IntactWorld: Joint World Modeling with Intact Features

While recent video generation models synthesize highly realistic visuals, they lack a genuine understanding of intrinsic real-world logic. Existing methods attempt to understand the world by internalizing diverse world knowledge, yet constrained by computational overhead or dimensionality alignment, their learning processes inevitably compress features, causing a severe loss of structural information. To address this, we propose $\mathbf{\text{IntactWorld}}$, a $\mathbf{\text{Joint}}\mathbf{\text{World}}\mathbf{\text{Modeling}}\mathbf{\text{Architecture}}$ utilizing uncompressed $\mathbf{\text{Intact}}\mathbf{\text{Features}}$. Since data naturally reside on a low-dimensional manifold within a high-dimensional space, predicting the flow velocity $v$ within this uncompressed high-dimensional space induces a severe manifold gap. To successfully eliminate this optimization bottleneck, our framework instead predicts the clean feature $x_0$ at intermediate layers. Furthermore, to mitigate the computational overhead of incorporating complete world knowledge, we introduce a $\mathit{\text{Full-to-Compact}}\mathit{\text{Training}}\mathit{\text{Paradigm}}$. By replacing raw full features with highly refined CLS tokens, this paradigm enables efficient single-branch guidance, reducing spatial memory consumption by 11.4% and cutting inference latency by 43.8%. Extensive evaluations demonstrate the effectiveness of IntactWorld, outperforming established baselines by 2.46 points on the VBench 2.0 benchmark.