Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware

arXiv:2609.37107 · cs.CV, cs.HC · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.HC

Submitted: 2026-09-29

Updated: 2026-09-30

Code: https://github.com/madebyollin/taehv

Terminology

• World Model — 19× in this paper · explained in 7 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Distillation — 13× in this paper · explained in 2 episodes
• KV cache — 7× in this paper · explained in 3 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Grouped Query Attention — 2× in this paper
• Latent Space — 2× in this paper · explained in 7 episodes
• Prompt Adherence — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Adversarial Prompting — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• COMBAT: Conditional World Models for Behavioral Agent Training
• SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
• LTX-Video: Realtime Video Latent Diffusion
• Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
• NorMuon: Making Muon more efficient and scalable
• Cosmos 3: Omnimodal World Models for Physical AI
• Solaris: Building a Multiplayer Video World Model in Minecraft
• DreamX-World 1.0: A General-Purpose Interactive World Model
• Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
• Wan: Open and Advanced Large-Scale Video Generative Models
• SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

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