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.islamic-parametric-architecture-datasetparametric-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.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.parametric-arithmetic-eval
Parametric & Arithmetic Eval
A 600-example control set for testing whether ablated attention heads are
retrieval-specific rather than generically important for model output. Every
question is answerable from the model's own parametric knowledge or by direct
computation — none require retrieving information from an in-context document.
This dataset accompanies LOCOS (Logit-Contribution Scoring). A retrieval-head
detector is only meaningful if ablating the heads it identifies… See the full description on the dataset page: https://huggingface.co/datasets/aryopg/parametric-arithmetic-eval.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.