Bucket-Level MOO is introduced, a scalable distributed framework that applies gradient-based MOO algorithms locally, within the parameter buckets of distributed training, that enables conflict-aware updates without ever materializing a full gradient vector for any objective, and improves multilingual performance over s...
Ho-Ang P. Long, Yiran Zhao, Wei Lu et al.· arXiv.org· 0 citations
Four parallelism plans are left unbounded by the parallelism plans in common use, and each grows differently: expert dispatch with the routing matrix, the vocabulary projection with tokens times vocabulary, gradient checkpoint boundaries with depth times sequence length, and optimizer state with parameter count.
Shrey Pandit, Xuan-Phi Nguyen, Yiran Zhao et al.· 0 citations
This work proposes TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE), and constructs a unified four-paradigm dataset with trajectory progress scoring, video-QA answer quality scoring, and their pairwise counterparts.
Yi-Dong Wang, Yan Zhan, Ziteng Feng et al.· 0 citations
The results suggest that dense credit assignment through distillation can be effective when its likelihood-based scores are empirically validated as meaningful proxies for outcome-relevant credit, when this alignment does not hold.
Xuan-Phi Nguyen, Z. Liu, Yang Li et al.· 3 citations
World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and how will it evolve. Human behavior, however, is driven by hidden mental state (what a person believes, wants, intends, feels, and considers socially permissible), so a m...
Hao Fei, Yiran Zhao· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
