geometry

Tag

Cards List
#geometry

@QuantaMagazine: How many lines lie on a cubic surface? (The answer is 27.) A statement that’s been known for nearly 180 years has recen…

X AI KOLs Timeline ↗ · 2026-08-17 Cached

A new mathematical theory is reviving the field of enumerative geometry, allowing mathematicians to solve ancient counting problems in various number systems.

0 favorites 0 likes
#geometry

@pickover: Mathematics. I love this animation by Daniel Piker (@KangarooPhysics). Each dot follows a path, and takes 3.5 hrs to re…

X AI KOLs Timeline ↗ · 2026-08-14 Cached

A mathematics animation by Daniel Piker shows dots following paths and returning to their starting points in 3.5 hours, resembling ants walking.

0 favorites 0 likes
#geometry

The Field Knows: Cross-Dimensional Geometry from Navigation to Black Holes

arXiv cs.AI ↗ · 2026-08-11 Cached

This paper introduces a continuous metric field framework trained by a single causal contrastive loss that unifies geometric structure discovery from robot navigation to black hole emergence, demonstrating zero-shot generalization across dimensions.

0 favorites 0 likes
#geometry

ArchEGraph: A Large-Scale Graph Dataset for Geometry-Topology-Physics Aligned Building Energy Modeling

arXiv cs.LG ↗ · 2026-08-10 Cached

Presents ArchEGraph, a large-scale graph dataset for building energy modeling with aligned geometry, topology, weather, and thermal loads, along with benchmark tasks for graph reconstruction and load prediction.

0 favorites 0 likes
#geometry

@KirkDBorne: The Shape of Data — Geometry-Based Machine Learning and Data Analysis: https://amzn.to/3JRxBZL

X AI KOLs Timeline ↗ · 2026-07-31 Cached

A tweet promoting the book 'The Shape of Data: Geometry-Based Machine Learning and Data Analysis in R' by Colleen M. Farrelly and Yaé Ulrich Gaba, highlighting its practical approach to using geometry and topology in data science.

0 favorites 0 likes
#geometry

Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing

Hugging Face Daily Papers ↗ · 2026-07-30 Cached

This paper introduces the Expert Subspace Separation Index (ESSI) to disentangle route coherence, candidate quality, and candidate-by-context interaction in sparse Mixture-of-Experts language models, revealing a pattern of coherent overlap where routing selects token-relevant experts from a shared geometric neighborhood yet multi-expert computation remains useful.

0 favorites 0 likes
#geometry

Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma

arXiv cs.LG ↗ · 2026-07-24 Cached

This preregistered study tests whether holonomy (a geometric measure) concentrates on active SAE feature planes in the Gemma 2 2B language model. Contrary to the semantic-concentration prediction, active-feature planes carried less holonomy than matched mixed-feature controls, resulting in a narrow operational reversal with the underlying cause remaining open.

0 favorites 0 likes
#geometry

An Analysis of Residual-Stream Geometry Across Transformer Depth

arXiv cs.LG ↗ · 2026-07-22 Cached

This paper proposes a geometric analysis of transformer residual streams across depth, using relative displacement and orthogonal Procrustes analysis to reveal structured regularities in six instruction-tuned models on code generation and translation tasks.

0 favorites 0 likes
#geometry

Dot product: Component vs. Geometric definition

Eli Bendersky ↗ · 2026-07-11 Cached

This article examines the equivalence between the component and geometric definitions of the vector dot product in Euclidean space, providing a geometric proof using the law of cosines and a projection proof using orthonormal basis vectors.

0 favorites 0 likes
#geometry

Otary – Image and Geometry Python Library Now Has Tutorials

Hacker News Top ↗ · 2026-07-08 Cached

Otary, a Python library for image and geometry processing, now has tutorials available to help users understand its capabilities.

0 favorites 0 likes
#geometry

Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence

arXiv cs.LG ↗ · 2026-07-08 Cached

This paper introduces Statistically Meaningful Geometry (SMG), a geometric framework for modeling over-parameterized learning systems as infinite-dimensional non-parametric Orlicz fiber bundles. It proposes that under out-of-distribution stimuli, the system undergoes a gauge symmetry break, leading to the emergence of new causal axes that can distinguish genuine scientific discovery from hallucinations.

0 favorites 0 likes
#geometry

@Phoenixyin13: As one of the world's top geometers and the quantitative king, James Simons' core learning methodology can be summarized as: incubation by the subconscious, stripping away noise, and an extreme aversion to rote memorization. His biography "The Man Who Solved the Market" and his past experiences at Stony Brook University's math department and on Wall Street reveal his unique mode of intellectual operation. Simons solved the most advanced...

X AI KOLs Timeline ↗ · 2026-07-04 Cached

The article summarizes the core learning methodology of world-class geometer and quantitative king James Simons: incubation by the subconscious, stripping away noise, and an extreme aversion to rote memorization, emphasizing deep thinking, leaving mental space, and cross-disciplinary learning through leveraging networks of genius.

0 favorites 0 likes
#geometry

Dispersion loss counteracts embedding condensation in small language models

Hacker News Top ↗ · 2026-07-03 Cached

This paper observes that token embeddings in small language models condense into a narrow cone-like subspace, a phenomenon termed embedding condensation, and proposes a dispersion loss to counteract it, improving generalization.

0 favorites 0 likes
#geometry

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

arXiv cs.LG ↗ · 2026-07-03 Cached

This paper studies the geometric properties of chain-of-thought trajectories in the hidden state space of transformers, introducing effective dimension and kinematic features to predict task hardness and solution correctness from early tokens.

0 favorites 0 likes
#geometry

@paperpaper886: Last week, I discussed the current state and future of AI4Math with a friend from the math department. He said that current AI is already powerful enough as an auxiliary tool, but there is still a long way to go for AI to achieve independent discovery.

X AI KOLs Timeline ↗ · 2026-07-02 Cached

Discussed the current state and future of AI in mathematics. Citing an example, ChatGPT 5.5 Pro autonomously solved the farthest pair problem in high-dimensional computational geometry, which had been stuck for years, demonstrating AI's potential in mathematical discovery.

0 favorites 0 likes
#geometry

The Field Equation, living shader geometry folded into a breathing object

Hacker News Top ↗ · 2026-07-02 Cached

An interactive web-based shader visualization that generates living geometry from a field equation, allowing users to explore and animate the forms.

0 favorites 0 likes
#geometry

@Gorden_Sun: Open-sourcing another math skill that converts math problems into GGB files. If converting a geometry problem from an image, the model needs vision capabilities (Opus or GPT). If the problem involves moving points, it generates interactive GGB files where you can freely move points to see how the figure changes. This helps teachers digitize problems from textbooks and aids students in understanding.

X AI KOLs Timeline ↗ · 2026-07-02 Cached

Gorden_Sun has open-sourced the Math2GGB skill, which converts geometry math problems into interactive GeoGebra files. It supports three modes: static reproduction, clean interaction, and dynamic teaching, helping teachers digitize problems and assisting students in comprehension.

0 favorites 0 likes
#geometry

Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs

arXiv cs.LG ↗ · 2026-06-30 Cached

This paper introduces a normal-fan geometry for finite-horizon adversarial MDPs with fixed transitions, developing a face-crossing price that separates consequential from harmless non-stationarity. It shows that dynamic regret decomposes into intrinsic priced face motion plus within-face selection error.

0 favorites 0 likes
#geometry

Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing

arXiv cs.AI ↗ · 2026-06-29 Cached

This paper introduces SD-GPS, a solver-driven framework for geometry problem solving that uses autoformalization guided by solver feedback and verified theorem proposing to overcome bottlenecks in neuro-symbolic systems.

0 favorites 0 likes
#geometry

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

arXiv cs.CL ↗ · 2026-06-25 Cached

This paper investigates the geometric relationship between directions in language model activations that detect a behavior versus those that control it, finding that for hallucination detection they are nearly orthogonal (cosine ~0.12), while for output format they align perfectly, challenging a common assumption in mechanistic interpretability.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback