4 papers indexed
Mingyu Wang, Weilin Jin, Wenbo Li, Haoyang Huang, Nan Duan, Tong Jia, et al.
Despite remarkable progress in vision-language generation, Vision-Language Models (VLMs) remain prone to hallucinations, producing content that is inconsistent with or unsupported by the input image. Existing works largely design detection or mitigation methods around one specifi…
Yong Liu, Xiaolong Fu, Zihang Xu, Wen Xue, Xueheng Li, Lin Song, et al.
We present Oxygen-TryOn, a unified foundation model for any-item virtual try-on. Rather than repurposing a general-purpose image editor, Oxygen-TryOn is fashion-native, built for try-on through a dedicated data engine and try-on-specific training. Given one or more reference item…
Junhao Zhuang, Shiyi Zhang, Yuxuan Bian, Yaowei Li, Yawen Luo, Yijun Liu, et al.
Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-truth video contexts. This reduces exposure bias, but the historical key-value cache is still used by f…
Chuyang Zhao, Yifei Song, Hongfa Wang, Jianlong Yuan, Yuan Zhang, Siming Fu, et al.
We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching models. Rather than performing velocity regression in the conventional VAE latent space, PFM supervises flow matching in a perceptual feature space using pretraine…