Efficient Computation
Efficient computation focuses on developing faster and more resource-friendly algorithms and hardware for solving complex computational problems across diverse fields. Current research emphasizes optimizing existing algorithms (e.g., integrating incremental learning into established methods, employing low-rank matrix approximations) and exploring novel architectures (e.g., state space models, photonic Ising machines, and specialized hardware like FPGAs) to reduce computational complexity and energy consumption. These advancements are crucial for tackling large-scale problems in areas such as machine learning, medical image analysis, and robotics, ultimately enabling faster processing and broader accessibility of powerful computational tools.
Papers
Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition
Edwin Arkel Rios, Femiloye Oyerinde, Min-Chun Hu, Bo-Cheng Lai
Efficient Computation of Whole-Body Control Utilizing Simplified Whole-Body Dynamics via Centroidal Dynamics
Junewhee Ahn, Jaesug Jung, Yisoo Lee, Hokyun Lee, Sami Haddadin, Jaeheung Park