arXiv:2611.18866v1 Announce Type: new Abstract: In cinematic storytelling, sound and visual transitions do not always coincide in lockstep: dialogue frequently bridges across cuts to reveal reactions or introduces new scenes via J- and L-cuts, while deliberate silences pace the …
⏱ Độ trễ thật của tab này: trung bình 0.8 giờ sau khi CVE được công bố (n = 1, sớm nhất 0.8 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-tuning, long-rollout distillati…
Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, yet reliable quality judgments, correction pairs, and controlled variations are d…
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions a…