Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,236 papers · 148 categories

Trend · papers per month

4794140187 · Jun 202019922001200920182026
48 results for 3D fields

VecMol generates 3D molecules as continuous vector fields, overcoming modality and geometry constraints.

problem Challenges in generating 3D molecules, especially in drug discovery and materials science.
method VecMol reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, parameterized by a neural field and generated using a latent diffusion model.
result Vector-field-based representations show promise for 3D molecular generation, validated on benchmarks.

We show that 3D gravity, in its pure connection formulation, admits a natural 6D interpretation. The 3D field equations for the connection are equivalent to 6D Hitchin equations for the Chern-Simons 3-form in the total space of the principal bundle over the 3-dimensional base. Turning this construction around one gets …

2016-05-24abs ↗pdf ↗

Proposes a model to generate 3D-aware images from 2D images.

problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.

3D Steerable CNNs learn equivariant features for 3D data.

problem Learning rotationally equivariant features in volumetric data.
method SE(3)-equivariant convolutions using steerable kernel basis.
result 3D Steerable CNNs are effective for protein structure classification and amino acid propensity prediction.

Study 3d N=1 vacua from M-theory compactification on Spin(7) space.

problem Quantum corrections in 3d N=1 vacua from M-theory compactification.
method Use Higgs bundles to analyze 3d N=1 vacua and track corrections.
result Topological anomalies are robust and calculable in 3d effective field theory.

InSphereNet uses infilling spheres for 3D object classification, improving accuracy with fewer parameters.

problem 3D object classification using points, voxels, or images.
method Constructs infilling spheres from signed distance field (SDF) for classification.
result InSphereNet achieves superior accuracy with fewer inputs and parameters.

The paper explores the connection between 3d gravity and Chern-Simons theory using affine group connections.

problem Exploring the relationship between 3d gravity and Chern-Simons theory.
method A variational problem of Chern-Simons type on a principal fiber bundle with general affine group structure is studied. The connection is established through a generalized notion of extension and reduction of connections.
result Established a correspondence between 3d gravity and Chern-Simons theory using affine group connections.

Generative model calibrates 3D battery cathode morphologies from 2D images.

problem Calibrate 3D morphologies of all-solid-state battery cathodes from 2D microscopy images.
method Combining GANs with excursion sets of Gaussian random fields.
result Calibrated digital twins enable systematic exploration of morphological scenarios.

Researchers found 5 local fields to uniquely describe 3D director fields, related through 6 differential relations.

problem Understanding the compatibility conditions for 3D director fields.
method Employed the method of moving frames.
result A director field is fully determined by five local fields related through six differential relations.

Study Schrödinger evolution on surfaces in 3D contact sub-Riemannian manifolds.

problem Analyzing the Schrödinger evolution on surfaces embedded in 3D contact sub-Riemannian manifolds.
method Relating self-adjointness of the Schrödinger operator to geometric invariants of the foliation.
result Classification of self-adjoint extensions yielding disjoint dynamics.

AniDS improves molecular force field modeling by learning anisotropic noise.

problem Molecular force field modeling suffers from oversimplified assumptions about atomic motions.
method AniDS introduces anisotropic noise generation for better modeling of directional and structural variability.
result AniDS outperforms existing methods on benchmarks, achieving significant improvements in force prediction accuracy.

We present a string inspired 3D Euclidean field theory as the starting point for a modified Ricci flow analysis of the Thurston conjecture. In addition to the metric, the theory contains a dilaton, an antisymmetric tensor field and a Maxwell-Chern Simons field. For constant dilaton, the theory appears to obey a Birkhof…

2003-06-27abs ↗pdf ↗

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.

Study magnetic flows on 3D contact sub-Riemannian manifolds using Rumin complex.

problem Understanding magnetic flows on 3D contact sub-Riemannian manifolds.
method Introducing horizontal magnetic flows via closed Rumin differential two-forms and analyzing the lifted sub-Riemannian structure.
result Horizontal magnetic flows can be interpreted as geodesic flows on a suitably lifted structure, which is of Engel type when the magnetic field is non-vanishing.

Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.

problem Need for basic methods in 3D action recognition.
method Roweisposes uses Roweis discriminant analysis for generalized subspace learning.
result Roweisposes is effective for 3D action recognition.

Improved 3D scene understanding from partial point sets using multiview fusion.

problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.

This paper defines directional derivatives and solves Maxwell's equations in curved 3D space.

problem Analyzing electromagnetic fields in curved non-flat 3D space.
method Defined directional derivatives and used Frenet formulas to express Serret-Frenet relations. Solved Maxwell's equations for electric and magnetic fields.
result Solved Maxwell's equations for electromagnetic fields in curved 3D space.

The paper tackles mapping tori by proposing a new approach to 3d-3d correspondence.

problem No existing approach fully describes 3d N=2N=2 SCFTs for all types of 3-manifolds.
method Systematic study of 3d N=2N=2 gauge theories with non-linear matter fields.
result Recovery of 3-manifold invariants from T[M3]T[M_3] indices and proposal of new qq-series invariants.

New method uses resurgent analysis to determine growth rate of quantum field theory coefficients.

problem Determining the growth rate of quantum field theory coefficients.
method Resurgence analysis on the Stokes line, leading to transseries decomposition and continued across natural boundary.
result Essential exponent of growth has Cardy-like interpretation as effective central charge.

Study of IR phases in 3D class R theories linked to non-hyperbolic 3-manifolds.

problem Understanding IR phases of 3D class R theories associated with non-hyperbolic 3-manifolds.
method Analysis of IR phenomena through `exceptional' Dehn fillings and gauging of flavor symmetries.
result 3D class R theories associated with certain atoroidal non-hyperbolic 3-manifolds exhibit supersymmetry enhancement at low energy.

3D manifolds with certain projective fields are projectively flat.

problem Geodesic rigidity of Levi-Civita connections with essential projective vector fields.
method Proved projective flatness for specific manifolds with projective vector fields.
result Connected 3D Riemannian and closed semi-Riemannian manifolds with non-linearizable projective singularities are projectively flat.

A scalable deep learning framework accelerates training of large neural networks for solving 3D Poisson equations.

problem Training large-scale neural networks for solving complex PDEs efficiently.
method Combines multigrid techniques with distributed deep learning to accelerate training.
result Solves 3D Poisson equations up to 512x512x512 resolution efficiently.