Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Dianbo Liu

Dianbo Liu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Vision×1ML×1

Frequent co-authors

Xiang Li1×
Kenji Kawaguchi1×
Ziwen Xie1×
Shaowen Xiang1×
Hongyu He1×

Research Timeline

2026
Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities

The paper introduces a quotient-DAG view to accurately estimate unordered slate propensities for off-policy evaluation, solving the nuisance variance and computational gap inherent in standard importance sampling for autoregressive recommenders.

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitigating mode collapse.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentJun 1, 2026

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

Xiang Li, Dianbo Liu, Kenji Kawaguchi

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitiga…

View →
cs.LGcs.AIRecentMay 28, 2026

Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities

Ziwen Xie, Shaowen Xiang, Hongyu He, Dianbo Liu

The paper introduces a quotient-DAG view to accurately estimate unordered slate propensities for off-policy evaluation, solving the nuisance variance and computational gap inherent in standard importa…

View →