Picture for Songfang Huang

Songfang Huang

Unlocking the Potential of Model Merging for Low-Resource Languages

Add code
Jul 04, 2024
Viaarxiv icon

Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models

Add code
Jun 04, 2024
Viaarxiv icon

Harder Tasks Need More Experts: Dynamic Routing in MoE Models

Add code
Mar 12, 2024
Viaarxiv icon

BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization

Add code
Jul 17, 2023
Viaarxiv icon

DiffDTM: A conditional structure-free framework for bioactive molecules generation targeted for dual proteins

Add code
Jun 24, 2023
Viaarxiv icon

Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning

Add code
May 24, 2023
Figure 1 for Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Figure 2 for Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Figure 3 for Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Figure 4 for Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Viaarxiv icon

VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning

Add code
Apr 17, 2023
Figure 1 for VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
Figure 2 for VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
Figure 3 for VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
Figure 4 for VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
Viaarxiv icon

RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Add code
Apr 11, 2023
Viaarxiv icon

Revisiting Automatic Question Summarization Evaluation in the Biomedical Domain

Add code
Mar 18, 2023
Viaarxiv icon

RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training

Add code
Mar 01, 2023
Viaarxiv icon