Picture for Fei Fang

Fei Fang

M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

Add code
Mar 06, 2025
Viaarxiv icon

$\text{M}^3\text{HF}$: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

Add code
Mar 03, 2025
Viaarxiv icon

Grounded Persuasive Language Generation for Automated Marketing

Add code
Feb 24, 2025
Figure 1 for Grounded Persuasive Language Generation for Automated Marketing
Figure 2 for Grounded Persuasive Language Generation for Automated Marketing
Figure 3 for Grounded Persuasive Language Generation for Automated Marketing
Figure 4 for Grounded Persuasive Language Generation for Automated Marketing
Viaarxiv icon

Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models

Add code
Oct 25, 2024
Figure 1 for Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
Figure 2 for Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
Figure 3 for Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
Figure 4 for Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
Viaarxiv icon

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy

Add code
Oct 17, 2024
Figure 1 for CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Figure 2 for CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Figure 3 for CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Figure 4 for CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Viaarxiv icon

TypedThinker: Typed Thinking Improves Large Language Model Reasoning

Add code
Oct 02, 2024
Viaarxiv icon

Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content

Add code
Aug 30, 2024
Figure 1 for Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content
Figure 2 for Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content
Figure 3 for Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content
Figure 4 for Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content
Viaarxiv icon

Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels

Add code
Jul 22, 2024
Figure 1 for Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Figure 2 for Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Figure 3 for Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Figure 4 for Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Viaarxiv icon

Multi-Agent Imitation Learning: Value is Easy, Regret is Hard

Add code
Jun 06, 2024
Figure 1 for Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Figure 2 for Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Figure 3 for Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Figure 4 for Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Viaarxiv icon

Global Rewards in Restless Multi-Armed Bandits

Add code
Jun 02, 2024
Figure 1 for Global Rewards in Restless Multi-Armed Bandits
Figure 2 for Global Rewards in Restless Multi-Armed Bandits
Figure 3 for Global Rewards in Restless Multi-Armed Bandits
Figure 4 for Global Rewards in Restless Multi-Armed Bandits
Viaarxiv icon