Lists (1)
Stars
Recipes to scale inference-time compute of open models
Attention-based Crystal to Sequence Learning for Density of States Prediction
[NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE benchmark with subquadratic complexity in length (or without…
Learning Iterative Neural Optimizers for Image Steganography
Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
A system for quickly generating training data with weak supervision
An annotated implementation of the Transformer paper.
Hyper-parameter Tuning through noisy multi-fidelity tree search
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
MPVAE: Multivariate Probit Variational AutoEncoder for Multi-Label Classification
SkinnerDB is an analytical database management system. It uses adaptive processing and reinforcement learning to find near-optimal join orders.
Official implementation for paper: A New Defense Against Adversarial Images: Turning a Weakness into a Strength