One-step cloud prediction with on-device decoding and regeneration after a control change.
The same input image and seed, with scripted control changes every six seconds that are not provided to the cloud in advance. The hexagon strip shows which model generated each 0.75-s chunk of the HIVE video.
Interactive video world models let users explore generated environments, empowering applications from games to robotics. To achieve good quality, video world models often need to run on cloud GPUs, which can be costly for model deployers. Cloud deployment can also lead to higher response latency. A small on-device model can respond locally, but it loses details and drifts over long rollouts. Motivated by the complementary strengths of cloud and edge computing, we study how to deploy a video world model across heterogeneous edge devices and cloud GPUs. Heterogeneous deployment is challenging because additional cloud computation can improve video quality but increases serving cost and can delay responses to user inputs. We present HIVE, a method that combines one-step cloud prediction with on-device decoding and regeneration after a control change. HIVE achieves judged video quality close to that of the four-step cloud model. Compared with four-step cloud-only generation, it achieves 2.9× the throughput and uses 65% less cloud GPU energy per second of generated video.
A chunk is a short group of video frames conditioned on the preceding video and a control input, such as a movement direction or no movement. Denoising steps predict a clean video latent from a noisy input. HIVE combines one-step cloud lookahead with local decoding and four-step regeneration when the control input changes. Both pretrained models retain their weights.
cloud
device
cloudWhile the current chunk is displayed, the cloud predicts the next chunk assuming the control input persists. It sends the x0 prediction from its first denoising step. The device’s VAE decoder converts this clean-latent estimate into frames, so the cloud does not run the decoder.
If the control input changes, the device discards the prediction made under the previous input. Its small model regenerates the chunk with all four denoising steps under the new input, without waiting for a cloud response. A device that cannot run the small model at the playback rate retains only the decoder and leaves regeneration to the cloud.
Every displayed chunk enters both models’ generation histories, so the cloud continues from the regenerated chunk. More frequent control changes reduce the number of cloud predictions that can be reused. No cache tensor is transmitted between the models.
On 300 scenes sampled from WorldScore, HIVE scores 7.07 out of 10 under a Qwen3-VL-32B evaluator, compared with 7.09 for four-step cloud-only generation. Throughput rises from 7.3 to 21.2 FPS, while cloud GPU energy falls from 1,141 to 398 J per video second: 2.9× the throughput and 65% less cloud energy.
Every method receives the same input image, actions, and seed. Great Wall and Stylized forest are the two rollouts of the qualitative figure in the paper, chosen by the gap in the VLM drift score: the device model, Hybrid SD, and SDVG lose the wall and the stylized trees, whereas the cloud model and HIVE keep both scenes to the end. EC-Diff, which is not in that figure, keeps the wall but not the stylized trees. Lake and Alley in the rain are two further scenes of the 20-scene set.
Sixteen scenes of the 20-scene evaluation set, seed 1234, without further selection (the four block-world game openings are left out). Hover over a scene for a preview of HIVE, click it to compare.
The device generates chunks that cannot arrive from the cloud. With cloud messages withheld for 20 s, playback stalls for 0.29 s per clip, compared with 19.33 s without the device model. This is an injected outage test of playback continuity, not a wide-area deployment or a measurement of video quality during the outage.
We vary cloud sampling depth, device computation, and generation history. On LingBot-World, the one-step 14B model scores 7.03 against 7.09 for four steps and 6.49 for the four-step 1.3B model. On the 20-scene analysis set, the small model’s regenerated chunks are sharper with cloud-generated history than when it generates the rollout alone. We use one cloud step for LingBot-World and the small model for regeneration after control changes.
HIVE applied unchanged to Self-Forcing 1.3B on the device and Krea Realtime 14B in the cloud, both based on Wan2.1, with text prompts as actions that switch four times per rollout without being announced. This pair runs below real time in our implementation, so it tests the quality, not the runtime.