Skip to content

Author

Ke-Jun He

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

OneWorld: Learning Consistent Physics Across Actions in World Models

OneWorld, a shared-mechanism counterfactual generation framework that jointly models multiple action-conditioned futures under a common latent physical mechanism, is proposed and experiments show that OneWorld improves cross-intervention physical consistency while maintaining competitive single-rollout prediction quali...

Ke-Jun He, Yi-Chen Ding, Bin Yang · 0 citations
#machine learning Preprint Sep 2026

Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling

Quantile AlignTree Flow Matching (QAT-FM), an efficient structured coupling strategy that constructs a hierarchical coupling between a Gaussian prior and the target data distribution via a quantile-aligned tree structure, is proposed, enabling scalable training for large-scale high-dimensional generative tasks.

Jun-Yi Lin, Meng-Yu Li, Jing-Xuan Hu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.