Optimal Mixture Transport
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
arXiv:2606.02515v1 Announce Type: new Abstract: Optimal transport (OT) provides a principled framework for mapping between probability distributions. Despite extensive progress, applying OT to large-scale data remains computationally demanding, and the resulting pointwise transport plans are often difficult to interpret. We introduce Optimal Mixture Transport (OMT), a scalable framework that shifts the transport paradigm from individual samples to mixtures of subpopulations, reformulating...
Variational Entropic Optimal Transport
Announce Type: replace Abstract: Entropic optimal transport (EOT) in continuous spaces with quadratic cost is a classical tool for solving the domain translation problem. In practice, recent approaches optimize a weak dual EOT objective depending on a single potential, but doing so is computationally not efficient due to the intractable log-partition term. Existing methods typically resolve this obstacle in one of two ways: by significantly restricting the transport family to obtain...
DOT-MoE: Differentiable Optimal Transport for MoEfication
arXiv:2606.01666v1 Announce Type: new Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) architectures address this by decoupling model size from inference cost, training MoEs from scratch is often unstable and compute intensive. Conversion of pre-trained dense models into sparse MoEs has emerged as an alternative solution; however, existing methods...
Selective Sinkhorn Routing for Improved Sparse Mixture of Experts
arXiv:2511.08972v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) models are scalable and computationally efficient, enabling large increases in model capacity with limited inference overhead. Existing SMoE methods often depend on auxiliary objectives, such as load-balancing loss and z-loss, or additional trainable components such as noisy gating. While these techniques encourage expert diversity, they can introduce objective misalignment, increase model complexity, or...
Concept Heterogeneity-aware Representation Steering
arXiv:2603.02237v2 Announce Type: replace Abstract: Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal activations at inference time. Most existing methods rely on a single global steering direction, typically obtained via difference-in-means over contrastive datasets.
CT scans of BYD car parts
Design to Reality Evolution of the Plastic Bottle In the dark nights of my soul, I fret about how inconsistently engineered my life is. The coffee table I made a year or two ago was intended to look like the dining room table I built a few years earlier, but in reality the two bear only a vague resemblance to each other. Open a drawer of my tool chest at random, and perhaps you’ll find a thematically-aligned collection of well-loved hand tools, meticulously cut into a nest of Kaizen foam, or...
Experimental Characterization of Bulk Micromegas for Development of Active Target Time Projection Chamber for Nuclear Astrophysics Studies
arXiv:2602.21238v3 Announce Type: replace Abstract: A Micromegas-based active target Time Projection Chamber, namely Saha Active Target TPC (SAT-TPC), is under development at Saha Institute of Nuclear Physics for its application in nuclear astrophysics experiment to measure the branching ratio of the direct and sequential decay of the Hoyle state of $^{12}$C. A bulk Micromegas was characterized to optimize its operating parameters and its performance for $\alpha$-particle tracking was...
Nvidia Cosmos 3
Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what’s happening in their world, predict what’s likely to happen next, and generate actions for specific environments, embodiments, and tasks. NVIDIA Cosmos 3 is a frontier foundation model for physical AI that combines physical reasoning, world generation, and action generation within a single open model.
Gene ancestries reveal diverse microbial associations during eukaryogenesis
Abstract The origin of eukaryotes remains a central enigma in biology1. Continuing debates agree on the pivotal role of a symbiosis between an alphaproteobacterium and an Asgard archaeon2,3. However, the nature, timing and contributions of other potential bacterial partners4,5,6 and the role of interactions with viruses7,8,9 remain contentious.
Is extracting oxygen from lunar soil the future of space exploration?
Is extracting oxygen from lunar soil the future of space exploration? Lisa Lock Scientific Editor Andrew Zinin Lead Editor A new race to the moon is emerging between the United States and China.