Picture for Robert Nowak

Robert Nowak

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning

Add code
Jun 15, 2024
Viaarxiv icon

Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning

Jun 07, 2024
Viaarxiv icon

SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP

Jun 04, 2024
Viaarxiv icon

Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments

Add code
Feb 11, 2024
Viaarxiv icon

Learning from the Best: Active Learning for Wireless Communications

Jan 23, 2024
Viaarxiv icon

DIRECT: Deep Active Learning under Imbalance and Label Noise

Dec 14, 2023
Figure 1 for DIRECT: Deep Active Learning under Imbalance and Label Noise
Figure 2 for DIRECT: Deep Active Learning under Imbalance and Label Noise
Figure 3 for DIRECT: Deep Active Learning under Imbalance and Label Noise
Viaarxiv icon

Looped Transformers are Better at Learning Learning Algorithms

Add code
Nov 21, 2023
Viaarxiv icon

Multi-task Representation Learning for Pure Exploration in Bilinear Bandits

Nov 01, 2023
Figure 1 for Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
Figure 2 for Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
Viaarxiv icon

On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation

Sep 04, 2023
Figure 1 for On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
Viaarxiv icon

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

Add code
Jun 15, 2023
Figure 1 for Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Figure 2 for Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Figure 3 for Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Figure 4 for Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Viaarxiv icon