Picture for Kee-Eung Kim

Kee-Eung Kim

Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning

Add code
Feb 13, 2024
Viaarxiv icon

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

Add code
Feb 11, 2024
Viaarxiv icon

AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation

Add code
Nov 03, 2023
Viaarxiv icon

Adapting Text-based Dialogue State Tracker for Spoken Dialogues

Add code
Aug 30, 2023
Figure 1 for Adapting Text-based Dialogue State Tracker for Spoken Dialogues
Figure 2 for Adapting Text-based Dialogue State Tracker for Spoken Dialogues
Figure 3 for Adapting Text-based Dialogue State Tracker for Spoken Dialogues
Figure 4 for Adapting Text-based Dialogue State Tracker for Spoken Dialogues
Viaarxiv icon

Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions

Add code
Oct 25, 2022
Figure 1 for Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
Figure 2 for Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
Figure 3 for Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
Figure 4 for Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
Viaarxiv icon

PAC-Net: A Model Pruning Approach to Inductive Transfer Learning

Add code
Jun 19, 2022
Figure 1 for PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Figure 2 for PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Figure 3 for PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Figure 4 for PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Viaarxiv icon

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Add code
Apr 19, 2022
Figure 1 for COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Figure 2 for COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Figure 3 for COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Figure 4 for COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Viaarxiv icon

LobsDICE: Offline Imitation Learning from Observation via Stationary Distribution Correction Estimation

Add code
Feb 28, 2022
Figure 1 for LobsDICE: Offline Imitation Learning from Observation via Stationary Distribution Correction Estimation
Figure 2 for LobsDICE: Offline Imitation Learning from Observation via Stationary Distribution Correction Estimation
Figure 3 for LobsDICE: Offline Imitation Learning from Observation via Stationary Distribution Correction Estimation
Viaarxiv icon

Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI

Add code
Dec 07, 2021
Figure 1 for Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Figure 2 for Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Figure 3 for Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Figure 4 for Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Viaarxiv icon

Dual Correction Strategy for Ranking Distillation in Top-N Recommender System

Add code
Sep 08, 2021
Figure 1 for Dual Correction Strategy for Ranking Distillation in Top-N Recommender System
Figure 2 for Dual Correction Strategy for Ranking Distillation in Top-N Recommender System
Figure 3 for Dual Correction Strategy for Ranking Distillation in Top-N Recommender System
Viaarxiv icon