4 papers
Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining
Bing Han, Feifei Zhao, Dongcheng Zhao +4
While fine-tuning services drive the rapid expansion of task capabilities in large language models (LLMs), they are often accompanied by the degradation and reorganization of safet…
Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism
Bing Han, Feifei Zhao, Yinqian Sun +2
Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of co…
Super Co-alignment of Human and AI for Sustainable Symbiotic Society
Yi Zeng, Feifei Zhao, Yuwei Wang +13
As Artificial Intelligence (AI) advances toward Artificial General Intelligence (AGI) and eventually Artificial Superintelligence (ASI), it may potentially surpass human control, d…
Evolving Efficient Genetic Encoding for Deep Spiking Neural Networks
Wenxuan Pan, Feifei Zhao, Bing Han +2
By exploiting discrete signal processing and simulating brain neuron communication, Spiking Neural Networks (SNNs) offer a low-energy alternative to Artificial Neural Networks (ANN…