
XL
Xin Li, Yiwen Chen
· 1 min read
ResearcharXiv cs.CV
Comparing Each Generation with Independent Siblings Gives Video World Model Post-Training a Proper Objective for Outcome Frequencies
arXiv:2611.24512v1 Announce Type: new
Abstract: Video world models are used as simulators, so when a first frame leaves several physical outcomes open, repeated generations should produce each outcome as often as it occurs in the data. Physics post-training scores every generation against the single recorded future of its history, which makes single videos more faithful, but the expected score is linear in the model distribution and is maximized by always producing the most likely outcome. The log-likelihood of the recorded outcome is maximized by the data distribution, and its gradient weights agreement with the record by the inverse of how often the model produces the generated outcome, a frequency that other generations of the same history with independent noise, its siblings, can estimate. To train with this weight from a finite group, we propose SibPO, which performs Sibling-paired Policy Optimization: siblings estimate a truncated inverse-frequency weight for agreement with the record, and a second term subtracts the same weight times the agreement with the siblings, which makes the expected objective a strictly proper divergence over outcome cells at every group size. On PisaBench, SibPO lowers the KS distance to simulated landing times by 9.1-10.2% relative to the strongest method outside its reward family on three of four video models without degrading single videos, and it lowers the error of estimated robot policy success rates by 13%.
Original source
This story was published by arXiv cs.CV and written by Xin Li, Yiwen Chen. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


