8 papers
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
Hongyuan Liu, Qinli Yang, Wen Li +6
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the m…
Bidirectional Sparse Attention for Faster Video Diffusion Training
Chenlu Zhan, Wen Li, Chuyu Shen +3
Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic com…
Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
Jie Du, Xinyu Gong, Qingshan Tan +7
Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largel…
LGCC: Enhancing Flow Matching Based Text-Guided Image Editing with Local Gaussian Coupling and Context Consistency
Fangbing Liu, Pengfei Duan, Wen Li +1
Recent advancements have demonstrated the great potential of flow matching-based Multimodal Large Language Models (MLLMs) in image editing. However, state-of-the-art works like BAG…
Ovis2.5 Technical Report
Shiyin Lu, Yang Li, Yu Xia +39
We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer…
Text-Driven Voice Conversion via Latent State-Space Modeling
Wen Li, Sofia Martinez, Priyanka Shah
Text-driven voice conversion allows customization of speaker characteristics and prosodic elements using textual descriptions. However, most existing methods rely heavily on direct…