- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents a self-corrective autoregressive world model for efficient long-horizon driving video generation. The method introduces Scheduled Rollout Recovery (SRR) to improve the teacher model's robustness against accumulated autoregressive errors, and Teacher Rollout DMD (TRD) to distill long-horizon generation capabilities into an efficient student model. Experiments on nuScenes and an in-house driving dataset demonstrate improvements in video generation quality and temporal consistency over existing streaming video generation methods.
Critical strengths
The paper addresses error accumulation and temporal inconsistency in long-horizon autoregressive world models, which are important challenges for autonomous driving simulation. The teacher-side recovery strategy provides an interesting perspective on stabilizing autoregressive generation before distillation. The method achieves competitive FID/FVD results against existing approaches, with relatively fair comparisons using a shared backbone and supporting ablation studies.
Critical weaknesses
- Limited Novelty: The proposed SRR and TRD mainly extend existing self-forcing, recovery training, and diffusion distillation techniques. The individual contributions of the SRR components are not sufficiently validated.
- Insufficient Long-horizon Evaluation: Quantitative evaluation mainly covers approximately 20-second sequences, while minute-level demonstrations are largely qualitative. Long-term error accumulation and physical consistency remain insufficiently investigated.
Questions for authors
See the "Weaknesses"
4 comments
Response to Reviewer JnAe (Part 2/2)
[W2] Long-horizon evaluation and consistency
a. Additional one-minute quantitative evaluation
We additionally evaluated the existing models, trained with 20-second rollouts, on 100 one-minute videos from our internal dataset:
| Method | FID ↓ | FVD ↓ | ARE ↓ | DTW ↓ |
|---|---|---|---|---|
| Self-Forcing | 189.48 | 1534.20 | 8.48 | 17.01 |
| Self-Forcing++ | 200.40 | 1369.73 | 12.03 | 18.43 |
| LongLive | 96.64 | 792.29 | 6.42 | 9.97 |
| HorizonDrive | 19.21 | 188.83 | 3.06 | 3.73 |
In the one-minute generation setting, HorizonDrive outperforms the compared methods on all four metrics: FID, FVD, ARE, and DTW. These results extend minute-scale validation from qualitative demonstrations to quantitative evaluation, supporting the visual quality of long-horizon generation and providing additional evidence of spatial consistency through lower ARE and DTW.
b. Chunk-wise evaluation: does error accumulate over generation time?
To illustrate long-horizon error accumulation, Figure 6 shows how chunk FID changes with generated video length. The values are:
| Method | 10 s | 20 s | 30 s | 40 s | 50 s | 60 s |
|---|---|---|---|---|---|---|
| LongLive | 30.89 | 45.73 | 58.51 | 64.45 | 69.39 | 73.33 |
| HorizonDrive w/o SRR | 20.72 | 24.91 | 28.98 | 31.49 | 33.32 | 34.99 |
| HorizonDrive | 18.11 | 17.40 | 18.00 | 19.33 | 19.45 | 19.88 |
HorizonDrive maintains low and stable chunk FID throughout the one-minute rollout, whereas the chunk FID of LongLive and HorizonDrive w/o SRR increases over time. These results support that, through the combined optimization of SRR and TRD, HorizonDrive maintains stable visual quality beyond the 211-frame training horizon.
References
[1] W. Li et al. Stable Video Infinity: Infinite-Length Video Generation with Error Recycling. ICLR, 2026.
Follow-up Response to Reviewer JnAe
Thank you again for your helpful feedback. We wanted to follow up on our response and see if you have any remaining questions or concerns. We’d be happy to clarify any points.
Follow-up on Novelty and SRR Validation
As the discussion deadline approaches, we would be grateful for your thoughts on the technical comparisons, SRR component ablations, and one-minute quantitative results presented in our rebuttal. If concerns remain about novelty or component validation, it would be helpful to know which specific aspects require further clarification so that we can address them. Thank you for your time and consideration.
Response to Reviewer JnAe (Part 1/2)
We thank the reviewer for recognizing the importance of error accumulation and the teacher-side recovery perspective. We clarify the methodological contribution and point to the component-level and longer-horizon evidence below.
[W1] Novelty and the contributions of the SRR components
a. Differences from existing long-video frameworks
(1) Compared with forcing methods such as Self-Forcing++ and LongLive, the distinction is whether the teacher also undergoes targeted recovery training. These methods primarily optimize long-horizon generation by the few-step student. HorizonDrive first uses SRR to strengthen the teacher's correction capability on degraded histories and then distills the student, rather than requiring only the student to adapt to accumulated errors without improving the teacher's guidance under those histories.
(2) Compared with recovery training methods such as SVI, SRR differs in its error source and intended application. SVI resamples and injects errors from an error bank. SRR instead uses degraded histories that actually accumulate during the teacher's continuous long-horizon rollouts, training the teacher to recover from semantic errors while preserving trajectory continuity, and then using the enhanced teacher for few-step student distillation.
HorizonDrive therefore contributes two successive technical designs: SRR strengthens teacher recovery on degraded histories while preserving semantic fidelity and trajectory continuity; TRD combines the enhanced teacher with CFG scheduling to reliably transfer its long-horizon capabilities to a few-step student.
The systematic evaluation further validates the practical value of this design. HorizonDrive achieves FID/FVD/ARE/DTW of 13.82/92.99/2.60/3.27, outperforming both Self-Forcing++ (28.84/147.57/3.78/3.61) and LongLive (29.05/161.41/3.28/3.65) across all four metrics. We believe these methods and experiments together reveal an important optimization direction that prior work has underexplored: providing the student with a teacher capable of long-horizon generation.
b. SRR's internal design and comparison with existing recovery methods
Are both curricula in SRR important?Table 3 further validates the two curricula. Under the same uniform boundary sampling, replacing the fixed transition radius w=4 with a progressively increasing radius w:0→8 reduces FID/FVD from 16.20/132.51 to 15.52/103.02, while also improving the geometric metrics. Adding boundary sampling decay further reduces FID/FVD to 13.73/94.84 and ARE/DTW from 2.05/3.16 to 1.95/2.99, showing that both curricula provide additional benefits.Does SRR offer advantages over existing recovery training methods?Table 8 directly compares SRR with Stable Video Infinity (SVI) [1] under the same teacher architecture, initialization, data, and training budget. SRR achieves FID/FVD of 13.73/94.84, compared with SVI's 25.39/173.98, and reduces ARE/DTW from 2.61/3.31 to 1.95/2.99. These results show that, under this driving-generation setting, SRR achieves better visual quality and geometric consistency than the existing recovery training method.c. SRR's contribution to student distillation and long-horizon stability
Table 4 fixes the TRD settings and student initialization. Replacing only the Base teacher with the SRR teacher reduces FID/FVD from 19.24/141.88 to 14.44/107.54; initializing both the teacher and student from SRR further reduces them to 13.82/92.99. These results demonstrate SRR's contribution to the quality of student distillation.
The minute-scale chunk-FID curves in Figure 6 further show that full HorizonDrive exhibits slower visual-quality degradation than the variant without SRR and remains relatively stable beyond the training horizon, supporting SRR's contribution to stable long-horizon generation.