Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-29 with 1 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Jiacheng Lu et al. |
| Year | 2026 |
| HF Upvotes | 1 |
| arXiv | 2605.31158 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps. We present Light Interaction, a training-free inference acceleration framework for interactive video world models. Our key insight is that interaction naturally enables trajectory-dependent adaptive computation: retrieved spatial memory can be discarded during novel exploration, temporal context can be adjusted according to local latent dynamics, and early-step model outputs can be reused when the camera revisits familiar regions. Based on this insight, Light Interaction combines adaptive context management, denoising cache acceleration, and hardware-software co-designed 3D block sparse attention with fused Triton kernels. Evaluated on HY-WorldPlay and Matrix-Game-3.0, Light Interaction achieves up to 2.59x speedup without model retraining while maintaining competitive visual quality.
Engineering Breakdown
The Problem
However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps.
The Approach
We present Light Interaction, a training-free inference acceleration framework for interactive video world models.
Key Results
Evaluated on HY-WorldPlay and Matrix-Game-3.0, Light Interaction achieves up to 2.59x speedup without model retraining while maintaining competitive visual quality.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Interaction
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::