Deep Learning
SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery Nina Montaña-Brown
However, the automation of MIS and RAMIS through the use of AI has been slow due to difficulties in data acquisition and curation, partially caused by the ethical considerations of training, testing and deploying AI models in medical environments.
DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
We also introduce a novel benchmark for evaluating NNPs in molecular property prediction, Hamiltonian prediction, and conformational optimization tasks.
Unlabeled Data Improves Adversarial Robustness
Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, John C. Duchi, Percy S. Liang
Neural Information Processing Systems http://nips.cc/
LearningaSingleNeuronwithBias UsingGradientDescent
Learning a single ReLU neuron with gradient descent is a fundamental primitive in the theory of deep learning, andhasbeen extensivelystudied inrecent years.
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction Manuel Brenner
Dynamical systems (DS) theory is fundamental for many areas of science and engineering. It can provide deep insights into the behavior of systems evolving in time, as typically described by differential or recursive equations.
rich Documents with Layout Annotations from Web Crawl Data Maurice Weber ETH Zurich Carlo Siebenschuh University of Chicago Rory M. Butler
The first three authors contributed equally.
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs).