In‑Context Algorithm Emulation in Fixed‑Weight Transformers

This is the code for the paper: In-Context Algorithm Emulation in Fixed-Weight Transformers. You can use this repo to reproduce the results in the paper.

Environmental Setup

1. Clone the repository

   gh repo clone MAGICS-LAB/algo_emu
   cd algo_emu

2. Create and activate a virtual environment

   conda create -n algo_emu python=3.10
   conda activate algo_emu

3. Install required packages

   pip install -r requirements.txt

Usage

Attention Emulating Continuous Function (Theorem 2.1)

Run att_sim_f.py.

Attention Emulating Attention Head (Theorem 3.1/3.2)

Run attn_sim_attn.py.

Attention Emulating Statistical Models (Corollary 3.2.1)

Run att_sim_statistical.py using synthetic data, and att_sim_statistical_ames_data.py using Ames Housing Data.

Citation

If you find our work useful, please cite:

@article{hu2025incontext,
  title   = {In-Context Algorithm Emulation in Fixed-Weight Transformers},
  author  = {Hu, Jerry Yao-Chieh and Liu, Hude and Zhang, Jennifer Yuntong and Liu, Han},
  journal = {arXiv preprint arXiv:2508.17550},
  year    = {2025}
}