datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
icml2026-repro-l35QweVxgn-code
Reproduction code — On the Theory of Continual Learning with Gradient Descent for Neural Networks
Clean-room NumPy reimplementation and full sweep harness for the ICML 2026 submission
l35QweVxgn (arXiv:2510.05573v2),
Taheri, Ghosh & Mazumdar.
The write-up lives in the Trackio logbook:
🚀 nmaher/repro-on-the-theory-of-continual-learning-with-gradient-descent-for-neural-networks.
This repo is the code and the raw numbers behind it.
Layout
code/ the… See the full description on the dataset page: https://huggingface.co/datasets/nmaher/icml2026-repro-l35QweVxgn-code.causal-jepa-icml2026-blog-assetsicml2026-epistemic-uncertainty-reproicml8440-logbook-source
Reproduction: Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better
An open experiment logbook, published with Trackio.
icml17708-grok-grokking-reprorepro-last-iterate-proximal-artifactsicml26-repro-xQLcklRDfM-atc-evidenceicml26-repro-oddshap
OddSHAP reproduction
This bundle independently checks the odd-component identity, paired-design
orthogonality, and Fourier recovery, then runs a scaled noisy Fourier-game
benchmark. Run uv run --with-requirements requirements.txt python reproduce.py.
author_code/ is a provenance checkout and is not imported by the independent
script.
icml_2023_posters_testicml2026_annoymous