Deep Learning
GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising Hyeonsu Kim Department of Chemistry KAIST Daejeon, South Korea Jeheon Woo
As quantum chemical properties have a dependence on their geometries, graph neural networks (GNNs) using 3D geometric information have achieved high prediction accuracy in many tasks.
Learning Time-Invariant Representations for Individual Neurons from Population Dynamics Lu Mi
Neurons can display highly variable dynamics.
Exploring Geometry of Blind Spots in Vision Models
We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients.
Transformer-based Planning for Symbolic Regression
Extensive experiments on various datasets show that our approach outperforms state-of-the-art methods, enhancing the model's
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
ToolkenGPT offers the flexibility to plug in an arbitrary number of tools by expanding the set of toolkens on the fly. In addition, it improves tool use by allowing extensive demonstration data for learning the toolken embeddings.