Picture for Lin Guan

Lin Guan

Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning

May 31, 2024
Viaarxiv icon

"Task Success" is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors

Add code
Feb 06, 2024
Viaarxiv icon

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks

Feb 06, 2024
Viaarxiv icon

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

Add code
May 24, 2023
Figure 1 for Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Figure 2 for Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Figure 3 for Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Figure 4 for Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Viaarxiv icon

TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

Feb 05, 2023
Figure 1 for TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
Figure 2 for TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
Figure 3 for TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
Figure 4 for TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
Viaarxiv icon

Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

Add code
Nov 16, 2022
Figure 1 for Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
Figure 2 for Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
Figure 3 for Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
Figure 4 for Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
Viaarxiv icon

Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion

Oct 27, 2022
Figure 1 for Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
Figure 2 for Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
Figure 3 for Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
Figure 4 for Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
Viaarxiv icon

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Add code
Feb 06, 2022
Figure 1 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Figure 2 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Figure 3 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Figure 4 for Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Viaarxiv icon

MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation

Jan 18, 2022
Viaarxiv icon

Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers

Dec 07, 2021
Figure 1 for Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
Figure 2 for Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
Figure 3 for Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
Figure 4 for Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
Viaarxiv icon