3 papers
cs.LG2025
Breaking Neural Network Scaling Laws with Modularity
Akhilan Boopathy, Sunshine Jiang, William Yue +3
Modular neural networks outperform nonmodular neural networks on tasks ranging from visual question answering to robotics. These performance improvements are thought to be due to m…
cs.LG2024
Towards General Purpose Robots at Scale: Lifelong Learning and Learning to Use Memory
William Yue
The widespread success of artificial intelligence in fields like natural language processing and computer vision has not yet fully transferred to robotics, where progress is hinder…
cs.LG2024
Permutation Invariant Learning with High-Dimensional Particle Filters
Akhilan Boopathy, Aneesh Muppidi, Peggy Yang +3
Sequential learning in deep models often suffers from challenges such as catastrophic forgetting and loss of plasticity, largely due to the permutation dependence of gradient-based…