CVPR 2026 | HiF-VLA: A Motion-Centric World Action Model

CVPR 2026 | 突破短视，理解变化！HiF-VLA：以motion为中心打造「边想边做」的世界动作模型

Westlake University and collaborators introduced HiF-VLA, a motion-centric VLA framework that extracts compact Motion vectors with codecs such as H.264 and uses a joint expert to predict future visual motion and generate action sequences, reporting 31.4GB peak memory and 117.7ms latency under the cited history-window setting.

Why it matters: HKR-H/K/R all pass: the H.264-motion angle, concrete VRAM/latency numbers, and robotics deployment pressure are clear. It remains a single research item without adoption or cross-source heat, so it sits in the lower featured band.