DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models

Huanran Hu; Zihui Ren; Dingyi Yang; Zhinan Song; Guozheng Wu; Tiezheng Ge; Qin Jin

cs.CVOct 1, 2026

DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models

Authors: Huanran Hu, Zihui Ren, Dingyi Yang, Zhinan Song, Guozheng Wu, Tiezheng Ge, Qin Jin

Organizations: Renmin University of China · Alibaba Group · Tianjin University

Abstract

Despite remarkable progress, video generation models often produce highly similar outputs when repeatedly sampled from the same prompt, limiting their usefulness for creative exploration. Existing diversity evaluations primarily rely on global scalar metrics, which obscure where diversity collapses in the spatiotemporal space of videos. We introduce DiVid, a dimension-level diagnostic framework that decomposes video generation diversity into six interpretable dimensions: Semantic, Style, Subject, Scene, Motion, and Camera. Each dimension is measured through a reproducible computer-vision pipeline and analyzed alongside quality and instruction faithfulness to examine potential trade-offs. Systematic evaluation of representative video generation models reveals that diversity is highly dimension-specific: models with strong global diversity scores still collapse on specific factors, particularly Motion and Camera. These rankings persist after filtering unfaithful generations, indicating genuine capability differences rather than off-prompt outputs. Beyond measurement, controlled prompt interventions identify two fundamental bottlenecks: default mode convergence, where models fall back to dominant patterns under open-ended prompts; and realization gaps, where models fail to faithfully realize diverse, explicitly requested alternatives, particularly for temporal factors. The larger faithfulness losses for temporal factors highlight the difficulty of controlling motion and camera variation through text alone. DiVid thus shifts the study of diversity from measuring whether it exists to diagnosing where and why it collapses, and provides actionable directions for dimension-aware training objectives and control signals. The framework will be released to facilitate future research on diverse and controllable video generation.

Figures & tables

Figure 1 : Diagnosing dimension-specific homogenization : For each dimension, the left set exhibits greater target-factor variation than the right set under the same prompt. DiVid consistently assigns the expected ordering in all dimensions, whereas global metrics such as TCE and TIE can fail to capture factor-level differences.

Figure 2 : Overview of the DiVid Framework . Given a set of videos generated from a single prompt, our diagnostic framework extracts representations across six spatiotemporal dimensions to compute fine-grained diversity scores.

	Faith / Quality					Prior Metrics		Holistic		Factor Level
Model	IF	AQ	IQ	TF	MS	TCE	TIE	Semantic	Style	Subject	Scene	Motion	Camera
Wan2.2-5B (g=5)	0.848	0.543	0.672	0.980	0.989	5.29	13.36	0.169	0.234	0.447	0.426	0.326	0.097
Wan2.2-14B	0.915	0.614	0.699	0.972	0.983	4.54	13.29	0.144	0.224	0.412	0.394	0.344	0.148
CogVideo	0.839	0.516	0.622	0.973	0.985	4.12	12.66	0.142	0.214	0.414	0.377	0.323	0.045
Hunyuan	0.893	0.541	0.662	0.965	0.991	5.05	13.07	0.142	0.197	0.392	0.378	0.433	0.490
Wan2.7	0.963	0.563	0.722	0.972	0.985	4.94	12.74	0.158	0.201	0.397	0.390	0.413	0.303

Table 1 : Faithfulness, quality and diversity profiles pooled over the 206 general prompts. The table is divided into open-source models, closed-source models, and two ablations. Results are macro-averaged over available prompt-level measurements. Bold and underlined denote the highest and second-highest values for normal setting.

Figure 3 : Rank Heatmap on all diversity metrics.

Figure 4 : Faithfulness–Diversity trade-off. (a) Equal-count MPD ( $k=3$ ) under faithfulness threshold $\tau$ ; colored curves highlight the Top-1 model at $\tau=0.8$ . (b) Six-dimension macro BPWR under diversity weight $w_{D}$ .

Model	Hinted				Omitted			Enumerated
Model	Subject	Scene	Motion	Camera	Scene	Motion	Camera	Subject	Scene	Motion	Camera
Wan2.2-5B	+0.237	+0.014	+0.128	+0.032	+0.041	+0.049	+0.003	+0.450	+0.395	+0.168	+0.031
Wan2.2-14B	+0.203	+0.028	+0.100	+0.219	+0.034	-0.021	+0.009	+0.461	+0.444	+0.174	+0.167
CogVideo	+0.138	+0.056	+0.034	+0.010	+0.041	+0.010	+0.004	+0.411	+0.397	+0.095	+0.017
Hunyuan	+0.209	+0.075	-0.047	+0.081	+0.076	-0.020	+0.093	+0.492	+0.308	+0.067	+0.281
Wan2.7	+0.234	+0.109	+0.067	+0.398	+0.105	-0.004	+0.109	+0.468	+0.341	+0.146	+0.534

Table 2 : Mean MPD changes relative to the Specified condition; bold denotes the largest responses within each column, while Positive models reports the number of models with positive mean changes.

Dimension	Omitted	Hinted	Enumerated
Subject	N/A	an animal	{dog, cat, horse, …}
Scene	remove on a beach	somewhere	{beach, forest, city, …}
Motion	remove resting	in motion	{walks, runs, jumps, …}
Camera	remove static camera	camera moves	{pan, zoom, dolly, …}

Table 3 : Illustration of the prompt settings.

Figure 5 : A subject convergence case: The model defaults “an animal” to “a golden retriever”.

Figure 6 : Faithful realization under enumeration on the original faithfulness scale. (a) Changes in target faithfulness from Hinted to Enumerated. (b) Camera diversity gain versus Enumerated faithfulness.

Appendix figures & tables41 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 7 : Sensitivity to the number of generated videos. Left: MPD. Right: raw Vendi Score.

Figure 8 : Each point represents a generated video. PCA visualization illustrates both intra-model and inter-model homogenization across six diversity dimensions and the global profile.

Group	Controlled variation	Motion MPD
1	Breathing / ear twitch / deep breath	0.254
2	Walk left / right / toward camera	0.469
3	Slow / normal / fast locomotion	0.483
4	Sleep / stand and stretch / chase	0.616
5	Shake / scratch / dig	0.456

Appendix

Table 4: Motion sensitivity pilot. Each row aggregates three prompts that share a subject and differ in the indicated motion property.

Dimension	Spearman $\rho$	Kendall $\tau_{b}$	Kripp. $\alpha$
Semantic	0.604	0.539	0.703
Style	0.563	0.522	0.682
Subject	0.549	0.503	0.679
Scene	0.541	0.489	0.680
Motion	0.531	0.471	0.692
Camera	0.556	0.502	0.686

Appendix

Table 5: Human evaluation for 6-dimension diversity. All correlations have

p<0.001

Factor	Strict	Direction	Kripp. $\alpha$
Subject	63.4%	85.4%	0.699
Scene	65.4%	88.9%	0.705
Motion	63.7%	90.1%	0.742
Camera	69.3%	90.3%	0.766

Appendix

Table 6: Human evaluation for factor-specific faithfulness.

Factor	VIF	Grouped-CV $R^{2}$ (95% CI)	Unexplained	Top-model change (95% CI)
Subject	1.73	0.419 [0.363, 0.471]	58.1%	25.6% [19.5, 31.8]
Scene	1.73	0.418 [0.363, 0.470]	58.2%	19.5% [13.8, 25.1]
Motion	1.39	0.274 [0.222, 0.326]	72.6%	22.6% [16.9, 28.7]
Camera	1.37	0.266 [0.212, 0.320]	73.4%	26.7% [20.5, 32.8]

Appendix

Table 7: Incremental diagnostic utility. Grouped-CV predicts one factor from the other three. Top-model change compares the prompt-level top set before and after deleting the factor.

Target factor	Prompts retrieved	Pair count
Subject	122/150 (81.3%)	286
Scene	112/150 (74.7%)	262
Motion	138/150 (92.0%)	484
Camera	140/150 (93.3%)	521

Appendix

Table 8: Factor-selective pair retrieval on VBench. The target response is in the top 10%, while all other factor responses are no higher than their medians.

Model	Semantic	Style	Subject
Wan2.2-5B	$0.169\pm 0.067\ [0.160,0.178]$	$0.234\pm 0.060\ [0.226,0.243]$	$0.447\pm 0.159\ [0.425,0.468]$
Wan2.2-14B	$0.144\pm 0.073\ [0.134,0.154]$	$0.224\pm 0.066\ [0.215,0.233]$	$0.412\pm 0.173\ [0.388,0.436]$
CogVideo	$0.142\pm 0.058\ [0.134,0.150]$	$0.214\pm 0.068\ [0.205,0.223]$	$0.414\pm 0.146\ [0.394,0.434]$
Hunyuan	$0.142\pm 0.060\ [0.134,0.150]$	$0.197\pm 0.063\ [0.188,0.205]$	$0.392\pm 0.163\ [0.370,0.414]$
Wan2.7	$0.158\pm 0.068\ [0.149,0.168]$	$0.201\pm 0.058\ [0.193,0.209]$	$0.397\pm 0.161\ [0.375,0.420]$
HappyHorse	$0.093\pm 0.054\ [0.086,0.101]$	$0.123\pm 0.042\ [0.117,0.129]$	$0.250\pm 0.141\ [0.231,0.269]$

Appendix

Table 9 : Complete model-level MPD statistics for the Semantic, Style and Subject dimensions. Each cell reports the mean

\pm

prompt-level standard deviation and the 95% confidence interval obtained from 20,000 prompt-bootstrap resamples.

Model	Scene	Motion	Camera
Wan2.2-5B	$0.426\pm 0.140\ [0.407,0.446]$	$0.326\pm 0.104\ [0.311,0.340]$	$0.097\pm 0.151\ [0.077,0.118]$
Wan2.2-14B	$0.394\pm 0.154\ [0.374,0.416]$	$0.344\pm 0.109\ [0.329,0.359]$	$0.148\pm 0.235\ [0.117,0.181]$
CogVideo	$0.377\pm 0.124\ [0.359,0.394]$	$0.323\pm 0.089\ [0.311,0.336]$	$0.045\pm 0.119\ [0.030,0.063]$
Hunyuan	$0.378\pm 0.135\ [0.360,0.397]$	$0.433\pm 0.093\ [0.420,0.446]$	$0.490\pm 0.222\ [0.458,0.520]$
Wan2.7	$0.390\pm 0.130\ [0.373,0.408]$	$0.413\pm 0.090\ [0.401,0.425]$	$0.303\pm 0.225\ [0.272,0.334]$
HappyHorse	$0.223\pm 0.106\ [0.208,0.237]$	$0.326\pm 0.096\ [0.313,0.339]$	$0.193\pm 0.188\ [0.168,0.219]$

Appendix

Table 10 : Complete model-level MPD statistics for the Scene, Motion, and Camera dimensions. Each cell reports the mean

\pm

prompt-level standard deviation and the 95% confidence interval obtained from 20,000 prompt-bootstrap resamples.

Dimension	Positive paired contrast	$N$	$\Delta$ MPD	95% bootstrap CI	Global BH $q$
Semantic	Wan2.2-5B $-$ Hunyuan	206	0.027	[0.019, 0.035]	$9.1\times 10^{-11}$
Style	Wan2.2-5B $-$ Hunyuan	206	0.038	[0.030, 0.046]	$1.9\times 10^{-16}$
Subject	Wan2.2-5B $-$ Hunyuan	203	0.054	[0.037, 0.072]	$1.2\times 10^{-8}$
Scene	Wan2.2-5B $-$ Hunyuan	203	0.047	[0.030, 0.063]	$4.6\times 10^{-8}$
Motion	Hunyuan $-$ Wan2.2-5B	204	0.107	[0.089, 0.125]	$5.0\times 10^{-20}$
Camera	Hunyuan $-$ Wan2.2-5B	204	0.394	[0.362, 0.424]	$9.8\times 10^{-33}$

Appendix

Table 11: Prompt-paired validation of the central Wan2.2-5B–Hunyuan rank reversal.

\Delta

MPD is positive for the first-named model. Confidence intervals are based on 20,000 paired prompt-bootstrap resamples;

q

values are obtained from two-sided Wilcoxon signed-rank tests with Benjamini–Hochberg correction across all 126 dimension–model-pair comparisons.

Source	AQ	IQ	TF	MS	Semantic	Style	Subject	Scene	Motion	Camera	Six-dim. Avg.
Real videos	0.574	0.707	0.980	0.991	0.239 (1)	0.261 (1)	0.523 (1)	0.540 (1)	0.407 (4)	0.243 (4)	0.369 (1)

Appendix

Table 12 : Quality and diversity of the retrieved real-video reference. Diversity ranks, shown in parentheses, are computed jointly with the seven evaluated generation models.

Metric	Sem.	Sty.	Subj.	Scene	Mot.	Cam.
IF	-0.214	-0.679	-0.786	-0.429	0.393	0.500
AQ	0.179	-0.179	-0.393	-0.036	0.286	0.214
IQ	-0.071	-0.214	-0.357	0.000	0.000	0.071

Appendix

Table 13: Spearman correlations across seven model means.

Metric	Negative	Positive	Total
IF	15	0	15
AQ	13	0	13
IQ	7	14	21
Total	35	14	49

Appendix

Table 14: Prompt-level correlations significant after BH-FDR correction across 126 tests.

Model	Overall IF	Subject	Scene	Motion	Camera
Wan2.2-5B	0.848	0.853	0.928	0.778	0.938
Wan2.2-14B	0.915	0.914	0.957	0.890	0.967
CogVideo	0.839	0.813	0.919	0.790	0.971
Hunyuan	0.893	0.898	0.937	0.842	0.977
Wan2.7	0.963	0.962	0.992	0.935	0.986
HappyHorse	0.986	0.984	0.999	0.968	1.000

Appendix

Table 15: Overall and factor-specific faithfulness.

Figure 9 : Equal-count diversity ranking at the primary setting $\tau=0.8$ , $k=3$ . Every cell displays the within-dimension model rank.

Figure 10 : Dimension-specific BPWR ranks over the full diversity-weight range.

Figure 11 : Prompt-level quality–diversity decision rates with AQ/IQ/Diversity weights 0.25/0.25/0.50.

	Faith / Quality					Prior Metrics		Holistic		Factor Level
Model	IF	AQ	IQ	TF	MS	TCE	TIE	Semantic	Style	Subject	Scene	Motion	Camera
Wan2.2-5B	0.845	0.553	0.682	0.982	0.990	5.555	13.422	0.184	0.241	0.473	0.450	0.317	0.083
Wan2.2-14B	0.916	0.620	0.704	0.972	0.984	4.590	13.262	0.149	0.228	0.425	0.406	0.338	0.146
CogVideo	0.857	0.531	0.636	0.974	0.986	4.006	12.385	0.148	0.217	0.421	0.382	0.315	0.051
Hunyuan	0.899	0.549	0.670	0.965	0.991	5.318	13.263	0.154	0.206	0.416	0.399	0.450	0.504
Wan2.7	0.965	0.572	0.731	0.972	0.985	5.177	12.765	0.170	0.206	0.414	0.408	0.422	0.308

Appendix

Table 16 : Complete quality, faithfulness, and diversity profiles on the 150 VBench prompts.

	Faith / Quality					Prior Metrics		Holistic		Factor Level
Model	IF	AQ	IQ	TF	MS	TCE	TIE	Semantic	Style	Subject	Scene	Motion	Camera
Wan2.2-5B	0.858	0.518	0.645	0.974	0.986	4.564	13.198	0.131	0.216	0.376	0.363	0.349	0.134
Wan2.2-14B	0.912	0.598	0.683	0.970	0.981	4.388	13.368	0.131	0.211	0.376	0.361	0.358	0.155
CogVideo	0.789	0.475	0.585	0.970	0.983	4.418	13.407	0.127	0.207	0.395	0.363	0.345	0.030
Hunyuan	0.876	0.517	0.641	0.965	0.991	4.351	12.546	0.109	0.173	0.329	0.323	0.389	0.453
Wan2.7	0.958	0.539	0.700	0.972	0.985	4.310	12.664	0.129	0.187	0.353	0.343	0.390	0.289

Appendix

Table 17 : Complete quality, faithfulness, and diversity profiles on the 56 T2V-CompBench prompts.

Dimension	Most complementary pair	$\Delta_{\mathrm{comp}}$
Semantic	CogVideo + HappyHorse	0.140
Style	CogVideo + HappyHorse	0.117
Subject	CogVideo + HappyHorse	0.230
Scene	CogVideo + HappyHorse	0.257
Motion	Wan2.2-5B + Seedance	0.139
Camera	CogVideo + Seedance	0.152

Appendix

Table 18: Model pair with the largest mean complementarity in each dimension.

Figure 12 : intra- and inter-model similarity matrices.

Panel of Figure 13 — Figure 13 : Holistic cases.

Panel of Figure 14 — Figure 14 : Composition cases.

Panel of Figure 15 — Figure 15 : Temporal cases.

Setting	Construction	Diagnostic role
Specified	All four dimensions are explicitly specified.	Paired reference condition.
Omitted	Remove the target-dimension description.	Tests autonomous exploration.
Hinted	Replace the specific description with a generic cue.	Tests dimension activation.
Enumerated	Enumerate target candidates; generate one video per prompt.	Tests candidate realization.

Appendix

Table 19: Controlled prompt settings. Subject omission is undefined because a valid prompt requires a subject.

Setting	Target	No.	Prompt
Specified	All	–	A large fluffy adult golden retriever is resting on a quiet sandy beach at golden hour, static camera
Hinted	Subject	–	An animal is resting on a quiet sandy beach at golden hour, static camera
Hinted	Scene	–	A large fluffy adult golden retriever is resting somewhere, static camera
Hinted	Motion	–	A large fluffy adult golden retriever is in motion on a quiet sandy beach at golden hour, static camera
Hinted	Camera	–	A large fluffy adult golden retriever is resting on a quiet sandy beach at golden hour, camera moves
Omitted	Scene	–	A large fluffy adult golden retriever is resting, static camera

Appendix

Table 20 : Complete controlled-prompt example for one semantic group. Only the target span changes within each intervention block.

Intervention	Dimension	Mean $\Delta$ [95% CI]	Positive blocks	$g_{z}$	$p$	$q$
Hinted	Subject	+0.197 [+0.144,+0.251]	19/20	1.49	$1.91\times 10^{-6}$	$3.00\times 10^{-6}$
Hinted	Scene	+0.056 [+0.032,+0.087]	17/20	0.81	$3.15\times 10^{-5}$	$4.33\times 10^{-5}$
Hinted	Motion	+0.069 [+0.044,+0.094]	18/20	1.13	$1.31\times 10^{-4}$	$1.60\times 10^{-4}$
Hinted	Camera	+0.210 [+0.184,+0.239]	20/20	3.05	$9.54\times 10^{-7}$	$1.75\times 10^{-6}$
Omitted	Scene	+0.051 [+0.025,+0.082]	18/20	0.73	$1.97\times 10^{-4}$	$2.17\times 10^{-4}$
Omitted	Motion	+0.011 [-0.007,+0.029]	12/20	0.26	0.139	0.139

Appendix

Table 21: Complete group-level uncertainty for the target responses. This table supplements the model-level means in the main paper.

Contrast	Dimension	Mean difference [95% CI]	Positive blocks	Positive models	$q$
Hinted $-$ Omitted	Scene	+0.005 [-0.007,+0.018]	10/20	4/7	0.298
Hinted $-$ Omitted	Motion	+0.058 [+0.032,+0.087]	17/20	6/7	$1.17\times 10^{-4}$
Hinted $-$ Omitted	Camera	+0.118 [+0.092,+0.147]	20/20	6/7	$1.00\times 10^{-6}$
Enumerated $-$ Hinted	Subject	+0.275 [+0.250,+0.301]	20/20	7/7	$1.00\times 10^{-6}$
Enumerated $-$ Hinted	Scene	+0.313 [+0.262,+0.364]	20/20	7/7	$1.00\times 10^{-6}$
Enumerated $-$ Hinted	Motion	+0.077 [+0.057,+0.098]	20/20	7/7	$1.00\times 10^{-6}$

Appendix

Table 22 : Adjacent-setting contrasts computed within each target dimension.

Dimension	Hinted mean	Enumerated mean	Enumerated $-$ Hinted [95% CI]	Negative blocks	Negative models	$q$
Subject	4.593	4.497	-0.096 [-0.258,+0.048]	10/20	5/7	0.226
Scene	4.999	4.791	-0.204 [-0.254,-0.156]	19/20	7/7	$8.90\times 10^{-5}$
Motion	4.780	4.090	-0.690 [-0.887,-0.486]	18/20	7/7	$3.82\times 10^{-5}$
Camera	4.469	4.075	-0.393 [-0.541,-0.247]	18/20	6/7	$8.90\times 10^{-5}$

Appendix

Table 23: Faithfulness changes when moving from Hinted to explicit enumeration.

Figure 16 : Prompt-gated default convergence.

Panel of Figure 17 — Figure 17 : Both cases use Hunyuan; the left column releases Motion and the right column releases Camera.

Panel of Figure 18 — Figure 18 : Realization-limited diversity. Left: Hunyuan Motion. Right: Hunyuan Camera. Each row displays the target-dimension Faithfulness score on the video.

Figure 19 : Prompt for Subject Annotation.

Figure 20 : Prompt for Evaluating Subject Faithfulness.

Figure 21 : Prompt for Evaluating Scene Faithfulness.

Figure 22 : Prompt for Evaluating Motion Faithfulness.

Figure 23 : Prompt for Evaluating Camera Faithfulness.

Figure 24 : Prompt for Subject Rewriting.

Figure 25 : Prompt for Scene Rewriting.

Figure 26 : Prompt for Motion Rewriting.

Figure 27 : Prompt for Camera Rewriting.

Explore similar work

Jun 16, 2026cs.CV

Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback--Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100--300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.

Siyi Chen, Shaowei Liu, Yixuan Jia +4

University of Michigan · NVIDIA · University of Illinois Urbana-Champaign

Video Diffusion Models Few-Step Distillation Generative Quality Symbolic Distillation Fidelity Diversity+1

Ask PDF

Sep 11, 2026cs.CV

Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation

Few-step distillation improves the efficiency of autoregressive (AR) video generation, but often causes diversity collapse: under the same prompt, different noise samples tend to produce highly similar videos with weakened motion dynamics. We analyze this degradation in Distribution Matching Distillation (DMD)-distilled AR video generators and find that, in the autoregressive setting, it takes the form of a structured uncertainty collapse: the mode-seeking bias of DMD maps different noise samples to nearly identical first chunks, and the deterministic AR cache then propagates this collapsed state to all subsequent chunks, turning a local loss of stochasticity at the rollout root into a global suppression of temporal variation. Based on this analysis, we propose Uncertainty DMD, a simple uncertainty-injection framework that restores stochasticity at two key stages of AR generation: a timestep perturbation for the first chunk to increase first-chunk diversity, and a stochastic cache-writing mechanism for later chunks to preserve uncertainty in autoregressive conditioning. The method requires no architectural changes and introduces only lightweight perturbation operations. The same perturbation mechanisms are used during both training and inference. Experiments show that Uncertainty DMD consistently improves diversity and motion dynamics while maintaining comparable per-sample visual quality.

Zixuan Duan, Xunzhi Xiang, Yabo Chen +6

Nanjing University, Institute of Artificial Intelligence, China Telecom (TeleAI), China · Institute of Artificial Intelligence, China Telecom (TeleAI), China · Fudan University, Institute of Artificial Intelligence, China Telecom (TeleAI), China

Autoregressive Video Diffusion Models Autoregressive Video Generation Distribution Matching Distillation Diversity Uncertainty

Ask PDF

Sep 30, 2026cs.CV

Video Generation Models: A Survey of Post-Training and Alignment

Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative priors learned through large-scale pretraining, pretrained video models often fail to reliably follow human intent, maintain temporal coherence, or satisfy physical and safety constraints. Compared with image and text generation, alignment in video generation presents unique challenges, including error accumulation over time, motion-appearance coupling, multi-objective trade-offs, and limited supervision for temporal properties. These challenges motivate systematic post-training strategies that adapt pretrained models without retraining them from scratch. In this survey, we present the first comprehensive review of post-training and alignment in video generation models. We frame post-training as a unifying framework and distinguish between implicit alignment and explicit alignment based on how alignment signals are enforced. From this perspective, we organize existing approaches into four broad categories: supervised fine-tuning methods, self-training and distillation methods, preference- and reward-based methods, and inference-time methods. This taxonomy provides a coherent view of how alignment signals shape model behavior across both training and deployment. Beyond methodological advances, we review commonly used datasets, benchmarks, and evaluation practices, and discuss open challenges such as scalable reward design, long-horizon temporal consistency, stability-expressiveness trade-offs, and safety-aware generation. This survey aims to provide a structured conceptual foundation and practical guidance for advancing controllable and reliable video generation models.

Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni +10

Arizona State University · Twitch · Stanford University +6

Generative Video Models Video Generation Post-Training

Ask PDF