Picture for Yi Ouyang

Yi Ouyang

Evolving to be Your Soulmate: Personalized Dialogue Agents with Dynamically Adapted Personas

Jun 20, 2024
Viaarxiv icon

COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detection

Jun 16, 2024
Viaarxiv icon

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection

Mar 15, 2024
Figure 1 for Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Figure 2 for Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Figure 3 for Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Figure 4 for Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Viaarxiv icon

Model approximation in MDPs with unbounded per-step cost

Feb 13, 2024
Viaarxiv icon

COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal

Add code
Dec 19, 2023
Figure 1 for COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
Figure 2 for COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
Figure 3 for COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
Figure 4 for COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
Viaarxiv icon

Grasping Core Rules of Time Series through Pure Models

Aug 15, 2022
Viaarxiv icon

A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems

Aug 19, 2021
Figure 1 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Figure 2 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Figure 3 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Viaarxiv icon

Scalable regret for learning to control network-coupled subsystems with unknown dynamics

Aug 18, 2021
Figure 1 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Figure 2 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Figure 3 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Viaarxiv icon

Causal Inference Q-Network: Toward Resilient Reinforcement Learning

Add code
Feb 18, 2021
Figure 1 for Causal Inference Q-Network: Toward Resilient Reinforcement Learning
Figure 2 for Causal Inference Q-Network: Toward Resilient Reinforcement Learning
Figure 3 for Causal Inference Q-Network: Toward Resilient Reinforcement Learning
Figure 4 for Causal Inference Q-Network: Toward Resilient Reinforcement Learning
Viaarxiv icon

Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation

Nov 24, 2020
Figure 1 for Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Figure 2 for Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Figure 3 for Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Figure 4 for Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Viaarxiv icon