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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “source-only”

TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selectioncs.LG

TopoGeoScore selects robust checkpoints using only source-domain representations.

problem Selecting robust checkpoints without target-domain labels or samples.

method Constructs class-conditional mutual k-nearest-neighbour graphs and extracts three interpretable signals.

result Source representations contain measurable global-local-topological evidence of robustness.

OOD robustness source-only checkpoint selection self-supervised geometric scoring

2026-05-09abs ↗pdf ↗

Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMsstat.ML

Framework for domain adaptation using pseudo-labels from unlabeled data.

problem Improving prediction accuracy in target domain with covariate shift.

method Kernel GLMs with labeled and pseudo-labeled data, using imputation model for target data.

result Non-asymptotic excess-risk bounds for effective labeled sample size.

unsupervised domain adaptation covariate shift kernel GLMs pseudo-labeling robust model selection

2026-03-19abs ↗pdf ↗

TILT: Target-induced loss tilting under covariate shiftcs.LG

TILT improves target domain performance by penalizing an auxiliary component on unlabeled target inputs.

problem Improving performance on target domain under covariate shift.

method TILT uses a novel objective function to decompose the source predictor and penalize an auxiliary component on unlabeled target inputs.

result TILT improves target domain performance over source-only training and other baselines.

unsupervised domain adaptation covariate shift target-side penalty auxiliary component sparse ReLU networks

2026-05-14abs ↗pdf ↗

Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shiftcs.LG

Paper improves bike-sharing demand prediction by adapting to changing patterns.

problem Improving bike-sharing demand prediction under temporal domain shifts.

method Gen-ROTDA, a robust optimal transport-guided residual domain adaptation framework.

result Gen-ROTDA achieves the lowest MAE and is the best OT-family method on average.

bike-sharing demand prediction domain adaptation temporal shift robust transport

2026-05-22abs ↗pdf ↗

Training Neural Networks on Data Sources with Unknown Reliabilitycs.LG

Improves neural network performance by dynamically adjusting model weights based on source reliability.

problem Training neural networks on data from unreliable sources leads to poor performance.

method Dynamic re-weighting strategy using likelihood tempering to adjust model weights based on estimated source reliability.

result Significant improvement in model performance when trained on mixtures of reliable and unreliable data sources.

neural networks reliability dynamic re-weighting likelihood tempering supervised learning

2022-12-06abs ↗pdf ↗

FinGPT: Democratizing Internet-scale Data for Financial Large Language Modelscs.CL

FinGPT democratizes financial data for LLMs, enabling innovation.

problem Limited financial text datasets and disparities between general and financial text data.

method Automates collection and curation of real-time financial data from diverse Internet sources, fine-tuning with RLSP and LoRA.

result Democratizes access to financial data for LLMs, enabling innovation.

Financial LLMs Data democratization Reinforcement Learning Low-rank Adaptation Robo-advisor

2023-07-19abs ↗pdf ↗