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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “structure-guided”

Structure of Motion under Constraints and non-Holonomic Path-Following on

R^3

math.DS

Study of motion constraints and path-following on 3D space.

problem Path-following with non-holonomic constraints on

R^3

method Exploration of geometric structure and construction of guiding vector fields.

result General principles for constructing guiding vector fields for path-following.

motion constraints non-holonomic path-following 3D space geometric structure guiding vector fields

2026-04-10abs ↗pdf ↗

Flows of conformally coclosed

G_2

-structures with dilatonmath.DG

Study $G_2$ -flows reducing to complex geometry flows, focusing on $G_2$ -anomaly and $G_2$ -Laplacian coflow.

problem Investigate flows of

G_2

-structures in relation to complex geometry.

method Analyze

G_2

-Laplacian coflow and

G_2

-anomaly flow, compare their properties.

result Compare

G_2

-anomaly flow to

G_2

-Laplacian coflow, investigate short-time existence and fixed points.

G2-structures complex geometry flows anomaly Laplacian coflow

2025-11-26abs ↗pdf ↗

Deep Reinforcement Learning Methods for Structure-Guided Processing Path Optimizationcs.LG

Deep RL optimizes processing paths to desired material structures.

problem Optimizing processing paths to achieve desired material properties.

method Deep reinforcement learning guided by structure representations and reward signals.

result Algorithm learns to find optimal paths to target structures in material space.

reinforcement learning materials design processing optimization structure-guided deep learning

2020-09-21abs ↗pdf ↗

Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approachq-fin.PM

Reinforcement learning for continuous-time risk-sensitive asset allocation

problem Continuous-time risk-sensitive asset allocation

method Free energy-entropy duality reformulation and

q

-learning actor-critic method

result Optimal policy learning with high accuracy

reinforcement learning risk-sensitive asset allocation free energy entropy duality

2026-06-18abs ↗pdf ↗

Geometry-Complete Diffusion for 3D Molecule Generation and Optimizationcs.LG

GCDM generates valid large 3D molecules and optimizes existing molecules.

problem Lack of geometric properties in 3D molecule generation models.

method Introduces Geometry-Complete Diffusion Model (GCDM) using equivariant GNNs.

result Significantly outperforms existing models in 3D molecule generation and optimization.

3D Molecule Generation Diffusion Models Geometric Properties Equivariant GNNs Molecular Optimization

2023-02-08abs ↗pdf ↗