7 papers
DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
Yufei Jia, Guangyu Wang, Yuhang Dong +17
We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper…
FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation
Linyan Huang, Haonan Lin, Yanning Zhou +1
With the rapid advancement of 2D generative models, preserving subject identity while enabling diverse editing has emerged as a critical research focus. Existing methods typically…
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
Wenbin An, Feng Tian, Sicong Leng +6
Despite great success across various multimodal tasks, Large Vision-Language Models (LVLMs) often encounter object hallucinations with generated textual responses being inconsisten…
Unleashing the Potential of Model Bias for Generalized Category Discovery
Wenbin An, Haonan Lin, Jiahao Nie +5
Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another la…
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
Haonan Lin, Mengmeng Wang, Jiahao Wang +7
Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires…
OneActor: Consistent Character Generation via Cluster-Conditioned Guidance
Jiahao Wang, Caixia Yan, Haonan Lin +5
Text-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject.…