing…

cs.CV2026

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

Feihong Yan, Peiru Wang, Yao Zhu +4

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration pot…

cs.CV2025

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping

Jiajun Li, Yue Ma, Xinyu Zhang +3

Recent studies on Visual Autoregressive (VAR) models have highlighted that high-frequency components, or later steps, in the generation process contribute disproportionately to inf…

cs.CV2025

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching

Feihong Yan, Qingyan Wei, Jiayi Tang +5

Masked Autoregressive (MAR) models have emerged as a promising approach in image generation, expected to surpass traditional autoregressive models in computational efficiency by le…