An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to count. Answers shared across histories that differ in event order, accumulation, or relations leave those distinctions unconstrained; we call this state under-specification...
Yihao Hu, Pan Wang, Yi-Tong Lin et al.· 0 citations
Arithmetic experiments show that similar first-attempt accuracies can lead to very different coverage after repeated attempts, and when this reuse is reliable and how much computation it requires is studied.
De-Yuan Liu, Ze-Cheng Wang, Xuan-Yi Liu et al.· 0 citations
This work introduces FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts and shows under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data.
Yan-Sen Han, Shengyi Liao, Peng Sun et al.· 1 citation
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong...
Chu-Yan Chen, Hao-Xin Chen, Kun Chen et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.