NewsReX: A More Efficient Approach to News Recommendation with Keras 3 and JAX
Paper β’ 2508.21572 β’ Published
TCCM news recommendation model trained on MIND-small using the NewsReX framework (JAX).
| Seed | AUC | MRR | NDCG@5 | NDCG@10 |
|---|---|---|---|---|
| 123 | 0.6781 | 0.3256 | 0.3639 | 0.4251 |
| 42 | 0.6809 | 0.3251 | 0.3635 | 0.4253 |
| 456 * | 0.6834 | 0.3321 | 0.3694 | 0.4308 |
| mean Β± std | 0.6808Β±0.0022 | 0.3276Β±0.0032 | 0.3656Β±0.0027 | 0.4271Β±0.0026 |
* Best seed (weights at repo root)
newsrex/TCCM-JAX-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/tccm \
framework=jax \
weights=hf://newsrex/TCCM-JAX-MIND-small/model.safetensors
# Run evaluation with a specific seed
uv run python src/eval.py \
experiment=mind/tccm \
framework=jax \
weights=hf://newsrex/TCCM-JAX-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},
}