진행중

• Meta Learning for AI Alignment
• Transformer-Guided Protein Mutagenesis
• Mechanistically Interpretable Transformer
• Interpretable Information Extraction

마무리 단계

• Causal Information Retrieval
• Post-OCR Error Corrections

대기중

• Diffusive Information Retrieval
• Tracing Training-Data Influence in Large Reasoning Models

종료

• Investigating Robustness of the Safety Properties in Large Language Models
• Korean Legal Benchmark II
• Legal Retrieval Augmented Generation System
• Improving the Robustness of Neuron Coverage
• AI Safety for Low-Resource Language
• Korean Legal Benchmark III
• Reducing Hallucination in Vision-Language Models
• Taxation AI Benchmark