- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents TTT2Reel, an end-to-end test-time training framework for long video generation. The authors design an elegant implementation of test-time training for long video generation with LoRA and first-order model-agnostic meta-learning (FOMAML). An error replay mechanism is further proposed to mitigate error accumulation during autoregressive rollouts. Experimental results show that TTT2Reel outperforms several strong baselines after training on UltraVideo-Long, which consists of only 17k videos.
Critical strengths
The implementation of TTT in this paper is elegant and practical. Unlike common designs that insert a new TTT layer (instantiated via an MLP) or replace the pre-trained attention layers of DiT, the approach in this paper uses a lightweight LoRA module. Such a design protects the original performance of base models and delivers better generalizability than prior work (e.g., [1]). And the performance achieved is also impressive, especially the results for ultra-long (3-minute) video rollouts.
[1] Dalal K, Koceja D, Xu J, et al. One-minute video generation with test-time training[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2025: 17702-17711.
Critical weaknesses
-
The contribution of the proposed TTT memory is unclear, as the main performance gains appear to come from error replay and no direct evidence demonstrates improved long-range memory retention or retrieval.
-
The computational cost of end-to-end bilevel training is not reported, making the method’s practical efficiency and comparisons with other approaches difficult to assess.
Questions for authors
The experimental results do not fully support the authors’ claims. The reported VBench results and qualitative demonstrations primarily evaluate the visual quality of the generated videos. However, as stated in line 75, TTT2Reel is intended to address both the exposure-bias problem and the capacity problem by representing completed chunks with limited capacity.
The ablation results also leave the contribution of the TTT component unclear. Table 3 suggests that the gains in most visual-quality and consistency metrics are driven more by error replay than by test-time training. For example, removing error replay decreases Aesthetic Quality from 58.90 to 56.80 and Imaging Quality from 67.64 to 64.57, whereas removing test-time training decreases them to 57.90 and 66.12, respectively. Moreover, when end-to-end training and error replay are enabled, adding test-time training slightly decreases Subject Consistency and Background Consistency. As currently presented, the VBench metrics do not provide sufficient evidence for the effectiveness of TTT, since the prompts and camera motions appear relatively simple and may not necessarily require a memory mechanism like TTT.
The ablation also suggests that end-to-end training is important for the reported performance. However, the proposed bilevel training procedure may incur substantially higher training costs than the baselines used for comparison, which should be discussed to ensure a fair comparison.
I would appreciate it if the authors could address the following questions:
-
Could the authors provide direct evidence that the proposed memory can retain and retrieve information from early chunks over long horizons, rather than evaluating only the final video quality? If not, the authors may wish to soften the described contributions.
-
Could the authors report the average time per optimization step and the total GPU-hours?
-
Please provide metrics to measure anti-drifting performance in the ablation study, for example, by computing the difference between the VBench metrics of the last chunk and those of the first chunk.
5 comments
Cost-Benefit of TTT2Reel: Requesting a Controlled Long-Term Memory Benchmark
Thank the authors for the constructive response and for adding the qualitative examples. I agree that the astronaut and fox examples show some scene-revisitation ability, and I appreciate this effort.
However, a remaining concern is whether the additional training overhead is justified by the observed memory benefits. The current evaluation compares models under an equal number of optimization steps; however, given that TTT2Reel requires 91.2 seconds per step compared to 14.0 seconds for standard SFT (roughly a 6.5× increase), this comparison is not compute-matched. Under equivalent GPU-hours, SFT would accrue substantially more optimization steps. Consequently, it would be beneficial to provide either an SFT baseline trained under matched compute budgets (GPU-hours) or a targeted, controlled memory benchmark.
While a full compute-matched evaluation might be computationally demanding, a smaller-scale controlled experiment could still offer valuable insights. For instance, on a curated subset of approximately 16 video clips (each around 30 seconds) where a subject exits the frame for a sustained interval and later re-enters, one could compute the face-embedding cosine similarity (e.g., via ArcFace) between pre-departure and post-return frames. Isolating the memory benefit could be achieved by comparing full TTT with a non-TTT or sliding-window variant under comparable settings, alongside LongLive 2.0 and other TTT baselines if applicable. Reporting quantitative metrics, failure modes, and representative visualizations would significantly strengthen the evaluation. Furthermore, while the first-chunk flow-matching loss serves as a useful auxiliary signal for monitoring forgetting, it does not constitute a direct metric for long-term retrieval.
If such an analysis demonstrates a clear and statistically significant memory advantage, I would be pleased to raise my score. Otherwise, I encourage the authors to moderate their claims regarding long-term visual memory and reposition the core contribution primarily as an efficient LoRA-based TTT framework—a contribution whose value I continue to recognize.
We thank the reviewer for the constructive follow-up and the opportunity to further substantiate the benefits of TTT2Reel through compute-matched comparisons and controlled long-term memory evaluations.
(Q1) Comparison with standard SFT under matched compute budgets.
We thank the reviewer for highlighting the discrepancy in training compute. We agree that standard SFT can benefit from substantially more optimization steps under an equivalent compute budget. As requested, we additionally train the SFT baseline on 16 NVIDIA H100 GPUs for 7,300 steps, totaling 374.6 GPU-hours, closely matching the training cost of TTT2Reel (374.1 GPU-hours).
The following table shows that extended SFT improves video generation performance on most metrics, but still lags behind TTT2Reel across all 6 VBench-Long dimensions, which justifies the additional training overhead of our approach.
| H100 GPU Hours | Dynamic Degree ↑ | Aesthetic Quality ↑ | Imaging Quality ↑ | Subject Consistency ↑ | Background Consistency ↑ | Motion Smoothness ↑ | |
|---|---|---|---|---|---|---|---|
| SFT | 57.0 | 61.56±1.20 | 56.47±0.79 | 61.50±1.54 | 96.14±0.52 | 95.94±0.63 | 97.75±0.69 |
| Compute-matched SFT | 374.6 | 69.44±0.96 | 55.83±0.67 | 65.69±0.54 | 96.12±0.33 | 96.06±0.40 | 97.83±0.12 |
| TTT2Reel | 374.1 | 73.57±0.77 | 58.90±0.48 | 67.64±0.31 | 96.88±0.08 | 96.77±0.13 | 98.64±0.04 |
(Q2) A targeted, controlled memory benchmark
We thank the reviewer for suggesting this controlled memory benchmark. As requested, we design 16 prompt streams following the format of Table 7 (Appendix F.3), each featuring a human character with a clearly visible face who exits the scene for a sustained interval before re-entering. Using these prompts, we compare TTT2Reel against LongLive-2.0, two ablation variants, TTT2Reel-Static (without TTT) and TTT2Reel-Reset (resetting LoRA weights to their learned initialization after each chunk), and two TTT video methods, TTTVideo [1] and LaCT [2]. Note that TTTVideo and LaCT released code without training data or checkpoints. So we retrained both using their official implementations, but with our own training data.
Quantitative metrics. As requested, we report the cosine similarity between ArcFace embeddings of pre-departure and post-return frames, alongside an instruction-following metric that measures whether the generated video follows the intended sequence of events (the character enters, leaves, the scene remains empty, and the character returns). TTT2Reel achieves the highest scores on both metrics, demonstrating strong identity consistency and prompt adherence in scenarios requiring long-term visual memory.
| Methods | Cosine Similarity ↑ | Instruction Following (%) ↑ |
|---|---|---|
| LongLive-2.0 | 0.447±0.025 | 10.4±1.5 |
| TTT2Reel-Static | 0.332±0.038 | 78.1±2.6 |
| TTT2Reel-Reset | 0.341±0.043 | 75.0±2.6 |
| TTTVideo | 0.268±0.012 | 32.3±1.5 |
| LaCT | 0.243±0.009 | 38.5±1.5 |
| TTT2Reel | 0.632±0.015 | 87.5±2.6 |
Failure mode analysis. Although LongLive-2.0 attains the second-highest cosine similarity, it exhibits the lowest instruction-following rate (10.4%). Inspecting its videos shows that the main character rarely leaves the scene. Its high similarity therefore reflects a person who always stays in the scene rather than a face recalled after a sustained absence, so it does not indicate long-horizon visual memory. Both TTT2Reel-Static and TTT2Reel-Reset generally follow the prompt streams, but they often regenerate a different person instead of recalling the face since they lack long-term memory. TTTVideo and LaCT follow the prompt streams in only 32.3% and 38.5% of the examples, far below TTT2Reel’s 87.5%. In particular, TTTVideo often changes the character’s identity even before departure, while LaCT tends to collapse into flat, saturated colors after ~15 seconds.
Representative visualizations. We have expanded Appendix F.3 of the revised manuscript to include two representative examples (Figure 13), illustrating the advantages of TTT2Reel and the failure modes of baselines.
[1] Dalal, Karan, et al. "One-minute video generation with test-time training." 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2025.
[2] Zhang, Tianyuan, et al. "Test-time training done right." International Conference on Learning Representations. Vol. 2026. 2026.
We thank the reviewer for recognizing the elegance and practicality of our LoRA-based TTT framework, particularly its ability to preserve the pretrained backbone, as well as the strong performance demonstrated on long-video generation. We appreciate the constructive feedback and address the concerns below.
(W1 and Q1) Evidence of long-term visual memory retention and retrieval.
As requested, we additionally evaluate memory retention by measuring the flow-matching loss on the first chunk after successive LoRA updates, and add a control in which the first chunk is never memorized (Fig. 11, Appendix F.2). With memorization, the loss remains stable, with relative changes within 1.7%, while the control rises monotonically to +4.0%. The memorized curve stays below the control throughout, indicating that earlier visual information is preserved despite subsequent updates.
Qualitative examples in Fig. 12 (Appendix F.3) and on our demo page further demonstrate long-horizon visual memory retention and retrieval. Specifically, the astronaut example (One Minute Video Rollouts) shows Earth moving out of view and reappearing with the correct spatial relationship, while the fox example (Ultra-Long Video Rollouts) exhibits similar scene-revisitation behavior.
(W2 and Q2) Computational cost of bilevel training.
As requested, we additionally report the training cost of TTT2Reel, including average wall-clock time per optimization step and total GPU-hours. Training TTT2Reel at the 5B scale requires 91.2 seconds per step on 8 NVIDIA H100 GPUs (96GB) and 374 GPU-hours in total. For comparison, standard SFT that randomly crops a 5-second clip from each UltraVideo-Long video and trains for the same number of steps requires 14.0 seconds per step and 57 GPU-hours in total under the same hardware configuration. Although TTT2Reel introduces additional computational overhead during training, it achieves consistent performance gains across 6 dimensions on VBench-Long as shown in the table below, without increasing inference cost. In addition, training the 14B variant of TTT2Reel takes 381.9 seconds per optimization step on 16 NVIDIA H100 GPUs (96GB) and 683 GPU-hours in total.
(Q3) Anti-drifting performance.
As requested, we evaluate anti-drifting performance by measuring the absolute difference in VBench-Long metrics between the first and last video chunks. The results below (mean ± std) show that removing TTT, bilevel training, or the error replay strategy increases the gaps in most metrics. Notably, removing bilevel training leads to larger differences in visual quality and consistency metrics than removing the error replay, highlighting the importance of end-to-end meta-learning in mitigating long-horizon drift.
The effect of TTT on consistency metrics. We also observe that removing TTT produces more static videos, leading to higher subject and background consistency scores at the expense of motion dynamics, as demonstrated by the lower Dynamic Degree score in Table 3.