Research
Research Area
Basically, we are open to ANY research topic relevant to NLP & ML. Currently, we are particularly focused on the following areas of interest:
Large Language Models & Foundation Models
LLM behavior analysis
Alignment learning (instruction fine-tuning, RLHF, Imitation learning)
AI-generated contents detection
Prompting
Plug-in modules (e.g., RAG)
Multimodality expansion
Machine Learning & Representation Learning
Uncertatinty measure (measuring confidence of the model output)
Improving learning strategies (e.g., self-supervised learning, contrastive learning)
Representation extraction & analysis
Training model in a restricted environment (Black-box model training & optimization)
Parameter-efficient training (e.g., LoRA)