Picture for Tu Vu

Tu Vu

Efficient Model Development through Fine-tuning Transfer

Add code
Mar 25, 2025
Viaarxiv icon

CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers

Add code
Feb 25, 2025
Viaarxiv icon

ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models

Add code
Feb 24, 2025
Viaarxiv icon

Few-shot Continual Relation Extraction via Open Information Extraction

Add code
Feb 23, 2025
Viaarxiv icon

What Matters for Model Merging at Scale?

Add code
Oct 04, 2024
Figure 1 for What Matters for Model Merging at Scale?
Figure 2 for What Matters for Model Merging at Scale?
Figure 3 for What Matters for Model Merging at Scale?
Figure 4 for What Matters for Model Merging at Scale?
Viaarxiv icon

Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation

Add code
Jul 15, 2024
Viaarxiv icon

Self-Evaluation Improves Selective Generation in Large Language Models

Add code
Dec 14, 2023
Viaarxiv icon

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

Add code
Oct 05, 2023
Figure 1 for FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
Figure 2 for FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
Figure 3 for FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
Figure 4 for FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
Viaarxiv icon

Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse Mixture of Experts

Add code
May 24, 2023
Viaarxiv icon

Multi-scale Transformer-based Network for Emotion Recognition from Multi Physiological Signals

Add code
May 08, 2023
Viaarxiv icon