works on

From the 1 of 6 linked papers with an AI index.

activity
20242026
most citedAdvancing Aesthetic Image Generation via Composition Transfer

1 citations · 1 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2026

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

Yupeng Zheng, Kai Zou, Bin Liu +1

VisCo introduces a training-efficient self-compression framework that reuses a pretrained vision-language model as an intrinsic autoencoder to compress visual tokens into a small s…

cs.CV2026

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

Dian Zheng, Manyuan Zhang, Hongyu Li +4

Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent tas…

cs.CV20261 cited

Advancing Aesthetic Image Generation via Composition Transfer

Kai Zou, Zhiwei Zhao, Bin Liu +1

Composition is a cornerstone of visual aesthetics, influencing the appeal of an image. While its principles operate independently of specific content, in practice, composition is o…

cs.CV2026

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Kai Zou, Dian Zheng, Hongbo Liu +3

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity whi…

cs.CV2025

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models

Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou +1

Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-…

cs.CV2024

NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou +1

We introduce NitroFusion, a fundamentally different approach to single-step diffusion that achieves high-quality generation through a dynamic adversarial framework. While one-step…