2 papers
cs.CV2026
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
Yuxi Zhou, Zhengbo Zhang, Jingyu Pan +2
Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-bas…
cs.CL2026
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…