← Back to all news
arXiv AI By Qingde Li, Qingqi Hong, Jie Tian

Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations

Read the original on arXiv AI →

Neuro‑Symbolic Geometric Abstraction (NeuSOGA) is a framework that converts raw observations into explicit symbolic mathematical representations. It achieves this by sequentially generating topological and geometric abstractions, using tools such as Euclidean Distance Transforms, Segment Anything, and Implicit Area Splines. The resulting analytical implicit models are interpretable, editable, and support arbitrary‑order smoothness, additive composition, and closed‑form evaluation across diverse sensing modalities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 18

NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction

NeuSOGA3D is a hybrid neuro‑symbolic framework that reconstructs 3D geometry from unorganized point clouds by combining learned perceptual priors with explicit symbolic geometric reasoning. It projects point clouds onto orthographic planes, builds symbolic implicit spline representations, and fuses them via shape‑preserving constructive solid geometry to produce a coarse visual hull. Additional detail is added through cross‑sectional decomposition and volumetric reconstruction with Partial Shape‑Preserving Splines, yielding CAD‑compatible, structurally meaningful models across all 40 ModelNet40 categories.

By Qingde Li, Qingqi Hong, Zihan Li, Jie Tian
computer-visionbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 10

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning

The paper introduces a framework that combines a Geometric Vision Parser and a Symbolic Solver to enable a Large Language Model to solve complex plane geometry problems. By translating diagrams into symbolic representations and performing formal deductions, the approach reduces hallucinations and produces interpretable, human-like solutions. Experiments on a new benchmark from 2025 Chinese Zhongkao exams show performance comparable to Gemini 2.5 Pro.

By Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou, Yan Cao, Xin Shen, Dongcai Lu, Yi Zhou
llmsmultimodalbenchmarkssafety
More like this →