12 papers · 1 filter
ReWorld: Representation Learning for World Action Models
Tianze Xia, Lijun Zhou, Kaixin Xiong +9
World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only the final outputs, leaving inter…
DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
Tianze Xia, Yongkang Li, Lijun Zhou +9
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approa…
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
Lunbin Zeng, Jingfeng Yao, Bencheng Liao +3
Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce…
Towards Scalable Pre-training of Visual Tokenizers for Generation
Jingfeng Yao, Yuda Song, Yucong Zhou +1
The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a l…
UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation
Ruiheng Zhang, Jingfeng Yao, Huangxuan Zhao +9
Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals: semantic abstracti…
Visual Generation Tuning
Jiahao Guo, Sinan Du, Jingfeng Yao +7
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However…