Locally Deployed LLMs for Python Bug Detection: Evaluation
Explore the effectiveness of locally deployed LLMs like LLaMA 3.2 and Mistral in detecting Python code bugs with up to 45% accuracy.
Explainable AI for Speaker Recognition: Understanding Clusters
Explore how Explainable AI reveals hierarchical clusters in speaker recognition, improving transparency and interpretability of neural network models.
Unlocking AI Solutions Hidden in Chain-of-Thought States
Discover how hidden states in Chain-of-Thought reasoning improve AI accuracy, revealing key insights for better problem-solving models.
EmoTrans Benchmark for Emotion Transitions in Multimodal LLMs
Discover EmoTrans, a new benchmark to evaluate emotion understanding and prediction in multimodal large language models across dynamic social contexts.
Jailbreaking Risks in LLMs for Smart Grid Operations
Explore jailbreaking vulnerabilities in LLMs used for smart grid operations and their compliance with NERC standards to enhance security and safety.