Jean Kaddour

NoTrainNoGain. Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)

SIN. Causal Effect Inference for Structured Treatments (SIN) (NeurIPS 2021)

LAWA. Latest Weight Averaging (NeurIPS HITY 2022)

tpo. Target Policy Optimization (JAX)

WASAM. Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)

sokoban_speedrun. RL models to play Sokoban. The fastest recipe wins.

PAML. Implementation of paper "Probabilistic Active Meta-Learning" (NeurIPS 2020).

ramenGPT. Python

pokerSettlements. TypeScript

oyster. Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

JeanKaddour.