Picture for Hang Chen

Hang Chen

Exploring Speaker Diarization with Mixture of Experts

Add code
Jun 17, 2025
Viaarxiv icon

M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset

Add code
Jun 17, 2025
Viaarxiv icon

Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation

Add code
May 28, 2025
Viaarxiv icon

SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect

Add code
May 26, 2025
Viaarxiv icon

Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates

Add code
May 15, 2025
Viaarxiv icon

Unveiling Language Skills under Circuits

Add code
Oct 02, 2024
Viaarxiv icon

Deep CLAS: Deep Contextual Listen, Attend and Spell

Add code
Sep 26, 2024
Figure 1 for Deep CLAS: Deep Contextual Listen, Attend and Spell
Figure 2 for Deep CLAS: Deep Contextual Listen, Attend and Spell
Figure 3 for Deep CLAS: Deep Contextual Listen, Attend and Spell
Figure 4 for Deep CLAS: Deep Contextual Listen, Attend and Spell
Viaarxiv icon

Data Processing Techniques for Modern Multimodal Models

Add code
Jul 27, 2024
Viaarxiv icon

Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation

Add code
Jul 17, 2024
Viaarxiv icon

Balance of Number of Embedding and their Dimensions in Vector Quantization

Add code
Jul 06, 2024
Viaarxiv icon