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. Gθ denotes the generator in DMD parameterized by θ .
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 ↑
Quality ↑
Semantic ↑
Total ↑
Subj. ↑
Back. ↑
Motion ↑
Aesth. ↑
Imaging ↑
Dyn. †
Q5 ↑
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.
Figure 7
(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
AGFCF
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 δ
generator parameters θ
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
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
✓
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, α=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
AGFCF
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 creates videos frame by frame or in chunks, conditioning each prediction on prior context for streaming and interactive use.
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.
We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation but suffer from motion collapse and training instability, resulting in static videos. AAD-1 addresses these challenges through two key designs in architecture and training strategy. Our key architectural insight is to break the symmetry between generator and discriminator. While the generator remains causal to preserve autoregressive sampling capability, the discriminator attends bidirectionally over the full spatiotemporal context and produces a single holistic realism score for the entire video sequence. This asymmetric design enables the discriminator to effectively detect global temporal failures and long-range drift that cause motion collapse in autoregressive generation. To stabilize training, we introduce a phased strategy that first uses distribution matching to bootstrap a stable one-step generator, providing a warm-up phase that brings the student distribution closer to the teacher before adversarial distillation begins. Extensive experiments on VBench demonstrate that AAD-1 achieves state-of-the-art performance in one-step autoregressive video generation.
Haobo Li, Yanhong Zeng, Yunhong Lu +6
AutoLab, SAI, SJTU · Ant Group · Department of Automation, Tsinghua University +2
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint optimization of visual quality and temporal consistency. We introduce Self Gradient Forcing Plus (SGF+), which assigns separate parameters to context writing and denoising while preserving their interaction through causal attention. Both roles are jointly optimized using the original generation objective without auxiliary losses, with context writing supervised through its contribution to future predictions. This simple change improves visual quality and long-horizon consistency over the evaluated baselines in both framewise and chunkwise generation, without additional video training data or a longer training horizon. Trained on only 5s rollouts, SGF+ supports continuous generation for up to 24 hours without long-video fine-tuning. These results highlight role-specific parameterization as an effective design principle for high-quality autoregressive video generation and native long-horizon extrapolation.
Zihan Su, Junhao Zhuang, Yaowei Li +10
Tsinghua University · Joy Future Academy, JD · The Chinese University of Hong Kong