Search Results for author:
Found 4 papers, 0 papers with code
Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory
For comparison, Sch\"utt et al. (2019) spent 626 hours creating a dataset on which they trained their NN for 160h, for a total of 786h; our method achieves comparable performance within 31h.
Training and inference of large language models using 8-bit floating point
FP8 formats are gaining popularity to boost the computational efficiency for training and inference of large deep learning models.
Tuple Packing: Efficient Batching of Small Graphs in Graph Neural Networks
However, the sizes of small graphs can vary substantially with respect to the number of nodes and edges, and hence the size of the combined graph can still vary considerably, especially for small batch sizes.
The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization
Realtime perceptual and interaction capabilities in mixed reality require a range of 3D tracking problems to be solved at low latency on resource-constrained hardware such as head-mounted devices.
