The Representational Power of Frontier Video Diffusion

Do video diffusion models learn useful representations? Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that frontier video diffusion models overcome this limitation. By systematically probing their intermediate activations using zero-shot and parametric probes, we reveal that visual representations evolve across both network depth and noise levels, forming a distributed hierarchical feature space. Importantly, these representations are easily accessible with a single forward pass, and yield state-of-the-art or competitive performance on semantic and geometric understanding tasks without any fine-tuning. Our findings pave the way towards unified backbones for both video generation and perception.