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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Re-Encoder”

VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detectioncs.LG

VELC model detects anomalies in time series data better than existing methods.

problem Anomaly detection in time series data.

method VELC model based on Variational AutoEncoder with re-Encoder and Latent Constraint network.

result VELC model outperforms state-of-the-art methods on benchmark datasets.

Anomaly detection Time series Variational AutoEncoder Re-Encoder Latent Constraint network

2019-07-03abs ↗pdf ↗

Efficient Autoregressive Inference for Transformer Probabilistic Modelsstat.ML

Efficiently combines autoregressive and set-based models for joint distributions.

problem Joint distributions over multiple predictions from set-based models.

method Causal autoregressive buffer that caches context and captures dependencies.

result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.

Transformer models autoregressive inference joint distributions set-based models causal buffer

2025-10-10abs ↗pdf ↗

Stochastic Schrödinger Diffusion Models for Pure-State Ensemble Generationstat.ML

SSDMs generate quantum states directly, outperforming classical methods.

problem Generating pure-state quantum representations efficiently.

method Score-based generative model on complex projective manifold.

result SSDMs match target pure-state ensembles by orders of magnitude.

quantum machine learning score-based models pure-state generation Stochastic Schrödinger Diffusion Models Fubini-Study metric

2026-05-05abs ↗pdf ↗

Folded Recurrent Neural Networks for Future Video Predictioncs.CV

Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution o…

2017-12-01abs ↗pdf ↗