Sliceformer: Advanced Static Program Slicing with Language Models
Discover Sliceformer, a cutting-edge framework using dataflow-aware pretraining and constrained decoding to enhance static program slicing accuracy.
Understanding and Mitigating Biases in Transformer AI
Explore key biases in transformer-based AI systems and learn strategies to ensure fair, reliable, and ethical AI deployment.
CareGuardAI: Ensuring Clinical Safety in Patient-Facing LLMs
CareGuardAI enhances patient-facing LLMs with context-aware guardrails to ensure clinical safety and reduce AI hallucinations in healthcare applications.
Ethical Emotion Regulation Framework for Agentic AI Design
Explore Toegye Yi Hwang's Ethical Emotion Regulation Framework to enhance moral-emotional learning in autonomous AI systems.
Improving MLLM Feedback Validity on Science Drawings
Explore challenges and solutions for accurate MLLM-generated feedback on student science drawings to enhance learning outcomes.