optimal transport
PulseAugur coverage of optimal transport — every cluster mentioning optimal transport across labs, papers, and developer communities, ranked by signal.
- uses Diffusion Models 90%
- instance of Entropic Optimal Transport 90%
- instance of Gotit.pub 70%
- instance of alphaXiv 70%
- instance of ScienceCast 70%
- instance of CatalyzeX 70%
- used by Gromov--Wasserstein 70%
- instance of Gromov--Wasserstein 70%
- used by CatalyzeX Code Finder for Papers 60%
- used by CORE Recommender 60%
- affiliated with alphaXiv 50%
- affiliated with Diffusion Models 50%
11 day(s) with sentiment data
-
New framework improves medical image segmentation with partial supervision
Researchers have developed a novel two-stage framework for multi-organ segmentation in medical imaging, designed to overcome challenges posed by partially annotated datasets and domain shifts. The first stage focuses on…
-
TecoPrompt enhances vision-language models with temporal-conservative prompt learning
Researchers have developed TecoPrompt, a novel framework for robust prompt learning in vision-language models, particularly effective under noisy supervision. This method utilizes optimal transport (OT) pseudo-labeling …
-
New arXiv Paper Links Physics Concepts to Machine Learning Applications
A new review paper published on arXiv explores the deep connections between control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning. The paper highlights how thes…
-
New method uses Optimal Transport for supervised graph prediction
Researchers have developed a new method for supervised graph prediction (SGP) that addresses the challenge of comparing predicted and target graphs with arbitrary node orderings. The approach utilizes Optimal Transport …
-
New Optimal Transport method enhances industrial anomaly detection
Researchers have developed a new unsupervised anomaly detection framework using Optimal Transport (OT) specifically for industrial data. This method requires minimal user input and no labeled training data, making it ad…
-
GeoTTER framework improves zero-shot classification using optimal transport
Researchers have introduced GeoTTER, a new framework designed to enhance zero-shot classification by refining optimal transport methods. GeoTTER addresses limitations in conventional approaches by integrating local geom…
-
New flow matching techniques improve generative AI and inverse problem solving · 3 sources tracked
Researchers have developed new methods for flow matching, a technique used in generative AI for tasks like image generation. One paper introduces CyFM, which uses cylindrical optimal transport to improve the generation …
-
Deep learning model accelerates optimal transport calculations for physics data
Researchers have developed a novel deep learning model, the Metric-Aware Particle Flow Network, designed to approximate optimal transport calculations for complex datasets. This model, built using Deep Sets architecture…
-
New HELLO solver drastically improves large-scale optimal transport performance
Researchers have developed HELLO, a novel hierarchical solver designed to tackle large-scale optimal transport (OT) problems. This method casts OT as an edge localization task, utilizing dual potentials for both initial…
-
New frameworks enhance robot policies with flow matching and safety constraints · 4 sources tracked
Researchers have developed several new frameworks for improving flow-based policies in reinforcement learning, particularly for robotics. These methods aim to address challenges like multimodal action distributions and …
-
New framework improves unsupervised visible-infrared person re-identification
Researchers have developed a new framework for unsupervised visible-infrared person re-identification, addressing limitations in existing cross-modality association methods. The proposed approach utilizes modality-unifi…
-
New BROT Method Achieves Optimal Transport Map Estimation in Machine Learning
Researchers have introduced BROT (Barycentric Regression for OT), a novel two-step method for estimating optimal transport (OT) maps, which are crucial for aligning probability distributions in machine learning. This ap…
-
New planning method achieves 3x lower complexity using optimal-transport smoothing
Researchers have developed a new planning method called SecondOrderSmoothCruiser that improves upon existing techniques by incorporating second-order smoothness. This advancement reduces the oracle complexity from \(\\w…
-
New Projected RGD Algorithm Improves Bures-Wasserstein Barycenter Computation
Researchers have developed a new Projected Riemannian Gradient Descent (RGD) algorithm that improves the efficiency of computing Bures-Wasserstein (BW) barycenters. This method achieves dimension-independent linear conv…
-
D-FROST algorithm uses optimal transport for decentralized prompt tuning
Researchers have introduced D-FROST, a novel decentralized federated learning algorithm designed for prompt tuning. This method addresses challenges in decentralized settings, such as non-aligned prompt sets and the nee…
-
New clustering algorithm ANCMM uses Marcus mapping for sparse matrices
Researchers have developed a new clustering algorithm called Doubly Stochastic Adaptive Neighbors Clustering (ANCMM), which leverages the Marcus mapping. This novel approach extends the Marcus theorem to enable the lear…
-
New PG-OT framework improves text-to-image alignment, reduces reward hacking
Researchers have developed a new framework called Pareto Frontier-Guided Optimal Transport (PG-OT) to improve alignment in text-to-image generation models. This method addresses challenges in balancing diverse reward mo…
-
New methods tackle unsupervised action segmentation in videos · 2 papers
Two new research papers, SpecT-OT and FIS-OT, introduce novel approaches to unsupervised action segmentation in videos. SpecT-OT utilizes spectral-temporal representation learning with an unbalanced optimal transport ps…
-
New research offers geometric and residual-based perspectives on flow matching for generative models
Two new research papers explore advancements in flow matching techniques for generative modeling. The first paper, "Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective,"…
-
SinkSLOT method offers faster optimal transport for large datasets
Researchers have introduced SinkSLOT, a novel method for entropic optimal transport (EOT) that significantly improves computational efficiency for large datasets. Unlike the standard Sinkhorn-Knopp algorithm, which requ…