parametric
neural-parametric-solver-datasets
Learning a Neural Solver for Parametric PDE to Enhance Physics-Informed Methods
This repository provides the datasets used in the paper "Learning a Neural Solver for Parametric PDE to Enhance Physics-Informed Methods", presented at ICLR 2025.
Project Page | ArXiv | Code
Usage
To use these datasets with the provided code, follow the setup instructions from the official repository:
# Setup
conda create -n neural-parametric-solver python=3.10.11
pip install -e .
#… See the full description on the dataset page: https://huggingface.co/datasets/2ailesB/neural-parametric-solver-datasets.Parametric-Optimization-ProblemsCurated by: [Andrew Rosemberg & Contributors]
Dataset Card for Parametric Optimization Problems
This dataset is a collection of parametrized optimization problems stored in MathOptFormat (.mof.json) files. Each file encodes a mathematical optimization problem—its objective, constraints, and parameters—using a standardized data structure for portability and ease of parsing.
Dataset Details
Dataset Description
Parametric optimization problems arise in scenarios… See the full description on the dataset page: https://huggingface.co/datasets/LearningToOptimize/Parametric-Optimization-Problems.parametric-cell-shapesdeepcell/parametric-cell-shapes
Fully synthetic cell images defined by a 10-dimensional morphometry vector, for precise resolution testing.
Description:
Parametric Cell Shapes (PCS) renders 256×256-pixel, 8-bit brightfield crops at 0.158 µm/px using Fourier descriptors and Perlin noise. Each image’s outline and texture are controlled by a 10-dimensional parameter vector that adjusts deviation, roughness, axis lengths, orientation, texture scale/intensity/contrast, and ring width/intensity.… See the full description on the dataset page: https://huggingface.co/datasets/Deepcell/parametric-cell-shapes.repro-accurate-evaluation-of-quickest-changepoint-detectors-via-non-parametric-survival-analysis
Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
This is a reproduction logbook for ICML 2026.
OpenReview ID: LhGxRnGmGJ
Paper Abstract
This logbook reproduces KM-ARL and KM-ADD estimators for changepoint detection.
See logbook.json for full claim verification details.
parametric-shapes
Parametric Shapes Dataset
This is a synthetic dataset of images containing geometric shapes with controllable parameters generated for educational purposes at the University of Toronto.
This dataset contains 7000 synthetic images (32x32) of geometric shapes including circles, rectangles, hexagons, stars, and triangles. Each image is generated with random parameters such as position, size, color, and rotation.
Dataset Splits
Train: 5,000 images (1,000 per shape)… See the full description on the dataset page: https://huggingface.co/datasets/r-three/parametric-shapes.UnifiedMemBench-ParametricMemory
UnifiedMemBench-ParametricMemory
This repository contains the parametric-memory component of UnifiedMemBench, a benchmark suite for evaluating memory capabilities of large language models.
The parametric-memory component is derived from the same synthetic character timelines and long-dialogue construction pipeline used by UnifiedMemBench. It is designed to evaluate whether language models can internalize, update, arbitrate, and retrieve character-specific memories after training… See the full description on the dataset page: https://huggingface.co/datasets/Ace1213812/UnifiedMemBench-ParametricMemory.