arXiv AI June 9, 2026 By Chenrui Wang, Yixuan Qiu

Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections

arXiv:2606. 07574v1 Announce Type: cross Abstract: Manifold-constrained hyper-connections (mHCs) have recently been proposed as a principled extension of hyper-connections, where the residual mixing matrices are constrained to be doubly stochastic via projection onto the Birkhoff polytope.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 2

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

arXiv:2601. 21579v2 Announce Type: replace-cross Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability.

By Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides, Danilo Mandic

benchmarks

arXiv Machine Learning

Jun 15

Scalable Deep Unfolding of Conic Optimizers

arXiv:2606. 13825v1 Announce Type: cross Abstract: Deep unfolding (DU) accelerates iterative optimizers by introducing learnable components and training them through unrolled iterations, but extending DU to the large-scale semidefinite programs (SDPs) common in robotics has remained limited.

By Alex Oshin, Rahul Vodeb Ghosh, Evangelos A. Theodorou

robotics benchmarks

arXiv AI

Jul 21

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks

arXiv:2601. 02451v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test.

By Subhankar Mishra

llms benchmarks

arXiv Machine Learning

Jun 9

Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming

arXiv:2606. 08638v1 Announce Type: cross Abstract: Recent research has developed practical, parallelizable first-order methods for large scale linear programming, but performance is highly dependent on hyperparameter selection.

By Siddharth Prasad, Dravyansh Sharma

benchmarks

arXiv AI

Jul 2

SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling

arXiv:2607. 00095v1 Announce Type: cross Abstract: Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics.

By Alaina Kolli, Theodoros Xenakis, Utkarsh Utkarsh, Pengfei Cai, Rafael Gomez-Bombarelli, Alan Edelman, Christopher Vincent Rackauckas

diffusion benchmarks

arXiv Machine Learning

Jun 11

A Riemannian Approach to Low-Rank Optimal Transport

arXiv:2606. 12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent updates that require careful hyperparameter tuning and ignore the optimization landscape's curvature.

By Pratik Jawanpuria, Bamdev Mishra

benchmarks

Related stories

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

Scalable Deep Unfolding of Conic Optimizers

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks

Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming

SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling

A Riemannian Approach to Low-Rank Optimal Transport