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%
- used by Sinkhorn divergence 80%
- used by CatalyzeX 70%
- used by alphaXiv 70%
- used by Gotit.pub 70%
- used by ScienceCast 70%
- instance of Gotit.pub 70%
- instance of alphaXiv 70%
- instance of ScienceCast 70%
- instance of CatalyzeX 70%
- used by Influence Flower 70%
10 day(s) with sentiment data
-
TraceRouter++ framework realigns LLM safety pathways using optimal transport
Researchers have introduced TraceRouter++, a novel framework designed to enhance the safety of large foundation models (LFMs) by realigning causal semantic routing pathways. Unlike existing methods that focus on localiz…
-
New FedFiOT framework enhances federated learning with Fisher-weighted optimal transport
Researchers have developed FedFiOT, a novel framework for federated learning that addresses the challenges of one-shot and few-round settings. This approach uses Fisher information to weigh parameter importance and alig…
-
New FOCUS method enhances imitation learning for complex control tasks
Researchers have developed FOCUS, a novel method for imitation learning from observations that addresses challenges in optimizing control for contact-rich trajectories. By combining local optimal-transport alignment wit…
-
New TACE method enhances multimodal RL credit assignment
Researchers have introduced TACE (Two-stage Advantage and Credit Estimation), a novel method for improving advantage estimation in Group Relative Policy Optimization (GRPO) for multimodal reinforcement learning. TACE ad…
-
New Riemannian geometry for Sinkhorn divergence established
Researchers have developed a new framework for understanding the geometry of Sinkhorn divergence, a widely used measure in optimal transport. This work establishes a formal Riemannian structure and derives key geometric…
-
New RPSD method enhances sequential recommendation with optimal transport
Researchers have introduced Retrieval-Privileged on-policy Self-Distillation (RPSD), a novel method for sequential recommendation that addresses limitations in current LLM-based approaches. RPSD tackles credit-blind opt…
-
AlignFlow enhances generative models with semi-discrete optimal transport
Researchers have introduced AlignFlow, a new method to enhance Flow-based Generative Models (FGMs) by integrating semi-discrete optimal transport. This approach establishes an explicit, optimal alignment between noise a…
-
New Lifted PCA method extends statistical analysis to Wasserstein space
Researchers have introduced Lifted PCA, a novel method for extending Principal Component Analysis (PCA) to data represented as probability distributions in Wasserstein space. This new technique addresses the lack of a c…
-
New Optimal Transport metric enhances object detection annotation agreement analysis
A new paper proposes an Optimal Transport (OT)-based metric to quantify agreement in object detection annotations. This method offers a more nuanced assessment than traditional metrics by considering graded costs for bo…
-
New WTF algorithm fine-tunes generative models with optimal transport
Researchers have introduced Wasserstein-Tilted Flow Maps (WTF), a novel simulation-free reinforcement learning algorithm for fine-tuning flow-based generative models. Unlike existing methods that rely on KL-regularized …
-
New research advances conformal prediction with volume optimization and covariate shift handling
Two new research papers on arXiv introduce advanced conformal prediction techniques. The first paper, "Minimum Volume Optimal Transport for Multivariate Conformal Prediction," proposes a framework that learns a Mahalano…
-
New PORTAL method skips projector training for multimodal LLMs
Researchers have developed a new method called PORTAL that bypasses the need for projector training in multimodal large language models (LLMs). This training-free initialization method uses summary statistics and optima…
-
New method aligns AI models with minimal paired data
Researchers have developed a new method for aligning independently pretrained unimodal encoders using a limited number of paired examples, around 100-500 pairs. The technique represents each data point by its similarity…
-
New method uses optimal transport for sparse learning on probability measures
Researchers have developed a novel method for dictionary learning tailored for probability measure-valued data. This approach embeds measures into Hilbert spaces using features derived from optimal transport geometry, e…
-
New OT-FlowRec framework enhances multimodal sequential recommendation
Researchers have introduced OT-FlowRec, a novel framework for multimodal sequential recommendation that addresses limitations in existing methods. OT-FlowRec utilizes optimal transport to model concurrent multi-interest…
-
New OTTER probe decodes visual grounding in frozen MLLMs
Researchers have developed a new method called OTTER to probe frozen Multimodal Large Language Models (MLLMs) and decode grounding information from modifier tokens. This technique uses Optimal Transport to align generat…
-
New Differentiable Resampling Method Enhances Variational Monte Carlo Learning
Researchers have developed Differentiable Systematic Resampling (DSR), a novel technique for variational sequential Monte Carlo methods. This approach allows for gradient-based learning by introducing a temperature-cont…
-
New method uses Optimal Transport to efficiently scale LLM depth
Researchers have introduced Optimal Transport Depth Up-Scaling (OT-DUS), a novel method for efficiently increasing the size of pre-trained large language models (LLMs). Unlike existing techniques that copy or average la…
-
New research explores optimal transport and flow matching in generative models
A new arXiv paper, "Expected Batch Optimal Transport Plans and Consequences for Flow Matching," co-authored by Samuel Boïté and associated with Hugging Face, delves into the complexities of optimal transport (OT) when a…
-
New BalLOT method enhances balanced k-means clustering with optimal transport
Researchers have introduced BalLOT, a novel approach to balanced k-means clustering that utilizes optimal transport. This method aims to provide a fast and effective solution, supported by theoretical guarantees and emp…