Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

ArXi:2511.20649v3 Announce Type: replace Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining fine-grained action control during long-form rollouts, and (iii) the inability to realize discontinuous cinematic transitions within a single generation stream. We