Programmable World Model
cs.CV
Submitted: 2026-09-09
Updated: 2026-10-13
Code: https://github.com/AlayaLab/pwm
Project page: https://alaya-lab.github.io/pwm
Terminology
Sources
- Qwen3-VL Technical Report
- Infinite Worlds with Versatile Interactions
- Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes
- LTX-Video: Realtime Video Latent Diffusion
- ViPE: Video Pose Engine for 3D Geometric Perception
- Generative World Renderer
- Yume: An Interactive World Generation Model
- WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
- Advancing Open-source World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
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