NewsReX: A More Efficient Approach to News Recommendation with Keras 3 and JAX
Paper β’ 2508.21572 β’ Published
NRMS news recommendation model trained on MIND-small using the NewsReX framework (PYTORCH).
| Seed | AUC | MRR | NDCG@5 | NDCG@10 |
|---|---|---|---|---|
| 123 | 0.6499 | 0.3024 | 0.3341 | 0.3986 |
| 42 | 0.6546 | 0.3061 | 0.3379 | 0.4031 |
| 456 * | 0.6557 | 0.3073 | 0.3382 | 0.4035 |
| mean Β± std | 0.6534Β±0.0025 | 0.3052Β±0.0021 | 0.3367Β±0.0019 | 0.4017Β±0.0022 |
* Best seed (weights at repo root)
newsrex/NRMS-PYTORCH-MIND-small/
βββ model.safetensors β best seed (456)
βββ test_results.json
βββ training_run_summary.json
βββ seed_123/model.safetensors
βββ seed_42/model.safetensors
βββ seed_456/model.safetensors
βββ README.md
git clone https://github.com/igor17400/NewsReX.git
cd NewsReX && uv sync
# Run evaluation with best seed weights
uv run python src/eval.py \
experiment=mind/nrms \
framework=pytorch \
weights=hf://newsrex/NRMS-PYTORCH-MIND-small/model.safetensors
# Run evaluation with a specific seed
uv run python src/eval.py \
experiment=mind/nrms \
framework=pytorch \
weights=hf://newsrex/NRMS-PYTORCH-MIND-small/seed_42/model.safetensors
@misc{newsrex2026,
title={NewsReX: An Open-Source Multi-Framework for Neural News Recommendation},
author={Igor L. R. Azevedo and Toyotaro Suzumura and Yuichiro Yasui},
year={2025},
eprint={2508.21572},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2508.21572},
}