Picture for Hui Xiong

Hui Xiong

PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization

Add code
Jul 12, 2024
Viaarxiv icon

Rethinking LLM-based Preference Evaluation

Add code
Jul 01, 2024
Viaarxiv icon

Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps

Add code
Jun 26, 2024
Viaarxiv icon

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

Add code
Jun 25, 2024
Figure 1 for Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Figure 2 for Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Figure 3 for Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Figure 4 for Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Viaarxiv icon

Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities

Add code
Jun 18, 2024
Viaarxiv icon

Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking

Add code
Jun 17, 2024
Figure 1 for Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Figure 2 for Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Figure 3 for Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Figure 4 for Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Viaarxiv icon

Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction

Add code
Jun 14, 2024
Viaarxiv icon

Holistic Memory Diversification for Incremental Learning in Growing Graphs

Add code
Jun 11, 2024
Viaarxiv icon

MAD: Multi-Alignment MEG-to-Text Decoding

Add code
Jun 03, 2024
Figure 1 for MAD: Multi-Alignment MEG-to-Text Decoding
Figure 2 for MAD: Multi-Alignment MEG-to-Text Decoding
Figure 3 for MAD: Multi-Alignment MEG-to-Text Decoding
Figure 4 for MAD: Multi-Alignment MEG-to-Text Decoding
Viaarxiv icon

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

Add code
May 30, 2024
Viaarxiv icon