4 papers
On the Decompositionality of Neural Networks
Junyong Lee, Baek-Ryun Seong, Sang-Ki Ko +5
Recent advances in deep neural networks have achieved state-of-the-art performance across vision and natural language processing tasks. In practice, however, most models are treate…
SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks
Hyunwoo Park, Baekryun Seong, Sang-Ki Ko
In cooperative multi-agent reinforcement learning (MARL), the permutation problem where the state space grows exponentially with the number of agents reduces sample efficiency. Add…
LBC: Language-Based-Classifier for Out-Of-Variable Generalization
Kangjun Noh, Baekryun Seong, Hoyoon Byun +3
Large Language Models (LLMs) have great success in natural language processing tasks such as response generation. However, their use in tabular data has been limited due to their i…
Towards Efficient Formal Verification of Spiking Neural Network
Baekryun Seong, Jieung Kim, Sang-Ki Ko
Recently, AI research has primarily focused on large language models (LLMs), and increasing accuracy often involves scaling up and consuming more power. The power consumption of AI…