- Rating
- 2
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
NextGAN trains a scalar critic's feature-input gradient on displacements between independently paired reference and generated samples. The generator then ascends the potential at generated endpoints. The paper characterizes the population field and conditional feature-distribution matching, and evaluates regression and adversarial implementations of the critic objective. Experiments cover controlled mode coverage, one-step image generation, and adaptation of pretrained video generators using offline reference samples without online teacher score or trajectory queries.
Critical strengths
- Equations (2)–(6), Proposition 1, and Appendix C clearly explain why independent-pair supervision need not pull each generated sample directly toward an arbitrary reference sample. The paper distinguishes feature-distribution matching from full image matching and states the limits of its particle analysis and moving-corridor interpretation.
- The results show that the approach works across image and video settings. Latent one-step generation reaches 1.54 FID with regression and 1.36 with the adversarial form, and one 1.3B video model supports multiple sampling budgets. The objective and representer comparisons provide evidence beyond the main benchmark results.
Critical weaknesses
- I am not yet convinced that the paper establishes a substantial advance over its closest construction. TBSM v1 §2.5, Eq. (13), and Appendix E.5.3 already contain the conservative displacement construction and projection interpretation (TBSM). Its illustrative displacement algorithm queries the corridor; its deployed unit-bearing algorithm differs. NextGAN acknowledges the overlap (pp.2–3), but Figure 7/Appendix B does not describe the TBSM comparator well enough to identify which changes explain the improvement. Please separate inherited results from the added analysis and practical contribution, and specify the comparator's critic, target, estimator, and update. If endpoint querying is the main methodological advance, holding the critic construction fixed and changing only the query would be informative. Proposition 1 characterizes the field under the corridor measure; Appendix H.3 and Appendix I do not establish descent for the practical endpoint update. A matched comparison or restricted analysis could establish the value of this change; a well-documented system contribution is another route. I am not asking for general GAN convergence or for regression to outperform its equivalent adversarial estimator.
- I could not reconstruct the video training and evaluation setup from Sections 3.6/4.2 and Appendix A. They give backbone, LoRA, batch-size, feature-layer, and pooling details, but omit parts of the optimization schedule, rollout-length and noise-level sampling, potential-head configurations, and VBench version and prompt/seed protocol. Since video adaptation is a principal contribution, please provide the configurations for each model size and sampling budget. Please also specify normalization, penalty coefficients, and training budgets for the objective comparisons. As the paper notes on p.14, rescaling the objective does not ensure identical optimization under spectral normalization.
- The stability and ranking conclusions need more evidence. Table 2's 1.3B total-score margins are small: 80.80 versus 80.68 at one step and 83.13 versus 82.78 at two steps, without uncertainty estimates. The toy illustration uses seed 0 (Appendix E). The authors disclose per-budget best-completed-run selection at 14B and acknowledge its weaker total scores, but do not give the number of runs considered. Paired evaluation intervals, selection counts, and repeated lower-cost experiments would help distinguish stable gains from variation across runs. The stability claim could instead be limited to the observed runs; these questions do not require repeated full 14B training.
Questions for authors
- What are the new methodological, theoretical, and implementation contributions relative to the closest construction? Which TBSM variant does Figure 7 use, and what differs in its critic, target, estimator, regularization, and generator query? Can existing controlled evidence resolve these differences, or is a query-only comparison needed?
- Can you provide the complete video optimization, rollout/noise, potential-head, and VBench configurations, along with the settings used in the objective comparisons?
- How many runs/configurations were attempted and considered for each selected 14B result? Do paired evaluation intervals or repeated lower-cost experiments support the small 1.3B margins and the stability claim?
- Figure 7b shows gains from combining representers, but each also adds a potential head. What evidence separates complementary feature information from added head capacity? Section 3.6 notes that the video representers tended to favor static appearance over motion. Beyond this observation, what guidance do the existing comparisons offer for choosing representers, and what errors do the chosen features still miss?
- For the offline Wan2.1-14B reference data, what are the costs of data creation and storage, and of feature extraction during adaptation? Please distinguish costs incurred in this study from upstream costs of creating the public dataset. Do the available observations suggest which reference-data properties matter most? An accounting or discussion would suffice; a new real-video study is not needed.
6 comments
K2 Complete optimization and evaluation configurations
Reviewer comment W2
I could not reconstruct the video training and evaluation setup from Sections 3.6/4.2 and Appendix A. They give backbone, LoRA, batch-size, feature-layer, and pooling details, but omit parts of the optimization schedule, rollout-length and noise-level sampling, potential-head configurations, and VBench version and prompt/seed protocol. Since video adaptation is a principal contribution, please provide the configurations for each model size and sampling budget. Please also specify normalization, penalty coefficients, and training budgets for the objective comparisons. As the paper notes on p.14, rescaling the objective does not ensure identical optimization under spectral normalization.
Reviewer comment Q2
Can you provide the complete video optimization, rollout/noise, potential-head, and VBench configurations, along with the settings used in the objective comparisons?
Response. We have added the video settings in Appendix A.1 (Table 3). Both model sizes use 8,000 generator updates, AdamW with G/D learning rates 2 × 10⁻⁶/10⁻⁵, a 100-update warmup followed by constant rates, and D:G = 5:1. Global batch sizes are 32 and 16 for 1.3B and 14B. Potential heads have width 768, four blocks, and 12 attention heads. Rollout lengths cycle through 1–4 steps, with log-normal intermediate-noise sampling; only the final generator call is differentiated.
The same weights support 1/2/4 NFE with CFG = 1 and σ_max = 1600. VBench uses the original 16-dimension protocol, 944 fixed augmented prompts × five samples, 832 × 480 × 81 resolution, and 16 fps. We also specify the angle schedules, feature normalization, token/head reductions, spectral normalization, and the absence of video EMA. The ImageNet objective-comparison settings are listed in Response B3. We agree that an algebraic rescaling does not ensure identical optimization under spectral normalization.
K3 Uncertainty and run selection
Reviewer comment W3
The stability and ranking conclusions need more evidence. Table 2's 1.3B total-score margins are small: 80.80 versus 80.68 at one step and 83.13 versus 82.78 at two steps, without uncertainty estimates. The toy illustration uses seed 0 (Appendix E). The authors disclose per-budget best-completed-run selection at 14B and acknowledge its weaker total scores, but do not give the number of runs considered. Paired evaluation intervals, selection counts, and repeated lower-cost experiments would help distinguish stable gains from variation across runs. The stability claim could instead be limited to the observed runs; these questions do not require repeated full 14B training.
Reviewer comment Q3
How many runs/configurations were attempted and considered for each selected 14B result? Do paired evaluation intervals or repeated lower-cost experiments support the small 1.3B margins and the stability claim?
Response. We additionally analyze the new trained NextGAN 1.3B checkpoint (8K updates, EMA), distinct from the original Table 2 runs. We use 20,000 paired bootstrap resamples of the same 944 prompts, retaining five videos per prompt and recomputing the 16 VBench dimensions. Brackets give marginal 95% confidence intervals (CIs).
| NFE | Method | Total [95% CI] | Quality [95% CI] | Semantic [95% CI] |
|---|---|---|---|---|
| 1 | NextGAN | 81.579 [80.874, 82.284] | 82.508 [81.770, 83.240] | 77.863 [76.029, 79.679] |
| 1 | rCM | 80.678 [80.106, 81.246] | 81.762 [81.206, 82.299] | 76.343 [74.590, 78.098] |
| 1 | AnyFlow | 78.117 [77.451, 78.790] | 78.739 [78.099, 79.386] | 75.631 [73.626, 77.618] |
| 1 | Wan2.1 + DMD2 (bidirectional) | 78.612 [77.925, 79.311] | 80.301 [79.613, 80.992] | 71.855 [69.889, 73.794] |
| 2 | NextGAN | 82.769 [82.112, 83.427] | 83.571 [82.887, 84.243] | 79.564 [77.812, 81.297] |
| 2 | rCM | 81.884 [81.336, 82.426] | 82.607 [82.074, 83.118] | 78.993 [77.320, 80.649] |
| 2 | AnyFlow | 82.656 [81.995, 83.321] | 83.083 [82.385, 83.775] | 80.948 [79.229, 82.665] |
| 2 | Wan2.1 + DMD2 (bidirectional) | 82.778 [82.138, 83.405] | 84.083 [83.421, 84.712] | 77.560 [75.749, 79.387] |
Paired score differences (new NextGAN checkpoint − baseline):
| NFE | Baseline | Total difference [95% CI] | Quality difference [95% CI] | Semantic difference [95% CI] |
|---|---|---|---|---|
| 1 | rCM | +0.901 [0.376, 1.432] | +0.746 [0.156, 1.328] | +1.521 [0.350, 2.692] |
| 1 | AnyFlow | +3.462 [2.846, 4.073] | +3.770 [3.063, 4.463] | +2.232 [0.958, 3.509] |
| 1 | Wan2.1 + DMD2 (bidirectional) | +2.968 [2.335, 3.591] | +2.208 [1.510, 2.905] | +6.009 [4.615, 7.409] |
| 2 | rCM | +0.885 [0.343, 1.445] | +0.963 [0.334, 1.617] | +0.571 [−0.502, 1.638] |
| 2 | AnyFlow | +0.113 [−0.403, 0.656] | +0.488 [−0.109, 1.126] | −1.384 [−2.438, −0.369] |
| 2 | Wan2.1 + DMD2 (bidirectional) | −0.009 [−0.582, 0.583] | −0.512 [−1.164, 0.165] | +2.004 [0.844, 3.180] |
At one step, total, quality, and semantic scores exceed all three baselines with CIs excluding zero. At two steps, total and quality exceed rCM; semantic is lower than AnyFlow and higher than DMD2. Other two-step differences remain unresolved. These intervals are conditional on the archived evaluations and do not cover training-run variability or model selection; no multiplicity correction is applied. Full historical baseline runtime and evaluator-cache identity remain unverified.
K1 Contributions relative to TBSM
Thank you for the precise distinction between TBSM variants and for identifying the missing implementation and evaluation details. We address each point below.
Reviewer comment W1
Reviewer comment Q1
Response. Please see Common Response C2 and the revised Appendix B.1 (Algorithm 3, Figure 8). We credit TBSM for the conservative displacement construction, adversarial identity, and projection interpretation. TBSM does not report any experiments demonstrating the effectiveness of the GAN-corner displacement formulations considered here. Its paper identifies Algorithm 3 as an expository displacement analogue and reports experiments using unit-bearing supervision (TBSM v1, Secs. 2.4–2.5).
Our methodological development is endpoint potential training in frozen feature spaces; the implementation contribution is its image/video adaptation system, and the additional analysis characterizes conditional feature distributions under explicit assumptions. Neither Proposition 1 nor the appendix analyses establish descent of the practical endpoint update.
The completed comparison includes both TBSM GAN-corner displacement variants, with direct v and conservative ∇u, using the shared-field, generator-first, one-to-one update rule. Their 50K FIDs are 10.794 and 350.367, compared with NextGAN's 1.335; all three curves contain 20 evaluated checkpoints. NextGAN retains its established two field updates per generator update. These results provide a documented comparison of the configured systems and leave the isolated effect of query location unresolved. We do not reinterpret Figure 7 or these new curves as query-only evidence, or as results for TBSM's deployed unit-bearing algorithm.