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

count % of corpus

4 results for “COIL-100”

Random Feature Maps via a Layered Random Projection (LaRP) Framework for Object Classificationcs.CV

LaRP framework improves object classification using random projections.

problem Efficiently approximating nonlinear kernels in high-dimensional spaces.

method Separates linear kernels and nonlinearity using a layered random projection approach.

result Notable improvement in object classification performance.

random projection kernel approximation object classification MNIST COIL-100

2016-02-04abs ↗pdf ↗

Learning Neural Models for End-to-End Clusteringcs.LG

End-to-end neural network clusters data in one pass.

problem Clustering high-dimensional data like images and speech.

method Trains a neural network to directly output cluster assignments based on perceptual similarity.

result Demonstrates promising performance on COIL-100 and TIMIT datasets.

end-to-end clustering neural networks clustering neural models perceptual similarity

2018-07-11abs ↗pdf ↗

Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifoldsstat.ML

ILDM combines diffusion and latent learning for generative modeling on unknown manifolds.

problem Diffusion models struggle with high-dimensional data and lack geometric structure.

method ILDM integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds.

result ILDM significantly improves generation quality compared to standard models.

Generative modeling Diffusion models Latent diffusion models Unknown manifolds Riemannian geometry

2026-08-05abs ↗pdf ↗

Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reductioncs.CV

Proposes a method to learn optimal neighbors and projection matrix in low-dimensional space.

problem Difficulty in precisely measuring similarity and selecting optimal neighbors in high-dimensional space.

method Models similarity and neighbors as variables, optimizing a unified objective function with nonnegative and sum-to-one constraints.

result Optimal similarity and projection matrix learned simultaneously, with adaptive regularization parameter.

dimensionality reduction neighborship learning projection matrix curse of dimensionality nonnegative constraints

2017-09-09abs ↗pdf ↗