Similar Items: Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization
- Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation
- Computer-Aided Design Generation by Cascaded Discrete Diffusion Model
- DVD: Discrete Voxel Diffusion for 3D Generation and Editing
- ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
- MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation
- UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors