Picture for Cangqing Wang

Cangqing Wang

Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees

Add code
May 22, 2024
Viaarxiv icon

Adapting LLMs for Efficient Context Processing through Soft Prompt Compression

Add code
Apr 07, 2024
Figure 1 for Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
Figure 2 for Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
Figure 3 for Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
Figure 4 for Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
Viaarxiv icon

Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques

Add code
Mar 09, 2024
Figure 1 for Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
Figure 2 for Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
Figure 3 for Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
Figure 4 for Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
Viaarxiv icon

Intelligent Agricultural Greenhouse Control System Based on Internet of Things and Machine Learning

Add code
Feb 14, 2024
Figure 1 for Intelligent Agricultural Greenhouse Control System Based on Internet of Things and Machine Learning
Figure 2 for Intelligent Agricultural Greenhouse Control System Based on Internet of Things and Machine Learning
Figure 3 for Intelligent Agricultural Greenhouse Control System Based on Internet of Things and Machine Learning
Figure 4 for Intelligent Agricultural Greenhouse Control System Based on Internet of Things and Machine Learning
Viaarxiv icon