WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models
cs.CV
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 27 pages, 10 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
- WorldScore: A Unified Evaluation Benchmark for World Generation
- LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
- Infinite Worlds with Versatile Interactions
- ViPE: Video Pose Engine for 3D Geometric Perception
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- MUSIQ: Multi-scale Image Quality Transformer
- WorldModelBench: Judging Video Generation Models As World Models
- Depth Anything 3: Recovering the Visual Space from Any Views
- Current World Models Lack a Persistent State Core
- Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models
- Yume: An Interactive World Generation Model
- DINOv2: Learning Robust Visual Features without Supervision
- Learning Transferable Visual Models From Natural Language Supervision
- WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- DreamX-World 1.0: A General-Purpose Interactive World Model
- Advancing Open-source World Models
- Towards Accurate Generative Models of Video: A New Metric & Challenges
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models