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

8 results for “target-aware”

Hierarchical Target-Attentive Diagnosis Prediction in Heterogeneous Information Networkscs.LG

HTAD predicts diagnoses from EHRs using target-aware attention.

problem Lack of specificity in aggregating clinical records for diagnosis prediction.

method Hierarchical target-attentive mechanism for EHRs.

result Target-aware attention significantly improves diagnosis prediction performance.

Electronic Health Records Heterogeneous Information Networks Diagnosis Prediction Attention Mechanism Hierarchical Structure

2019-12-22abs ↗pdf ↗

Single-Shot Domain Adaptation via Target-Aware Generative Augmentationcs.CV

Paper proposes SiSTA for single-shot domain adaptation using target-aware generative augmentation.

problem Adapting models from source to target domains with limited target data.

method Fine-tunes a generative model on a single-shot target and uses novel sampling strategies for synthetic data.

result Improves performance by up to 20% over existing baselines in face attribute detection.

domain adaptation single-shot target-aware generative augmentation synthetic data

2022-10-29abs ↗pdf ↗

Supervised Dynamic Dimension Reduction with Deep Neural Networkstat.ML

Paper proposes SDDP for improving time series forecasting with high-dimensional predictors.

problem Improving time series forecasting with high-dimensional predictors.

method SDDP framework that incorporates target variable and lagged observations into factor extraction process.

result SDDP improves predictive accuracy in time series forecasting.

dimension reduction time series forecasting deep neural networks principal component analysis forecasting accuracy

2025-08-05abs ↗pdf ↗

Weighted Training for Cross-Task Learningcs.LG

TAWT improves cross-task learning efficiency and guarantees.

problem Improving cross-task learning efficiency and theoretical understanding.

method Target-Aware Weighted Training (TAWT) minimizing representation-based task distance.

result TAWT achieves non-asymptotic learning-theoretic guarantees and is effective in NLP tasks.

cross-task learning weighted training representation-based task distance BERT natural language processing

2021-05-28abs ↗pdf ↗

Target-Focused Feature Selection Using a Bayesian Approachcs.LG

In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value. The need for highly confident models with an extremely frugal acquisition of features can be addressed by allowing a feature…

2019-09-15abs ↗pdf ↗

Resource-Constrained Adaptive Inference for Sequential Pricingstat.ML

A new pricing controller handles resource constraints to infer target prices effectively.

problem Resource constraints prevent fixed-price inference, leading to support exclusion.

method Formalizes support-exclusion failure, designs a target-aware controller, and uses a realized information clock.

result The controller can certify feasible target bands and log continuous local densities, leading to polynomial rates of inference.

pricing resource constraints inference local non-identification realized information clock

2026-06-02abs ↗pdf ↗

Target-agnostic Source-free Domain Adaptation for Regression Taskscs.LG

TASFAR adapts regression models without labeled source data.

problem Lack of labeled source data for domain adaptation.

method Uses prediction confidence to estimate target label distribution and calibrate source model.

result Substantially reduces errors in various regression tasks.

domain adaptation source-free regression prediction confidence label density map

2023-12-01abs ↗pdf ↗

Accelerating Inhibitor Discovery With A Deep Generative Foundation Model: Validation for SARS-CoV-2 Drug Targetsq-bio.QM

Deep generative model discovers inhibitors for unknown targets.

problem Discovering novel inhibitor molecules for unknown drug targets.

method Deep generative framework trained on protein sequences, small molecules, and interactions.

result Micromolar-level inhibition observed for two out of four synthesized candidates, including activity against SARS-CoV-2 variants.

inhibitor discovery deep generative model SARS-CoV-2 main protease spike protein

2022-04-19abs ↗pdf ↗