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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “feature-aware”

Hierarchical Feature-Aware Trackingcs.CV

A new tracking method using expert selection and feature fusion.

problem Efficient visual tracking with multiple component trackers.

method Pre-event selection of experts based on past performance and feature fusion.

result Superior performance compared to ensembled trackers on public datasets.

tracking feature-aware pre-event post-event ensemble

2019-10-13abs ↗pdf ↗

Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasterscs.LG

Develops a method to continuously audit black-box conditional quantile forecasts.

problem Continuous monitoring of black-box forecasts under changing data streams and regimes.

method Distribution-free and game-theoretic testing framework for non-i.i.d. losses.

result Derives finite-time detection guarantees for miscalibrated forecasts based on features.

conditional quantile forecasting black-box models continuous monitoring game-theoretic testing non-i.i.d. losses

2026-07-13abs ↗pdf ↗

What Does It Take to Build a Performant Selective Classifier?cs.LG

New analysis reveals gaps in selective classifiers, guiding improvements.

problem Improving selective classifiers to match perfect-ordering oracle performance.

method Formalized selective classification gap, decomposed into five sources of looseness.

result Monotone post-hoc calibration has limited impact on closing the gap.

Selective classifiers Bayes noise approximation error ranking error statistical noise

2025-10-23abs ↗pdf ↗

HGV4Risk: Hierarchical Global View-guided Sequence Representation Learning for Risk Predictioncs.LG

Proposes a novel model for healthcare and SME credit risk prediction.

problem Lack of guidance from global view in sequence representation learning for time series modeling.

method Hierarchical Global View-guided (HGV) sequence representation learning framework with GGE and

β

-Attn modules.

result Competitive prediction performance compared with other known baselines.

risk prediction deep learning sequence representation global view attention mechanism

2022-11-15abs ↗pdf ↗