DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Reflexion: an autonomous agent with dynamic memory and self-reflection

Magnushammer: A Transformer-based Approach to Premise Selection

Exphormer: Sparse Transformers for Graphs

Eliciting Latent Predictions from Transformers with the Tuned Lens

Toolformer: Language Models Can Teach Themselves to Use Tools

Progress measures for grokking via mechanistic interpretability

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

Extracting Training Data from Diffusion Models

Learning on tree architectures outperforms a convolutional feedforward network - Scientific Reports

Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research

Generative Adversarial Neural Operators

General Intelligence Requires Rethinking Exploration