South America
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the sequence, thus incurring a quadratic cost. In this study, we present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness, resulting in reduced memory and computational
AV ERI
Fact-checking is considered crucial for limiting the impact of misinformation [Lewandowsky et al.,
TopoSRL: Topology Preserving Self-Supervised Simplicial Representation Learning
This paper proposes an SSL method for simplicial complex data that preserves topological and geometric information while learning representations. Although no existing studies focus on SSL for simplicial complex data, a closely related field of SSL for graph data has been extensively studied.
Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity
How neuronal circuits achieve credit assignment remains a central unsolved question in systems neuroscience.
