Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents X-World~1.6, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.
Figures & tables
Figure 1: (a) Data curation through quality filtering, behavior tagging, and scenario selection; flow widths are illustrative. (b) Tag distribution across ego behavior, environment, and conditions; bar lengths indicate within-category percentages.
Figure 2: Base-model conditioning paths. Separate models use visual references or 3D scene representations to guide seven-camera generation. Dashcam conditioning is a related synchronized-completion capability.
Figure 3: Generation without and with 3DGS absolute static scene (ASC) conditioning, alongside ground truth. Each row shows a different scene.
Figure 4: Two-stage training pipeline. Block 01 develops the controllable base model. Blocks 02–06 adapt it for causal few-step generation, restore cross-chunk feedback, extend the training horizon, and apply reward-guided refinement.
Obs/s ↑
Denoiser (s) ↓
Step latency (s) ↓
Configuration
PPU
Node
P50
Mean
P50
Mean
P99
Speedup ↑
Reference kernels
0.156
0.625
5.96
5.92
19.04
18.68
23.80
1.00 ×
+ Channels-last VAE with fused causal input
0.201
0.803
4.48
4.55
14.70
14.46
18.94
1.28 ×
+ Fused DiT kernels
0.218
0.873
3.95
4.16
13.42
13.25
18.36
1.40 ×
+ AIU convolutions
0.237
0.949
3.69
3.80
12.49
12.22
15.23
1.52 ×
+ X-Cache
0.320
1.281
2.10
2.62
8.69
8.94
17.82
2.05 ×
Table 1: Steady-state closed-loop serving throughput, server denoiser forward time, and per-session end-to-end step latency on a 4 × PPU M810E node (12 concurrent sessions) with optimizations enabled cumulatively. Best and second-best values in each column are bold and underlined, respectively.
Metric
Our evaluator
Qwen3-VL-8B (zero-shot)
Evaluation set
Same-scene pairwise accuracy (%)
71.4 [53.6, 88.5]
21.4 [7.4, 37.9]
28 scenes
Video-penalty Spearman ρ
0.671 [0.476, 0.815]
0.097 [ −0.181 , 0.378]
60 videos
Video-penalty Pearson r
0.867 [0.540, 0.943]
−0.074 [ −0.238 , 0.207]
60 videos
Table 2: Agreement with human evaluation on paired X-World 1.0 and X-World 1.6 generations. Brackets give 95% confidence intervals from a scene-level cluster bootstrap. The zero-shot baseline uses Qwen3-VL-8B-Instruct with the same inputs and prompts. The three metrics capture complementary aspects of agreement. Same-scene pairwise accuracy measures how often the VLM selects the video preferred by humans within a scene. Across all 60 videos, Spearman ρ measures agreement in quality ordering using penalty ranks, while Pearson r measures the strength of the linear relationship between the actual penalty values. Spearman therefore focuses on ordering, whereas Pearson also reflects relative score differences; high Pearson correlation does not require identical score scales or absolute values.
Tracking
Compression
Reconstruction
Overall
Model / Variant
App. ↑
Decay ↑
Ray ↓
Δ SSIM ↑
Δ PSNR ↑
Bits ↓
SSIM ↑
PSNR ↑
MAE ↓
Avg. Rank ↓
X-World 1.0
0.8832
-0.0257
0.1836
0.0333
0.8587
0.6305
0.7238
21.4834
14.3622
3.83
SF
0.8856
-0.0241
0.1813
0.0336
0.8947
0.6277
0.7279
21.2349
14.6864
3.56
CSF
0.8873
-0.0234
0.1686
0.0339
0.9183
0.6305
0.7272
21.2381
14.7831
2.94
SF+LongTuning
0.8857
-0.0230
0.1680
0.0322
0.8160
0.6445
0.7300
21.5293
14.4123
2.78
CSF+LongTuning
0.8868
-0.0228
0.1691
0.0353
1.0039
0.6244
0.7286
21.3137
14.6838
1.89
Table 3: Consistency comparison with X-World 1.0 and training variants. SF denotes Self Forcing, CSF denotes Connected Self Forcing, and LongTuning denotes long-horizon tuning. Best and second-best results in each column are shown in bold and underlined, respectively; missing values are excluded. App. denotes Mean Appearance Consistency, Decay denotes Mean Appearance Decay Rate, Ray denotes Mean Ray Residual (m), and Bits denotes the inter/intra encoded-size ratio. A less negative decay slope indicates slower loss of appearance similarity with temporal separation. Both PSNR quantities are measured in dB, and reconstruction MAE uses pixel intensity units (0–255). Avg. Rank is the mean rank across the nine metrics among the five models, with average ranks assigned to ties; lower is better.
Figure 5: Qualitative comparison of temporal consistency between Self Forcing (SF) and Connected Self Forcing (CSF). Each pair of rows shows synchronized frames from SF (top) and CSF (bottom). From top to bottom, the examples compare vehicle appearance, sky color, gate details, and road structure. Blue and orange boxes mark selected earlier and later regions, respectively, with corresponding enlarged views and timestamps shown in the rightmost column.
Figure 6: Shared interaction pipeline for simulation and RL. Conceptual illustration of scene-conditioned generation and the policy–environment loop. Interaction records support behavioral evaluation; the RL branch adds training feedback and policy updates.
Metric
Change
Mean FDE (relative)
−20.9%
Share with FDE <1 m
+5.6 pp
Share with FDE <2 m
+9.4 pp
Share with FDE <5 m
+10.6 pp
Table 4: Trajectory consistency and target-behavior reproduction: X-World 1.6 versus 1.0.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 8: Compression-based temporal consistency. (a) Inter-frame and all-intra coding of the same video provide quality gains and an encoded-size ratio. (b) Conceptual illustration of larger prediction residuals from irregular appearance changes under the same motion.
Figure 9: One Packed NFT. Sequential evaluation interleaves target prediction and clean-cache extension; packed evaluation uses a detached clean KV bank while preserving the same causal visibility. Both use frozen old-model trajectories.