papers

Publications (16)

cs.CV2025

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency

Jiajian Xie, Hubery Yin, Chen Li +2

Diffusion models have achieved remarkable generative quality but remain bottlenecked by costly iterative sampling. Recent training-free methods accelerate diffusion process by reus…

cs.CV2024

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

Pengze Zhang, Hubery Yin, Chen Li +1

Most diffusion models assume that the reverse process adheres to a Gaussian distribution. However, this approximation has not been rigorously validated, especially at singularities…

cs.CV2026

NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing

Tianlin Pan, Jiayi Dai, Chenpu Yuan +7

Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly ch…

cs.CV2024

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models

Fangyikang Wang, Hubery Yin, Yuejiang Dong +5

The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact…

cs.CV2026

StableWorld: Towards Stable and Consistent Long Interactive Video Generation

Ying Yang, Zhengyao Lv, Tianlin Pan +6

In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds th…

cs.CV2025

Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin

Fangyikang Wang, Hubery Yin, Lei Qian +9

The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniq…