9 papers
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Yuhan Li, Fangao Zeng, Sicong Kang +5
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequenti…
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
Yu Cheng, Siyue Yao, Zhongang Qi +3
Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significa…
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
Zhizhou Chen, Shanyan Guan, Zhanxin Gao +6
Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency textu…
Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models
Yuehao Liu, Shanyan Guan, Weijia Zhang +4
Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent l…
Guiding a Diffusion Model by Swapping Its Tokens
Weijia Zhang, Yuehao Liu, Shanyan Guan +4
Classifier-Free Guidance (CFG) is a widely used inference-time technique to boost the image quality of diffusion models. Yet, its reliance on text conditions prevents its use in un…
NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
Yanpeng Zhao, Shanyan Guan, Yunbo Wang +3
We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the scie…