Similar Items: Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
- MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
- Generative Motion In-betweening by Diffusion over Continuous Implicit Representations
- Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
- MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
- PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation
- LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR