Tag
Slot-JEPA 将 JEPA 的稠密表示分解为可复用的语义槽与空间掩码，提供面向对象的预测接口，并结合 Transition Memory Predictor 与非平衡最优传输提升视觉理解迁移和目标条件规划，在七项视觉基准与 REALM-JEPA 机器人规划任务上取得改进。
OrderFlowDiT提出了一种带非平衡最优传输正则的条件扩散Transformer，用于预测未来五分钟限价订单簿的成交量-价格分布，相比MSE训练将全字段传输成本降低45.8%。
CleanRM 使用少量干净反馈，通过最优传输校准逐样本噪声比例，并以噪声校正的代理损失训练奖励模型，在 RLHF 中实现无偏的干净风险估计并超越现有去噪基线。
该论文提出带误差证书的Sliced Wasserstein草图方法，通过一维最优加权MM-原子量化并扩展到高维切片，将平方距离误差精确分解为残差与分区不匹配项，从而为任意质心草图提供可计算的误差保证，在文档、点云和流式细胞术基准上以更少存储保持了原始切片距离的分类性能。
该论文提出垂直切片Wasserstein距离(VSW)，一种用于比较meta-measures（分布的分布）的可扩展度量，证明其为有效度量并具有维度无关的统计收敛保证，在效率和精度上优于现有方法。
该论文提出 PORTAL，一种无需配对图像-文本数据、基于最优传输的多模态投影器初始化方法，可以完全跳过投影器训练阶段，在六个 LLM 主干和 16 个基准上匹敌使用 558k 图文对的标准训练流程。
该论文提出了一种可扩展的在线熵正则最优传输（OT）近似方法，使 Flow Matching 能够使用显著更大的源-目标耦合小批量，同时在理论上证明了相对独立配对能严格降低随机梯度方差和积分误差，并通过单细胞基因插值和图像流训练实验验证了效果。
提出一种通过蒸馏最优传输在仅有100-500个配对样本下对齐两个独立预训练单模态编码器的方法，在Flickr30k、MS-COCO和ChEBI-20上以相同锚点预算超越现有方法。
该论文引入了一种以神经网络复杂度（Barron能量）为核心的最优传输框架，替代传统L²动能，从而在概率测度空间上定义新的几何结构，并证明了扩散生成模型在Barron几何下的次优性（超多项式score逼近下界）。
PXtal 提出一种在模态间信息不对称条件下对齐粉末X射线衍射（PXRD）与晶体结构表示的框架，利用非平衡最优传输（UOT）和广义Kullback-Leibler散度监督传输计划，在PXRD到晶体候选检索及下游材料任务上优于基线模型。
FlashSinkhorn 2 introduces a two-stage block-sparse GPU solver for entropic optimal transport that scales to 1.34e8-particle point clouds, solving them on a single A100 to a marginal residual below 0.01 in under 2.5 hours — claimed to be the largest discrete EOT problem solved at this accuracy within hours. An open-source implementation is released.
This paper proposes BaryFM, a flow matching model that learns to approximate the entire Wasserstein simplex — the full family of Wasserstein barycenters over the simplex of weight vectors — rather than a fixed-weight barycenter. BaryFM achieves the best average rank among 15 methods across 10 domain adaptation benchmarks and is validated on tasks including generalization, Bayesian posterior aggregation, and algorithmic fairness.
The paper proposes OTROPE, a likelihood-free off-policy evaluation method for LLMs that uses optimal transport to align limited human-labeled behavior-policy samples with unlabeled target-policy samples in semantic space, yielding a doubly robust-style evaluator that outperforms baselines under distribution shift.
ATLAS is a training objective for latent world models that preserves relational geometry from encoder representations into the planning latent while calibrating its marginal distribution via Wasserstein-2 transport (WEMReg). Instantiated in LeWM, it improves goal-reaching success on PushT, TwoRoom, and OGBench-Cube benchmarks, particularly on higher-novelty episodes.
OTRetarget 提出一种统一方法，利用熵最优传输联合重定向机器人与多物体的运动，通过保持接触一致性显著优于 OmniRetarget，并在物理人形机器人 G1 上验证了迁移到强化学习训练的全身策略的可行性。
This paper introduces Coupled Usage–Sense Processes (CUSP), a hierarchical model for analyzing lexical semantic change by quantifying timing, mechanisms, and attributions in word usage over time.
ColNanoVDR introduces the first document-free query distillation framework for multi-vector visual document retrieval, using optimal transport to align student and teacher query embeddings, enabling faster encoding while retaining high performance.
The paper proposes PsyBer-Agent, a psychology-inspired LLM user simulator for recommender systems that models evolving latent states like fatigue and shifting preferences, calibrated via Unbalanced Gromov-Wasserstein optimal transport, along with the WebSim platform and PsyBer Benchmark for evaluating behavioral fidelity at scale.
The paper introduces Reward-Weighted Transport Distillation (RWTD), a post-training method for one-step generative models that needs only generated samples and scalar rewards, blending tilted current and reference distributions via feature-space optimal transport. It boosts the GenEval score of the SanaSprint 1.6B one-step backbone from 0.73 to 0.80 while preserving compositional capabilities.
This paper introduces Riemannian Wasserstein Entropic Flow Matching (RWEFM), a generative framework for modeling probability distributions on Riemannian manifolds, with applications in scientific domains like single-cell biology and protein conformations.