11 papers
REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
Hang Xu, Guohui Zhang, Xiaoxiao Ma +7
Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter…
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Yicheng Xiao, Wenxun Dai, Xinran Qin +22
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present…
AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory
Hang Xu, Xiaoxiao Ma, Guohui Zhang +7
Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps. While existing resea…
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
Guohui Zhang, XiaoXiao Ma, Jie Huang +9
Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synch…
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Tianfei Ren, Zhipeng Yan, Yiming Zhao +13
While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked a…
RAE-AR: Taming Autoregressive Models with Representation Autoencoders
Hu Yu, Hang Xu, Jie Huang +4
The latent space of generative modeling is long dominated by the VAE encoder. The latents from the pretrained representation encoders (e.g., DINO, SigLIP, MAE) are previously consi…
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…
Highly Efficient Test-Time Scaling for T2I Diffusion Models with Text Embedding Perturbation
Hang Xu, Linjiang Huang, Feng Zhao
Test-time scaling (TTS) aims to achieve better results by increasing random sampling and evaluating samples based on rules and metrics. However, in text-to-image(T2I) diffusion mod…
FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward Signal
Hang Xu, Linjiang Huang, Feng Zhao
Test-time scaling (TTS) has become a prevalent technique in image generation, significantly boosting output quality by expanding the number of parallel samples and filtering them u…
FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
Hang Xu, Jie Huang, Linjiang Huang +3
Domain Adaptation(DA) for dense prediction tasks is an important topic, which enhances the dense prediction model's performance when tested on its unseen domain. Recently, with the…
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution
Hang Xu, Wei Yu, Jiangtong Tan +2
Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous meth…