- Rating
- 4
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper introduces WorldPlay2, an interactive video world model that supports both navigation and semantic events while maintaining consistency over longer rollouts. It separates low-level actions from text descriptions of the scene, character, and event to make the controls easier to learn. Historical video is compressed into memory tokens used by both the student and teacher, allowing the teacher to evaluate shorter clips without processing the full rollout at once. The authors also introduce Stable Forcing, which uses PDD for few-step initialization, then runs complete student rollouts and replays selected denoising steps for gradient updates. The main contribution is how the memory and distillation procedures work together to make long-rollout training more efficient and stable. Results on WBench, RevisitBench, and interaction tests show improvements in control and consistency, with streaming generation reaching 16 FPS on eight H20 GPUs.
Critical strengths
-
The combination of compressed memory and Stable Forcing is a strong part of the paper. The memory design makes long histories cheaper to use during both generation and teacher evaluation, while the distillation procedure helps preserve quality over longer rollouts. The revisit results and qualitative examples provide encouraging evidence that this combination improves long-term consistency. This addresses a practical difficulty in current world models and is my main reason for viewing the work positively.
-
The engineering work also looks solid. The paper brings together a multi-stage training pipeline, caching, quantization, and a lightweight VAE, and provides a latency breakdown for the resulting streaming system. The reported 16 FPS on eight H20 GPUs supports its practical value. The examples shown in the paper look good, and the method and training workflow are explained clearly, making the overall contribution easy to follow.
Critical weaknesses
-
Could the authors provide the model, training, and evaluation settings, including the base model and its size, output resolution, training parameters for each stage, and inference sampling settings? Are there plans to release the training and evaluation pipelines and datasets? If some parts cannot be shared, please clarify what will be available for reproducing the results.
-
Which VLM version was used for the interaction evaluation, and what were the evaluation settings, including video sampling, model parameters, and score aggregation? Have the authors evaluated the same samples with other VLMs to check whether the reported gains and model rankings remain consistent? This would help show how sensitive the results are to the choice of evaluator.
Questions for authors
Please refer to the two questions in the Weaknesses section.
3 comments
Thank you for the detailed response and additional experiments. The clarified experimental settings and the evaluation using a second VLM have addressed my main concerns. Overall, I consider this a solid piece of work and appreciate the authors’ efforts to strengthen the paper.
We sincerely thank you for the review and the suggestions.
Best regards,
Authors
Rebuttal for Reviewer MUJa (Part 1)
We sincerely thank the reviewer for the positive feedback on our work and the valuable comments. Below, we address your concerns point by point:
Our base model is Wan2.2-A14B with a resolution of 448×832, and the detailed training configurations and inference settings are provided in Table 5 of the revised Appendix. Regarding open-sourcing, while the training dataset cannot be publicly released due to copyright restrictions, we will release the inference code, along with the model weights from each training stage, to support the reproduction of our results.
We use Doubao-Seed-2.1-Pro-260628 as our VLM evaluator, whose model parameters are not publicly disclosed as it is a proprietary model. For each video, we sample frames at 3 FPS, and the final score is computed by aggregating the scores across the two dimensions described in the Appendix, averaging them over all test samples, and finally normalizing the result to a 0–100 scale. To verify the sensitivity to different VLM evaluators, we also conduct an evaluation using Gemini-3.8-Flash under the same protocol. Although there are slight variations in the model rankings, the average scores still clearly demonstrate the superiority of our method.