Randomized Positional Encodings Boost Length Generalization of Transformers

Additive Causal Bandits with Unknown Graph

Hierarchical Perceiver

PGMax

Memory-Based Meta-Learning on Non-Stationary Distributions

Transformer Grammars

Dramatron

Conformal Training

Zipfian Environments for Reinforcement Learning

Tell me why! Some environments for explanations in RL

Normalizing Flows for Atomic Solids

Informed adversary mnist reconstruction

A model of egocentric to allocentric understanding in mammalian brains

Distribution Shift Framework

Monte Carlo tree search in JAX

An implementation of Deep Kernel Shaping and Tailored Activation Transformations in JAX

Adversarial Robustness through Local Linearization

Temporally Abstract Partial Models

Self-Supervised Learning with Kernel Dependence Maximization

Advancing mathematics by guiding human intuition with AI

Discretization Drift in two player games

Hamiltonian Dynamics Suite

Arnheim

PIX

Encoders and Ensembles for Task-Free Continual Learning