Pinned Loading

1. meicoder meicoder Public

   Code for our paper "MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs" (NeurIPS 2025).

   Jupyter Notebook 1

2. learning-to-optimize learning-to-optimize Public

   Code for our paper "Investigation into the Training Dynamics of Learned Optimizers" (AAAI 2024 & ICAART 2024).

   Jupyter Notebook

3. rl-memory rl-memory Public

   Code for our paper "Reverse-Engineering Memory in DreamerV3: From Sparse Representations to Functional Circuits" (NeurIPS 2025, Spotlight at Mech Interp Workshop).

   Python

4. fractional-learning-to-optimize fractional-learning-to-optimize Public

   Code for our paper "Enhancing Fractional Gradient Descent with Learned Optimizers".

   Jupyter Notebook 1 1

5. in-context-learning in-context-learning Public

   Paper reproduction: "General-Purpose In-Context Learning by Meta-Learning Transformers".

   Jupyter Notebook 2 1

6. deep-q-learning-driver deep-q-learning-driver Public

   Implementation of Deep reinforcement learning (Q-learning) in a self-made game environment of a highway driver.

   Python