Tag
A new mathematical theory is reviving the field of enumerative geometry, allowing mathematicians to solve ancient counting problems in various number systems.
A mathematics animation by Daniel Piker shows dots following paths and returning to their starting points in 3.5 hours, resembling ants walking.
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.
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.
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.
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.
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.
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.
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.
Otary, a Python library for image and geometry processing, now has tutorials available to help users understand its capabilities.
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.
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.
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.
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.
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.
An interactive web-based shader visualization that generates living geometry from a field equation, allowing users to explore and animate the forms.
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.
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.
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.
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.