- Rating
- 2
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper focuses on the problem that RL post-training for video generation is almost always done at a single fixed length. Based on the Length-Scale Inconsistency phenomenon, it proposes LA-Framework, which has two parts. The first is length-conditioned timestep credit assignment, which uses a hand-designed length prior combined with reward sensitivity estimated through sparse branching over shared prefixes to build timestep weights for each length. The second is multi-length joint training, which normalizes advantages within groups that share the same prompt and the same length. The authors verify cross-length consistency on Wan2.1-1.3B and CogVideoX-2B and compare against Flow-GRPO, DanceGRPO, and DDRL. LA-Framework basically reaches SOTA results on VBench and VideoScore.
Critical strengths
- Existing video RL methods are almost all trained at a fixed length, but real deployment needs to support many different durations. This problem has barely been studied before, so it can give the video RL community a new perspective, and it also has real practical value.
- LA-Framework normalizes by length group and uses timestep weights that are calibrated offline just once. This adds almost no training cost and can be dropped straight into existing GRPO-style frameworks, so it's very portable.
- The authors use 5 proxy rewards, 9 metrics, standardized effect sizes, FDR correction and other tools to quantitatively analyze the flaws of fixed-length RL. This is convincing enough, and the evidence for the phenomenon analysis is solid. The experiments are also fairly complete.
Critical weaknesses
- Appendix D says the fully uniform variant is equivalent to the fixed-length baseline, which doesn't seem to hold up logically. Because of this, the necessity of length-conditioned credit assignment is questionable.
- Fig. 3 shows that after short-video training, subject consistency, motion smoothness, and dynamic degree are positive under most rewards. This somewhat conflicts with the "flat or even negative" claim in the main text (L363). It doesn't seem consistent with the core premise of LA-Framework, or put another way, the authors overstate the flaws of short-video training.
- Table 3 states that the length pool is {29, 49, 81}, while the model in Table 5 uses the {25, 33, 49} pool and is only evaluated at 49 frames. These two experiments seem to have different configurations, yet the 4 metrics reported for LA-Framework (full) in Table 3 (90.92 / 94.95 / 77.85 / 80.82) match the corresponding columns in Table 5 exactly. This result is confusing.
Questions for authors
- The four metrics of LA-Framework (full) in Table 3 are exactly the same as the Wan2.1-Ours results in Table 5, but the two places state different training length pools. Do these two sets of results come from the same model? If so, which length pool was actually used?
- Are there results for the baselines trained on the same length pool? This is key to judging whether length-conditioned credit assignment makes an independent contribution.
- Fig. 3 shows that motion-related metrics mostly improve after short-video training. What is the concrete basis for the conclusion that "short videos have static hacking"? Is there direct quantitative evidence for it?
- In Fig. 3, are the fixed-length models (33f / 81f) evaluated at their own training lengths or at a common length? Why doesn't Sec. 4.3 directly compare the unified model with the fixed-length models in the same set of figures, at the same held-out lengths (33f / 57f)?
4 comments
Response to Reviewer aNsa (Part2)
W2 & Q3: Fig. 3 shows positive motion-related effects after short-video training; is the flaw of short-video training overstated, and what is the basis for "static hacking" in short videos?
A2: (1). We did not intend to overstate the flaws of short-video training. Our claim concerns the direction of the effects rather than their sign alone: under the same reward, short-video and long-video training change quality along different dimensions. Models trained with different reward functions differ in which aspects of video quality they improve, i.e., the hacking dimensions differ; and for a fixed reward function, short and long videos hack along very different dimensions. Multi-length joint training compresses these deviations. We also agree with the reviewer that the short-video deviations are milder; Appendix B states explicitly that short-video training yields mild deviations (below 0.3 SD), whereas long-video training frequently exceeds −0.3 SD.
(2). Whether an effect after short-video training is positive or negative depends on the reward function. When an evaluation dimension is close in nature to what the reward function favors, the effect is often a positive gain, while other dimensions may be harmed. For example, under the HPS-Score reward, short-video training degrades text–video alignment (Appendix B, Fig. 5) and motion smoothness (−0.08 in Fig. 3), whereas under PickScore and CLIP-Score it improves both.
(3). Importantly, positive subject consistency and motion smoothness after short-video training are not evidence against static hacking; they are partly its consequence. A clip with less motion is trivially smoother and more self-consistent, so these metrics can be inflated by suppressing motion, as noted in Appendix B ("a short clip can inflate smoothness by suppressing motion while a long video cannot avoid genuine motion"). The VideoScore dynamic-degree score is a judged score and is only weakly sensitive to this. To provide direct quantitative evidence, we measure the motion and appearance of the generated videos independently of all reward models and benchmarks (Wan2.1, VideoAlign reward):
| Indicator | Base 33f | Short-RL 33f | LA-Framework 33f | Base 81f | Long-RL 81f | LA-Framework 81f |
|---|---|---|---|---|---|---|
| Color saturation, static hacking ↑ | 0.412 | 0.486 | 0.425 | 0.405 | 0.418 | 0.417 |
| Warping error (×10⁻³), temporal hacking↑ | 6.8 | 5.9 | 6.5 | 7.4 | 10.3 | 7.2 |
Short-video training increases color saturation by 18%, while its warping error decreases: the video moves less and becomes more saturated, which is precisely what raises smoothness and consistency scores. This is the direct evidence for static hacking. The unified model keeps both indicators close to the base model.
(4). We agree that the sentence at L363 ("motion-related metrics remain flat or even negative") does not accurately describe Fig. 3. We revise it to state that, under short-video training, the motion-related gains concentrate on smoothness and consistency, which can be inflated by reduced motion, as shown by the decrease in optical-flow magnitude.
W3 & Q1: Table 3 and Table 5 report identical metrics but different length pools.
A3: We apologize for the typo in the description of the ablation setting in Appendix D. The ablation in Table 3 actually uses the length pool {25, 33, 49}, the same configuration as the comparison in Table 5, and the four absolute scores of LA-Framework (full) in Table 3 come from the same model as the Wan2.1 results in Table 5, evaluated at 49 frames. The cross-length spread column is computed between the 29- and 49-frame evaluations of each variant. We have corrected the description of Table 3 and the text of Appendix D.
Q4: Evaluation lengths in Fig. 3
A4:
(1). In Fig. 3, the fixed-length models (33f and 81f) are each evaluated at their own training length, so as to characterize the behavior of fixed-length RL in its own regime.
(2) In Sec. 4.3, in addition to evaluating the unified model at the same lengths as Fig. 3 (33 and 81 frames), we add an evaluation at 57 frames. Both 33 and 57 frames are held out from the unified model's training pool {29, 49, 81}, so they test generalization to interpolated lengths and give a more complete picture of cross-length consistency.
Thank you again for your valuable suggestions. We value the opportunity to discuss our work with the research community and welcome any further questions or comments.
Thank you for the comments. My concerns are addressed. I keep my score unchanged.
This is a polite inquiry.
Hi Reviewer aNsa,
Thank you very much for your prompt response. We would greatly appreciate it if you could further elaborate on any remaining concerns that may still prevent the paper from meeting the ICLR acceptance standards. This would help us better understand your perspective and provide additional clarification or evidence if needed.
Thank you again for your time and valuable feedback.
Response to Reviewer aNsa (Part1)
We really appreciate your time and insightful comments. Thank you so much for acknowledging notable performance gain and detailed analysis of our work. The response to your concerns are summarized as follows.
W1 & Q2: The statement that the fully uniform variant is equivalent to the fixed-length baseline; baselines trained on the same length pool.
A1: (1). We thank the reviewer for pointing this out, and we agree that the statement in Appendix D is imprecise. Under our multi-length joint training, the fully uniform variant (W ≡ 1) still uses the length pool, the prompt–length groups and within-group normalization, so it is not equivalent to a fixed-length baseline; it is a multi-length GRPO baseline with uniform timestep weights. We have corrected this statement.
(2). We did not include such a baseline because there is no established recipe for directly training GRPO on multiple video lengths: videos of different lengths have intrinsically different reward distributions, so the standard GRPO procedure cannot simply be applied to a mixed-length batch. Pooled normalization lets the length with the largest reward magnitude dominate the gradient, which is reflected in our ablation without within-group normalization (cross-length spread 0.183 vs. 0.087, Table 3). Our multi-length joint training paradigm addresses this through prompt–length groups, within-group normalization (Eq. 6) and balanced sampling across lengths.
(3). To answer whether length-conditioned credit assignment makes an independent contribution, we train exactly this baseline, i.e., the fully uniform variant on the same length pool, with the same grouping, normalization and reward. Results on Wan2.1-1.3B with the VideoAlign reward:
The uniform-weight baseline benefits from multi-length training, but the full method outperforms it on every metric at both lengths, with the largest margins on dynamic degree and factual consistency at 49 frames. This shows that the length-conditioned credit assignment makes an independent contribution beyond training on the same length pool.