Picture for Shuai Wang

Shuai Wang

The Hong Kong University of Science and Technology

Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks

Add code
Jan 20, 2025
Viaarxiv icon

How Should I Build A Benchmark?

Add code
Jan 18, 2025
Viaarxiv icon

Leveraging Metamemory Mechanisms for Enhanced Data-Free Code Generation in LLMs

Add code
Jan 14, 2025
Viaarxiv icon

ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification

Add code
Jan 14, 2025
Figure 1 for ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
Figure 2 for ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
Figure 3 for ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
Figure 4 for ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
Viaarxiv icon

Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory

Add code
Jan 03, 2025
Viaarxiv icon

Clutter Resilient Occlusion Avoidance for Tightly-Coupled Motion-Assisted Detection

Add code
Dec 24, 2024
Viaarxiv icon

SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor

Add code
Dec 18, 2024
Figure 1 for SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
Figure 2 for SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
Figure 3 for SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
Figure 4 for SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
Viaarxiv icon

Surrealistic-like Image Generation with Vision-Language Models

Add code
Dec 18, 2024
Viaarxiv icon

Hierarchical Control of Emotion Rendering in Speech Synthesis

Add code
Dec 17, 2024
Figure 1 for Hierarchical Control of Emotion Rendering in Speech Synthesis
Figure 2 for Hierarchical Control of Emotion Rendering in Speech Synthesis
Figure 3 for Hierarchical Control of Emotion Rendering in Speech Synthesis
Figure 4 for Hierarchical Control of Emotion Rendering in Speech Synthesis
Viaarxiv icon

AI PERSONA: Towards Life-long Personalization of LLMs

Add code
Dec 17, 2024
Viaarxiv icon