GeoFlip Preview: Benchmarking Geometry-Sensitive Physics in Video Generation
cs.CV
Submitted: 2026-10-30
Updated: 2026-11-04
Comments: 14 pages, 7 figures
Code: https://github.com/SkyworkAI/SkyReels-V1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
- SkyReels-V2: Infinite-length Film Generative Model
- LTX-Video: Realtime Video Latent Diffusion
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- A Plausible Future Is Not a Causal Future: Can Video Models Generate How the World Unfolds?
- Advancing Open-source World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- HunyuanVideo 1.5 Technical Report
- A Very Big Video Reasoning Suite
- Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
- FutureWorlds: Learning Robotic World Models from Alternative Futures
- Remembering What Matters for Long-Horizon Robotic World Models
- I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models
- Thinking in Video: Can Video Generators Really Reason About the Real World?
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment
- Efficient All-in-One Weather Restoration using Spectral Harmonization
- Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment