9 papers
Scaling Unified Multimodal Models to Long-Horizon Interleaved Generation
Ziqiao Peng, Yutao Cui, Wang Lin +12
Unified multimodal models (UMMs) provide an interface for interleaved text-image generation, where generated visual states can directly inform subsequent reasoning and synthesis. H…
HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
Xuerui Qiu, Yutao Cui, Guozhen Zhang +10
Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for gener…
Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
Youliang Zhang, Zhengguang Zhou, Zhentao Yu +11
Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task…
ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars
Ziqiao Peng, Yi Chen, Yifeng Ma +10
Despite significant advances in talking avatar generation, existing methods face critical challenges: insufficient text-following capability for diverse actions, lack of temporal a…
StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
Zhiyao Sun, Ziqiao Peng, Yifeng Ma +8
Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remar…
Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy
Teng Hu, Zhentao Yu, Guozhen Zhang +6
The synthesis of synchronized audio-visual content is a key challenge in generative AI, with open-source models facing challenges in robust audio-video alignment. Our analysis reve…
Video Generation Models Are Good Latent Reward Models
Xiaoyue Mi, Wenqing Yu, Jiesong Lian +9
Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges.…
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
Guozhen Zhang, Zixiang Zhou, Teng Hu +6
Due to the lack of effective cross-modal modeling, existing open-source audio-video generation methods often exhibit compromised lip synchronization and insufficient semantic consi…
Pack and Force Your Memory: Long-form and Consistent Video Generation
Xiaofei Wu, Guozhen Zhang, Zhiyong Xu +3
Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To ad…