Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We rec...
Xianshui Sun, Wei Chow, Yingshuo Wang et al.· 1 citation
This work organizes the embodied data ecosystem as a pyramidspanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelit...
Yifan Ye, Yankai Fu, Ya-hui Lv et al.· arXiv.org· 4 citations
The results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.
Weina Zhou, Xiongwei Zhu, Ling-Dong Kong et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
