A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
UniLat3D introduces geometry-appearance unified latents for single-stage 3D generation, evaluated against state-of-the-art models like Hunyuan3D2.1 and TRELLIS.
Dhruva Karkada, D. Korchinski, A. Nava, et al.
This paper proves that translation symmetries in language statistics explain the geometric structures (circles, manifolds) in LLM word embeddings, deriving manifold geometry analytically and showing robustness to perturbations.
Mark V. Pauly, Richard Keiser, Leif Kobbelt, et al.
A hybrid geometry representation combining unstructured point clouds with moving least squares implicit surfaces enables versatile free-form shape modeling with boolean operations and topology control.
Gunnar Carlsson
This paper introduces topological data analysis (TDA) as a framework for extracting qualitative, large-scale structure from high-dimensional, noisy point clouds using geometry and topology.
Zhicheng Cai, Xinyuan Guo, Hanlin Wu, et al.
Reveals PPO-Clip's Euclidean geometry flaw causing exploration collapse in LLM RL and proposes Riemannian Isometric Policy Optimization (RIPO) for balanced exploration.