TS-ICL introduces a probabilistic in-context learning encoder-regressor Transformer that unifies forecasting and imputation for time series via timestamp-aligned regression trained on synthetic causal data.
Title resolution pending
15 Pith papers cite this work, alongside 242 external citations. Polarity classification is still indexing.
15
Pith papers citing it
242
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
First adaptation of Uncertainty Herding to cascaded TD-TSR pipelines via RankFusion and CAPA extensions yields consistent gains over baselines on four table extraction datasets under annotation budgets of 71-500 documents.
TypedCSIP applies typed counterfactual selective intervention pretraining on expert revisions to lift macro-F1 by 0.9-1.3 pp on the LCR-CN Chinese legislative conflict classification benchmark under a pre-registered multi-seed test.
Vigil deploys a proactive agent for full on-call lifecycle support with autonomous self-improvement from human-resolved cases.
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
LLMs using few-shot in-context learning on serialized k-hop subgraphs from synthetic AML scenarios can assess suspiciousness and generate natural-language justifications.
ConRTF adds an edge-constrained fine-grained localization loss to a distribution-based real-time detector to improve boundary accuracy in table structure recognition, claiming up to +1.6 GriTS gains on PubTables-1M while remaining data-efficient.
PHKT uses personalized dynamic hypergraphs and KAN-Transformer to outperform baselines in multi-behavior sequential recommendation on Tmall, RetailRocket, and IJCAI.
A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class.
Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
This survey defines the Federated Continual Learning problem, proposes a taxonomy for approaches, reviews applications and metrics, and identifies open challenges in lifelong privacy-preserving learning on non-stationary distributed data.
DALight-3D achieves a mean Dice of 0.727 with 2.22M parameters on the Medical Segmentation Decathlon BrainTumour benchmark, slightly above the 0.710 Dice of Residual 3D U-Net with 3.20M parameters.
Compares Markov chain, beta regression and multinomial logistic regression for loan default term-structures on mortgage data and reports successive outperformance plus new diagnostics.
citing papers explorer
-
TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
TS-ICL introduces a probabilistic in-context learning encoder-regressor Transformer that unifies forecasting and imputation for time series via timestamp-aligned regression trained on synthetic causal data.
-
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
-
Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines
First adaptation of Uncertainty Herding to cascaded TD-TSR pipelines via RankFusion and CAPA extensions yields consistent gains over baselines on four table extraction datasets under annotation budgets of 71-500 documents.
-
TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification
TypedCSIP applies typed counterfactual selective intervention pretraining on expert revisions to lift macro-F1 by 0.9-1.3 pp on the LCR-CN Chinese legislative conflict classification benchmark under a pre-registered multi-seed test.
-
Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement
Vigil deploys a proactive agent for full on-call lifecycle support with autonomous self-improvement from human-resolved cases.
-
Multi-Label Node Classification with Label Influence Propagation
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
-
Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs
LLMs using few-shot in-context learning on serialized k-hop subgraphs from synthetic AML scenarios can assess suspiciousness and generate natural-language justifications.
-
ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition
ConRTF adds an edge-constrained fine-grained localization loss to a distribution-based real-time detector to improve boundary accuracy in table structure recognition, claiming up to +1.6 GriTS gains on PubTables-1M while remaining data-efficient.
-
PHKT:Personalized Dynamic Hypergraph-enhanced KAN-Transformer for Multi-behavior Sequential Recommendation
PHKT uses personalized dynamic hypergraphs and KAN-Transformer to outperform baselines in multi-behavior sequential recommendation on Tmall, RetailRocket, and IJCAI.
-
Few-Shot Network Intrusion Detection Using Online Triplet Mining
A triplet network using online triplet mining and KNN classifier achieves competitive few-shot performance on network intrusion detection with as few as 10 malicious samples per class.
-
Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation
Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.
-
Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
-
Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data
This survey defines the Federated Continual Learning problem, proposes a taxonomy for approaches, reviews applications and metrics, and identifies open challenges in lifelong privacy-preserving learning on non-stationary distributed data.
-
DALight-3D: A Lightweight 3D U-Net for Brain Tumor Segmentation from Multi-Modal MRI
DALight-3D achieves a mean Dice of 0.727 with 2.22M parameters on the Medical Segmentation Decathlon BrainTumour benchmark, slightly above the 0.710 Dice of Residual 3D U-Net with 3.20M parameters.
-
Modelling the term-structure of default risk under IFRS 9 within a multistate regression framework
Compares Markov chain, beta regression and multinomial logistic regression for loan default term-structures on mortgage data and reports successive outperformance plus new diagnostics.