Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation

Chenxi Xia; Yixuan Xu; Shan Liu; Jiapeng Wang; Maohua Li; Hanlin Tang; Kan Liu; Tao Lan

cs.CVOct 10, 2026

Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation

Authors: Chenxi Xia, Yixuan Xu, Shan Liu, Jiapeng Wang, Maohua Li, Hanlin Tang, Kan Liu, Tao Lan,

Organizations: Zhejiang University · Alibaba Group · Nanjing University

Abstract

Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self Forcing and its follow-up methods substantially mitigate exposure bias caused by the mismatch between training- and inference-time history distributions. However, these models still suffer from error accumulation during long-horizon generation. We identify a key underlying limitation: the model remains highly sensitive to errors in its generated history, allowing small deviations to be amplified through subsequent generations. We refer to this underexplored problem as the local history robustness gap. To address this gap, we introduce Adversarial Gradient Forcing (AGF), a framework designed to improve the robustness of few-step autoregressive video models to perturbations and accumulated errors in their own generated histories. AGF uses distribution matching gradients from future block predictions to select adversarial perturbations of self-generated histories. It then jointly trains the generator on the original and perturbed histories to improve the robustness of future generation. Extensive experiments show that AGF achieves the highest VBench Total score on 60-second video generation and the best visual quality on four-minute video generation. Notably, AGF achieves such long-horizon robustness while requiring only 5-second rollouts for training.

Figures & tables

Figure 1: An example of four-minute video generation. Self Forcing and AGF generate four-minute videos using the same ODE initialization. With Self Forcing, visual artifacts emerge and progressively worsen over time, while AGF maintains coherent subjects and scene structure.

Figure 2: A single perturbation leads to severe visual degradation in long-horizon autogressive video generation. The top row shows an unperturbed Self-Forcing rollout, while the bottom row uses the same model and identical sampling randomness for future generation, differing only by a one-time perturbation applied to the generated history. Compared with the unperturbed rollout, concentric background artifacts emerge earlier and progressively intensify in the perturbed rollout, accompanied by increasingly severe subject distortion.

Figure 3: Adversarial Gradient Forcing. (a) Sample autoregressive rollout trajectories offline without gradient. (b) Use DMD gradients from blocks after

j

to select a history perturbation that most adversely affects subsequent generations. (c) With the perturbation fixed, train jointly on the clean and perturbed histories.

G_{\theta}

denotes the generator in DMD parameterized by

\theta

Figure 4: Effects of selected and Gaussian history perturbations. The leftmost clean history serves as the scene reference. History difference shows the pixel difference between corresponding frames decoded from the perturbed and original histories. Later-frame difference shows the pixel difference between corresponding later frames generated from two separate histories.

	5 s	60 s			240 s
Method	Total $\uparrow$	Quality $\uparrow$	Semantic $\uparrow$	Total $\uparrow$	Subj. $\uparrow$	Back. $\uparrow$	Motion $\uparrow$	Aesth. $\uparrow$	Imaging $\uparrow$	Dyn. †	Q5 $\uparrow$
Self-Forcing	82.21	82.95	66.01	79.56	96.36	95.79	97.95	54.97	67.26	63.19	82.47
Causal Forcing	82.94	83.82	63.88	79.83	94.44	94.82	95.99	55.29	68.41	91.41	81.79
LongLive	80.34	82.11	70.59	79.81	97.08	96.24	98.60	58.29	67.86	49.53	83.62
SGF	82.08	83.56	64.09	79.67	97.11	96.10	98.18	58.32	70.63	51.08	84.07
OPSD-V	81.95	83.16	67.67	80.06	96.29	95.64	97.91	56.60	67.77	65.10	82.84

Table 1: Quantitative comparison with relevant baselines. We benchmark all methods from native 5-second generation to 240-second long-horizon generation. Except for Dynamic Degree, orange and blue indicate the best and second-best results, respectively; the best results are bolded. Higher Dynamic Degree may also arise from severe camera drift or visual corruption and does not necessarily indicate better generation quality.

Figure 5: Long-horizon qualitative comparison. Six-method rollouts on the coastal church scene at 0, 48, 96, 144, 192, and 240 seconds. AGF better preserves the subject and scene composition.

(a) Perturbation and regularization									(b) ODE initialization
	Default	Perturbation	Regularizer	Regularized steps			Reference model			Model
Duration	AGF	Gaussian	None	1–2	1–3	1–4	ODE init	Teacher	Duration	CF	$\mathrm{AGF}_{\mathrm{CF}}$
5 s	82.03	71.09	81.38	77.75	82.06	74.30	78.79	80.78	5 s	82.94	81.74
60 s	81.47	68.60	77.96	76.24	80.40	72.77	75.63	79.74	60 s	79.83	81.00
240 s	84.82	75.11	82.75	79.87	83.94	78.19	79.72	82.82	240 s	81.79	84.60

Table 2: Ablation studies of AGF. Panel (a) studies perturbation and regularization strategies, while panel (b) evaluates AGF under a different ODE initialization. Best scores in each row are bolded.

	Perturbation selection	Generator training
Differentiated variable	history perturbation $\delta$	generator parameters $\theta$
Active path	history K/V computation and later predictions	history K/V computation and predictions
Fixed values	parameters, recorded inputs and history, DMD gradient	perturbation, recorded inputs and history, DMD gradient
Output	history perturbation	generator update

Table 3: Gradient paths for perturbation selection and generator training.

Figure 8: Pixel changes around objects and illumination regions. In the ship scene, the selected perturbation changes pixels along the hulls, masts, and material boundaries. In the dancer scene, changes appear around the subject, her reflection, and regions of similar brightness. Similar patterns appear in the differences between later frames. The matched Gaussian perturbation produces weaker and more diffuse later-frame differences in these examples.

Figure 9: Pixel changes along object outlines and scene structures. The selected perturbations change pixels along the pigeon’s head and body outline, or around the hoop, net, and surrounding basketball scene. Similar contours appear in the differences between later frames, while the matched Gaussian perturbation produces more diffuse changes.

Field	Configuration
Generator / fake-score model	Wan2.1-T2V-1.3B / one Wan2.1-T2V-1.3B fake-score model
Frozen target score model	Wan2.1-T2V-14B
Initialization	Self-Forcing ODE checkpoint
Prompt source	Self-Forcing’s filtered, LLM-extended VidProM text prompts; sampled line-wise
Training rollout	21 latent frames; 3 frames per block; 7 latent blocks ( $\sim$ 5 s)
Steps 1–200	AGF with regularization applied to the first denoising prediction

Table 4: Training configuration for the evaluated AGF model. Optimizer and perturbation settings correspond to the pure-AGF stage.

(a) Training configuration and video-data requirements
Method	Training stage	Iterations	Global batch	Training horizon	Extra video data
Self-Forcing	DMD	600	64	5 s	–
Causal Forcing	Asymmetric DMD	750	64	5 s	–
LongLive	Long tuning	3,000	64	60 s stream (5 s windows)	–
SGF	ODE-init reproduction	1,200	8	5 s	–
OPSD-V	LoRA post-training	200	24	45 s	$\checkmark$

Table 5: Training requirements and cost accounting on eight H20 GPUs. Only the listed stages are counted; upstream initialization and data preparation are excluded. Check marks indicate yes and dashes indicate no.

Horizon	Prompts	Frames	Seconds	Segments/video	Evaluated dimensions
5 s	944	81	5.0625	1	16 VBench dimensions
60 s	240	957	59.8125	6 (10 s) or 30 (2 s)	16 VBench dimensions
240 s	120	3837	239.8125	120	6 dimensions

Table 6: Evaluation sets for each video duration. Each method produces one video per prompt, using the same mapping from prompt index to noise seed.

Method	Evaluated weights
Self-Forcing	Self-Forcing generator checkpoint; no additional EMA selection at inference
OPSD-V	Rank-256, $\alpha=256$ LoRA (dropout 0); non-EMA weights
SGF	Our reproduction using the official hyperparameters and ODE initialization; generator EMA at iteration 1200
LongLive	Released generator base and generator LoRA; non-EMA weights
Causal Forcing	Released final Stage-3 chunkwise generator; non-EMA weights
AGF (ours)	Step-400 generator EMA after 200 regularized and 200 pure-AGF iterations

Table 7: Model variants used in the controlled comparison. All six methods share the generation and evaluation protocol described above.

Dimension	$n$	Self-Forcing	OPSD-V	SGF	LongLive	Causal Forcing	AGF
Subject consistency	72/72/72/72/72/72	96.32	96.08	96.73	97.47	95.68	96.52
Background consistency	86/86/86/86/86/86	95.84	95.24	95.45	97.07	95.70	95.05
Temporal flickering	75/75/75/75/75/75	99.00	98.55	97.97	99.31	98.81	98.85
Motion smoothness	72/72/72/72/72/72	98.65	98.43	98.23	98.94	98.21	98.52
Dynamic degree	72/72/72/72/72/72	72.22	73.61	73.61	31.94	84.72	70.83
Aesthetic quality	93/93/93/93/93/93	62.29	62.62	64.69	63.71	64.65	63.92

Table 8: Complete raw dimension scores at 5 seconds. Each

n

entry gives valid prompt counts in Self-Forcing/OPSD-V/SGF/LongLive/Causal Forcing/AGF order. Scores are percentages; the reported summary scores are computed after normalization.

Dimension	$n$	Self-Forcing	OPSD-V	SGF	LongLive	Causal Forcing	AGF
Subject consistency	20/20/20/20/20/20	97.51	97.46	97.83	98.36	95.07	97.91
Background consistency	42/42/42/42/42/42	96.32	95.82	95.92	96.78	94.87	96.56
Temporal flickering	17/17/15/19/19/18	99.06	98.53	98.54	99.43	99.02	99.14
Motion smoothness	20/20/20/20/20/20	98.53	98.39	98.49	98.78	97.05	98.58
Dynamic degree	20/20/20/20/20/20	61.33	61.67	57.50	35.83	87.83	68.50
Aesthetic quality	20/20/20/20/20/20	55.08	57.07	59.92	58.17	56.18	58.48

Table 9: Complete raw dimension scores at 60 seconds. The count and method order follow Table 8 .

Dimension	Self-Forcing	OPSD-V	SGF	LongLive	Causal Forcing	AGF
Subject consistency	96.36	96.29	97.11	97.08	94.44	97.32
Background consistency	95.79	95.64	96.10	96.24	94.82	96.38
Motion smoothness	97.95	97.91	98.18	98.60	95.99	98.31
Aesthetic quality	54.97	56.60	58.32	58.29	55.29	61.20
Imaging quality	67.26	67.77	70.63	67.86	68.41	70.91
Dynamic degree	63.19	65.10	51.08	49.53	91.41	62.54

Table 10: All six dimensions evaluated at 240 seconds on the same 120 prompts. Values are percentages.

Figure 10: Camera drift changes the scene composition. (a) Warehouse flowers: SGF shifts into close-ups that lose the industrial surroundings, while AGF keeps the flowers and warehouse visible together. (b) Yawning child: Causal Forcing moves the view toward the toys and partly or fully excludes the child; AGF retains a clear view of the child and the changing expression.

Figure 11: Loss of fine detail and object structure. (a) Dandelion: distorted surfaces and colored artifacts replace the fine seed structure in Self-Forcing, while AGF retains the radial organization and visible filaments. (b) Pirate ships: Causal Forcing distorts the foam, cup, and ship placement; AGF preserves two recognizable ships within a clearly defined cup.

Figure 12: Maintaining subjects and settings during dynamic actions. (a) Sculpting: OPSD-V introduces adjacent copies of the clay figure; Causal Forcing repeatedly reframes the interaction around the sculptor’s face, taking the work surface out of view. AGF keeps one figure on the work surface as the hands shape it. (b) Salad tossing: Self-Forcing develops repeated chefs and background striping; OPSD-V also duplicates the chef. AGF retains one chef, the bowl, and the kitchen. (c) Dancing characters: the alternatives develop background deformations and colored bands, while AGF preserves the green and orange pair and their pastel setting as they move.

Figure 13: Subject copies and background artifacts in long rollouts. (a) Gift: Self-Forcing and OPSD-V add copies of the woman and alter the room; AGF retains one main subject and the holiday setting. (b) Felt monsters: Causal Forcing and SGF replace the softly blurred background with patterned scenery or indoor structures, while AGF retains the soft bokeh. (c) Papercraft reef: Self-Forcing adds colored stripes and LongLive introduces oversized dark forms; AGF keeps the coral environment and papercraft texture recognizable.

Figure 14: Two additional scenes across all six methods. (a) Bookshelf mushrooms: several alternatives develop repetitive geometry or striping, or shift away from the shelf. AGF preserves a clear view of the mushrooms on the shelf. (b) Dragon and underworld: close-ups and distorted geometry disrupt the relation between the dragon and people in several alternatives; AGF keeps the dragon, people, and cavern recognizable together.

Time (s)	Self- Forcing	OPSD-V	SGF	LongLive	Causal Forcing	AGF (ours)
0–20	84.19	83.75	84.85	84.58	82.73	84.71
20–40	83.50	83.06	84.39	83.87	81.68	84.65
40–60	82.77	82.62	84.07	83.70	81.35	84.58
60–80	82.45	82.57	83.95	83.38	81.29	84.65
80–100	82.33	82.58	83.85	83.32	81.45	84.71
100–120	82.18	82.41	83.61	83.34	81.29	84.60

Table 11: Local Q5 (%) over unperturbed four-minute generation. Q5 averages the five quality dimensions and excludes Dynamic Degree. Bold marks the highest mean in each interval.

Figure 15: Generation stability under temporary history perturbations. Mean local Q5 change from each video’s first 20 seconds, over 120 prompts. The first point summarizes 0–20 seconds; subsequent points use 10-second bins. Gray shading marks the 30–60-second intervention. Colored bands show pointwise 95% bootstrap intervals from 2,000 prompt resamples. These trajectories include natural quality drift as well as the effects of the intervention.

Model	Subject consistency	Background consistency	Motion smoothness	Aesthetic quality	Imaging quality	Dynamic Degree	Q5
CF	94.44	94.82	95.99	55.29	68.41	91.41	81.79
$\mathrm{AGF}_{\mathrm{CF}}$	97.37	96.44	98.33	59.87	71.01	79.95	84.60

Table 12: Alternative initialization at 240 seconds (%).

Figure 16: Distribution of human-assigned ranks. Each cell shows the percentage of 240 ranking tasks assigning that rank to the method. Rows follow the mean-rank ordering in Figure 7 ; darker cells indicate a larger share. Percentages are rounded to one decimal place.

Autoregressive Video Generation

Autoregressive video generation creates videos frame by frame or in chunks, conditioning each prediction on prior context for streaming and interactive use.

See all 211 papers

Direct Forcing: Single-Stage Training with Representation-Space Supervision for Few-Step Autoregressive Video Generation
Oct 22, 2026Haojun Xu, Jie Huang, Chuyang Zhao +6T2V Generation Autoregressive Video Generation
Beihang University · JD Future Academy
AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
Jun 2, 2026Haobo Li, Yanhong Zeng, Yunhong Lu +6Image-to-Video Generation Autoregressive Video Generation
AutoLab, SAI, SJTU · Ant Group · Department of Automation, Tsinghua University +2
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Oct 7, 2026Zihan Su, Junhao Zhuang, Yaowei Li +10Autoregressive Video Generation Long-Horizon Video Generation
Tsinghua University · Joy Future Academy, JD · The Chinese University of Hong Kong

Oct 22, 2026J/K move · Enter open · S save

Direct Forcing: Single-Stage Training with Representation-Space Supervision for Few-Step Autoregressive Video Generation

Haojun Xu, Jie Huang, Chuyang Zhao, Xin Lu+5

Beihang University · JD Future Academy

T2V Generation Autoregressive Video Generation

Open paper AskPDF arXiv

Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based text-to-video methods retain this separation by starting with an ODE initialization stage, even when the target distribution is defined directly by reference videos. We introduce \method, the first single-stage framework that uses reference videos both as paired examples of how a history continues and as a target population for self-generated rollouts. Specifically, Direct Forcing is trained with two complementary signals: (1) Causal Continuation Alignment learns paired spatiotemporal correspondence under reference histories; and (2) Rollout Distribution Matching employs maximum mean discrepancy to align the representation distributions of self-generated and reference videos. To coordinate these signals, we introduce Dynamic Gradient Balancing, which adapts their relative gradient contributions during training. Experiments with Wan2.1-1.3B show that Direct Forcing learns a four-step autoregressive generator in 250 updates without a separate ODE initialization stage or online diffusion-score supervision, achieving 84.63 VBench Total and 86.01 Quality.

Abstract

Autoregressive Video Generation

Explore similar work

Direct Forcing: Single-Stage Training with Representation-Space Supervision for Few-Step Autoregressive Video Generation

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation