arXiv:2610.11318v1 Announce Type: new Abstract: Single-cell snapshot data can resolve a continuum of cellular states but do not uniquely determine the dynamics governing transitions between them. However, additional dynamical information can often be encoded in a cell-cell Markov…
arXiv cs.LG
TIER_1English(EN)·Peng Liu, Shaoxiang Qin, Theodore Potsis, Lili Ji, Dingyang Geng, Liangzhu Leon Wang·
arXiv:2610.10430v1 Announce Type: cross Abstract: Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation. Large-eddy simulation (LES) effectively resolves these instantaneous fields, but its application…
arXiv:2610.07229v1 Announce Type: new Abstract: Motivated by sequence-to-sequence transport in the context time-series domain adaptation, we study the problem of transportation between trajectories of Markov processes. Given a limited number of trajectories from source distributi…
arXiv cs.LG
TIER_1English(EN)·Zeyu Michael Li, William Xingxu Chen, Xiang Cheng·
arXiv:2610.08717v1 Announce Type: cross Abstract: We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving path network and a flow network…
Reward post-training of flow models either reweights the model's own samples under a KL penalty or a frozen reference, often for thousands of updates, or backpropagates the reward and moves every sample without checking that the move is worth its size. We introduce MEND, a reinfo…
arXiv cs.AI
TIER_1English(EN)·Shizheng Lin, Soon Hoe Lim, N. Benjamin Erichson·
arXiv:2610.03483v1 Announce Type: cross Abstract: We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the mom…
arXiv:2610.03202v1 Announce Type: cross Abstract: Flow Matching enables high-quality visual generation via continuous-time dynamics, but inference remains costly due to multiple sequential function evaluations. Existing acceleration methods reduce the number of function evaluatio…
arXiv cs.AI
TIER_1English(EN)·Yesom Park, Kelvin Kan, Qifan Chen, Thomas Flynn, Hayden Schaeffer. Xihaier Luo·
arXiv:2610.02260v1 Announce Type: new Abstract: Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers oft…
arXiv:2610.13606v1 Announce Type: new Abstract: Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefore involves two distinct problems. First, every output must remain on the correlat…
arXiv:2610.10823v1 Announce Type: new Abstract: Scaling a learned flow-matching velocity field $v_\theta$ by a gain $\gamma(t)$ was recently shown to greatly improve generation quality. Prior work argued that velocity fields trained with mean-squared error (MSE) systematically un…
arXiv:2610.09723v1 Announce Type: new Abstract: Prior artisan mesh generation works largely predict face tokens autoregressively, which makes inference slow. Recent methods instead flow match continuous latents built by Variational AutoEncoders (VAEs), but reconstruction quality …
arXiv:2610.05349v2 Announce Type: replace Abstract: We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas standard conditional flow matching (FM) incorporates conditioning through the v…
arXiv cs.CV
TIER_1English(EN)·Xi Ye, Yuzhu Wang, Xiaoyang Liu, Jiayi Wang, Yangyang Xu, Ruyu Wang, Wenlin Chen, Duo Su, Jun Zhu·
arXiv:2610.02726v1 Announce Type: new Abstract: Flow-matching-based multi-view world models generate realistic videos, but are commonly restricted to fixed camera rigs. Extending them to continuously varying camera poses requires paired pose--video observations with dense pose co…