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: A Westlake University team proposes HiF-VLA, replacing per-frame visual encoding with H.264 motion vectors and predicting visual dynamics and actions together, at 31.4GB peak memory and 117.7ms latency.