Picture for Heinrich Jiang

Heinrich Jiang

SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection

Jan 24, 2024
Viaarxiv icon

Is margin all you need? An extensive empirical study of active learning on tabular data

Oct 07, 2022
Figure 1 for Is margin all you need? An extensive empirical study of active learning on tabular data
Figure 2 for Is margin all you need? An extensive empirical study of active learning on tabular data
Figure 3 for Is margin all you need? An extensive empirical study of active learning on tabular data
Figure 4 for Is margin all you need? An extensive empirical study of active learning on tabular data
Viaarxiv icon

Predicting on the Edge: Identifying Where a Larger Model Does Better

Feb 15, 2022
Viaarxiv icon

SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption

Jun 29, 2021
Figure 1 for SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
Figure 2 for SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
Figure 3 for SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
Figure 4 for SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
Viaarxiv icon

Churn Reduction via Distillation

Add code
Jun 04, 2021
Figure 1 for Churn Reduction via Distillation
Figure 2 for Churn Reduction via Distillation
Figure 3 for Churn Reduction via Distillation
Figure 4 for Churn Reduction via Distillation
Viaarxiv icon

Active Covering

Jun 04, 2021
Figure 1 for Active Covering
Figure 2 for Active Covering
Figure 3 for Active Covering
Figure 4 for Active Covering
Viaarxiv icon

MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking

Apr 01, 2021
Figure 1 for MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
Figure 2 for MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
Figure 3 for MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
Figure 4 for MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
Viaarxiv icon

Locally Adaptive Label Smoothing for Predictive Churn

Feb 09, 2021
Figure 1 for Locally Adaptive Label Smoothing for Predictive Churn
Figure 2 for Locally Adaptive Label Smoothing for Predictive Churn
Figure 3 for Locally Adaptive Label Smoothing for Predictive Churn
Figure 4 for Locally Adaptive Label Smoothing for Predictive Churn
Viaarxiv icon

Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection

Feb 09, 2021
Figure 1 for Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
Figure 2 for Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
Figure 3 for Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
Figure 4 for Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection
Viaarxiv icon

Stochastic Bandits with Linear Constraints

Jun 17, 2020
Figure 1 for Stochastic Bandits with Linear Constraints
Viaarxiv icon