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.

169,341 papers · 148 categories

Trend · papers per month

23456890 · May 202619922001200920182026
48 results for 3D coordinates

3D dust map of the Milky Way improves resolution and accuracy.

problem Reconstructing the 3D dust distribution in the Milky Way.
method Gaussian process regression on spherical coordinates with iterative grid refinement.
result Improved 3D dust map with increased resolution and accuracy.

Proposes local coordinate frames for improving model performance in complex dynamical systems.

problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.

HLTF generates chemically valid 3D molecules with improved topology control.

problem Generating chemically valid 3D molecules is challenging due to bond topology errors.
method HLTF uses a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures.
result HLTF achieves high validity and uniqueness on QM9 and GEOM-DRUGS datasets.

Study how large-scale flows align small-scale vortices in 3D Euler equations.

problem Understanding how large-scale flows align small-scale vortices in 3D Euler equations.
method Constructing a Lagrangian coordinate to identify when the Lie bracket is zero and investigating the locality of the pressure term.
result Clarified conditions under which small-scale vortices are aligned by large-scale flows.

Improved 3D LiDAR data classification using product coefficients.

problem Enhancing accuracy in 3D LiDAR data classification.
method Introducing product coefficients derived from measure theory as additional features in the classification process, alongside PCA.
result Significant improvement in classification accuracy with product coefficients.

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.

DECAF optimizes molecular graphs for ensemble properties, improving drug design accuracy.

problem Designing molecules with ensemble properties rather than single conformations.
method DECAF uses Boltzmann-expected design with decoupled annealing flows to optimize molecular graphs.
result DECAF optimizes molecular graphs to shift ensemble properties towards targets, improving accuracy over single-conformer methods.

A neural atlas simplifies 3D geometry simulation by avoiding meshing.

problem Simulation of complex 3D geometries with thin features or non-trivial topology.
method Learned geometric representation of overlapping volumetric coordinate charts, trained from point-cloud or level-set data.
result The learned atlas enables different solvers without re-meshing or re-parametrization.

Paper uses tensor regression to analyze point clouds for process optimization.

problem Challenges in modeling and analyzing high-dimensional point cloud data.
method Utilizes multilinear algebra and tensor regression techniques.
result Successfully models and links point cloud variational patterns to process variables.

STRING improves 2D and 3D position encodings for better performance.

problem Efficient and accurate position encoding for 2D and 3D applications.
method STRING extends Rotary Position Encodings with a unifying theoretical framework, maintaining translation invariance and low computational cost.
result STRING shows substantial gains in open-vocabulary object detection and robotics.

Detect spacetime curvature without rulers and clocks in 3D.

problem Detecting spacetime curvature without traditional measurement tools.
method Generalized results from 2D to 3D spacetime, proving well-stitched spacetime for conformally flat cases.
result A 3D spacetime is well-stitched if and only if it is conformally flat, providing a tool for curvature detection.

Only helicoids and spheres satisfy a specific surface equation in 3D space.

problem Characterizing surfaces in 3D space based on a specific differential equation.
method Analyzing ruled and quadric surfaces in 3D Euclidean space satisfying a particular differential equation.
result Helicoids and spheres are the only surfaces satisfying the given differential equation.

End-to-end model predicts protein interfaces from atomic coordinates.

problem Improving protein interface prediction using large datasets.
method Developed SASNet, an end-to-end learning model using only atomic coordinates.
result SASNet outperforms state-of-the-art methods trained on gold-standard data.

New classification of complex hypersurfaces in 3D.

problem Classifying simply-transitive Levi non-degenerate hypersurfaces in C3\mathbb{C}^3.
method Novel Lie algebraic approach, new coordinate-free formula for quartic tensor.
result Unique non-tubular model with geometric relations to planar equi-affine geometry.

Method predicts spinal deformity progression using 3D models and machine learning.

problem Predicting the progression of spinal deformities in scoliosis patients.
method Discriminative probabilistic manifold embedding for 3D spine models.
result 81% classification rate and 2.1° prediction difference in curve angulation.

A 1D-fully convolutional network classifies 3D point clouds efficiently.

problem Efficiently classifying 3D point clouds with reliable features.
method Directly consumes terrain-normalized points and spectral data, implicitly learning contextual features.
result Ranked second in ISPRS 3D Semantic Labeling Contest with 81.6% overall accuracy.

Unified framework for nuclear reactor perturbation analysis using CNN and LSTM.

problem Monitoring reactor cores for safety and perturbation identification.
method 3D-CNN and LSTM networks for frequency and time domain analysis, respectively.
result High accuracy in recognising perturbation type and precise source localisation in frequency domain.

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.

Deep learning predicts protein structures accurately.

problem Predicting the 3D structure of proteins from amino acid sequences.
method Embeddings and deep learning models for backbone atom distance matrices and torsion angles.
result Competitive results in CASP13 and CASP12, surpassing previous winners.

New method uses scalar-based models to approximate spherical tensors efficiently.

problem Efficiently approximating spherical tensors with equivariant functions.
method Expressing equivariant functions as the product of a scalar function and a small tensor basis.
result Approximations are fast, simple to implement, and accurate in practical settings.

Classifies 3D non-degenerate left-symmetric algebras.

problem Classifying left-symmetric algebras in 3D.
method Using Nijenhuis geometry and algebraic independence of coefficients in characteristic polynomial.
result Classification of differentially non-degenerate LSA in dimension 3.

TarMAC targets and coordinates multi-agent communication for cooperative tasks.

problem Coordinating multi-agent reinforcement learning in partially observable environments.
method Targeted multi-round communication approach without supervision.
result Improved performance and sample efficiency in diverse environments.

Neural network learns atomic coordinates from Patterson maps in a simplified case.

problem Training a neural network to infer atomic coordinates from Patterson maps.
method Synthetic data training, centering output maps, removing centrosymmetric inversion, and adding empty space.
result The network can generalize to infer atom positions from Patterson maps not in the training set.

New method reconstructs 3D protein structures from cryo-EM images.

problem Reconstructing continuous protein structures from noisy cryo-EM projections.
method Neural network-based approach that models structural heterogeneity in Fourier space.
result Demonstrated successful ab initio reconstruction of 3D protein complexes.

New algorithm beats traditional methods for seismic data interpolation.

problem Efficiently filling in missing seismic data volumes.
method Primal-dual alternating approach using matrix factors and block-coordinate algorithm.
result Successfully interpolated a large 5D seismic data volume from a 3D model.

The paper constructs and classifies 3D Walker manifolds with specific structures.

problem Classifying 3D Walker manifolds with specific paracontact structures.
method Constructing structures using a unit space-like vector field and a function, characterizing the Lorentzian metric.
result Necessary and sufficient conditions for the manifold to belong to specific classes of almost paracontact metric manifolds.

New neural network predicts accurate protein complex structures.

problem Predicting accurate protein complex structures from atomic coordinates.
method Rotation-equivariant neural network combining point-based representation, equivariance, local convolutions, and hierarchical subsampling.
result Significant improvement in identifying accurate structural models.

Method estimates section thickness and XY anisotropy in ssEM images.

problem Accurate 3D reconstructions require precise section thickness and XY anisotropy estimates.
method Non-parametric Bayesian regression of image statistics.
result Method has lower estimation error compared to existing methods.

Neural network Kalman filtering improves 3D ultrasound object tracking.

problem Accurate and robust 3D positional estimation from 2D ultrasound data.
method Neural network training for out-of-plane offset estimation, combined with Kalman filtering.
result Mean error of 0.1mm for simulated data, 0.2mm for experimental data.

Bayesian model classifies X-ray binaries as black holes, neutron stars, or bursters.

problem Uncertainty in classifying X-ray binaries as black holes or neutron stars.
method Developed a Bayesian statistical model using 3D coordinates from X-ray spectral data.
result Accurate prediction of X-ray binary types, but non-pulsing neutron stars near black hole boundary misclassified.

Extends Wigner's representation to study super hyperbolic geometry.

problem Understanding geometry in super hyperbolic three-space.
method Extended Wigner's representation of the Lorentz group to OSp_C(1|2) and applied to Minkowski (3,1|4)-dimensional super space.
result Proof of divergence of the volume of a typical ideal tetrahedron in super hyperbolic three-space.