#riemannian-manifolds News & Analysis

3 articles tagged with #riemannian-manifolds. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · Mar 127/10

🧠

Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences

Researchers introduce Gradient Flow Drifting, a new mathematical framework for generative AI models that connects the Drifting Model to Wasserstein gradient flows of KL divergence under kernel density estimation. The framework includes a mixed-divergence strategy to avoid mode collapse and extends to Riemannian manifolds for improved semantic space applications.

$KL

AINeutralarXiv – CS AI · 5d ago6/10

🧠

A Geometric Theory of Cognition for Machine Intelligence

Researchers propose a geometric framework for machine intelligence where cognitive computation emerges from Riemannian gradient flow on learned latent manifolds, eliminating the need for explicit memory modules. The approach demonstrates superior robustness across reinforcement learning tasks involving partial observability, sensory disruptions, and long-horizon prediction compared to feedforward baselines.

AINeutralarXiv – CS AI · May 126/10

🧠

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds

Researchers introduce intrinsic Muon (iMuon), a unified optimization framework that extends the Muon optimizer to Riemannian manifolds while preserving symmetries and enabling closed-form solutions. The approach demonstrates applications in LLM fine-tuning, image classification, and subspace learning with convergence guarantees dependent only on manifold dimension rather than factor conditioning.