Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

arXiv:2609.17909 · cs.CV, cs.LG · Submitted 2026-09-15 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: 19 pages, 8 figures. Authors listed alphabetically by surname. Project: https://zing.loopit.me/ ; Code: https://github.com/seedleap/zing-world-model ; Models: https://huggingface.co/seedleap/zing-0.5 ; Serving: https://github.com/seedleap/Zing-SGLang

Code: https://github.com/seedleap/zing-world-model

Project page: https://meituan-longcat.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 30× in this paper · explained in 2 episodes
• Consistency — 18× in this paper · explained in 3 episodes
• World Model — 17× in this paper · explained in 7 episodes
• Adaptation — 12× in this paper · explained in 1 episode
• Consistency Distillation — 7× in this paper · explained in 2 episodes
• Distribution Matching — 7× in this paper · explained in 2 episodes
• KV cache — 5× in this paper · explained in 3 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Data-Forcing Distillation — 3× in this paper
• Embeddings — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes

Sources

• GameGen-X: Interactive Open-world Game Video Generation
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• H3-World: Turning Language Understanding into World Control
• Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
• LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
• Infinite Worlds with Versatile Interactions
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation
• Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
• Classifier-Free Diffusion Guidance
• CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
• DisCo: World Models with Discrete Camera Motion Control
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
• Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
• Flow Matching for Generative Modeling
• Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
• CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
• WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
• Advancing Open-source World Models

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