video generation
Video generation involves creating realistic motion picture content using AI technologies, such as deep generative models. This includes generating entirely new videos or manipulating existing footage to create novel outcomes.
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals
- Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
- Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
- GeoVideo: Introducing Geometric Regularization into Video Generation Model
- Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
- Improving Video Generation with Human Feedback
- Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
- MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference
- MoCha: Towards Movie-Grade Talking Character Generation
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
- PlayerOne: Egocentric World Simulator
- PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
- Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
- Sekai: A Video Dataset towards World Exploration
- Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
- Show-o2: Improved Native Unified Multimodal Models
- Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
- Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
- Training-Free Efficient Video Generation via Dynamic Token Carving
- UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
- UniTransfer: Video Concept Transfer via Progressive Spatio-Temporal Decomposition
- Video Perception Models for 3D Scene Synthesis
- VideoMAR: Autoregressive Video Generation with Continuous Tokens
- WorldModelBench: Judging Video Generation Models As World Models