← Search

Siyeol Kim

2 accepted papers

2025

FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning

ICLR 2025poster

Multi-agent reinforcement learning has demonstrated significant potential in addressing complex cooperative tasks across various real-world applications. However, existing MARL approaches often rely on the restrictive assumption that the number of entities (e.g., agents, obstacles) remains constant…

2025

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

NeurIPS 2025poster

Residual connections are pivotal for deep neural networks, enabling greater depth by mitigating vanishing gradients. However, in standard residual updates, the module’s output is directly added to the input stream. This can lead to updates that predominantly reinforce or modulate the existing stream…

Cited by 0SourcecodeScholar