AI RESEARCH
FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis
arXiv CS.CV
•
ArXi:2603.07192v1 Announce Type: new Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for video generation, scaling resolution and frame counts leads to a "token explosion" that creates a massive computational bottleneck in the final refinement stages. To address this, we propose FastSTAR, a