Publications (17)
Unmasking Bias in Diffusion Model Training
Hu Yu, Li Shen, Jie Huang +2
Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling.…
VideoMAR: Autoregressive Video Generatio with Continuous Tokens
Hu Yu, Biao Gong, Hangjie Yuan +5
Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored…
SynBoost: A Synergistic Framework for Fast Sampling of Diffusion Models
Hu Yu, Hao Luo, Fan Wang +3
Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation. However, their iterative sampling mechanism results in slow inference speeds. While…
MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
Guohui Zhang, Hu Yu, Xiaoxiao Ma +3
Reinforcement learning (RL) has demonstrated significant potential for post-training language models and autoregressive visual generative models, but adapting RL to masked generati…
Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction
Inclusion AI, Biao Gong, Cheng Zou +14
We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifyi…
Source-Free Domain Adaptation for Real-world Image Dehazing
Hu Yu, Jie Huang, Yajing Liu +3
Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images…