datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MLS-Bench-Tasks
MLS-Bench Tasks
MLS-Bench is a benchmark for machine learning science. Where most agent benchmarks reward engineering one fixed instance — clean the data, tune the pipeline, climb a leaderboard — MLS-Bench asks the harder question: can an AI agent propose a new component, loss, optimizer, or training procedure whose gain transfers across settings, seeds, datasets, and scales?The benchmark contains 140 tasks across 12 ML research domains. Each task fixes a research scaffold… See the full description on the dataset page: https://huggingface.co/datasets/Bohan22/MLS-Bench-Tasks.osworld_tasks_filesgeoguesser-tasks
GeoGuesser Task Splits
Task indexes for the GeoGuesser OpenEnv environment.
Each line is one episode: an ordered list of panorama frames with coordinates,
headings and capture dates, plus the sequence and contributor it came from.
Split
Tasks
Countries
Frames
Fully mirrored
eval
200
73
4673
200/200
train
3452
130
80179
3448/3452
What a task is
These files carry metadata only, not imagery. Every frame's coordinates,
heading and capture date are… See the full description on the dataset page: https://huggingface.co/datasets/FineEnvs/geoguesser-tasks.ProbeScout-tasks
ProbeScout Main17 task packages
Use with ProbeScout source and setup instructions.
Download only the dataset(s) you need, and extract each ZIP into the code repository root.
The ZIP paths already include dataset/ and visual_analytics/.
File
Tasks
Compressed size
cars.zip
7
93.74 MB
hico.zip
8
320.29 MB
celeba.zip
2
439.43 MB
Each package includes task definitions, attributes, query image IDs, ordered
records, original VQA source/fit/Validation labels, fixed… See the full description on the dataset page: https://huggingface.co/datasets/Ian100/ProbeScout-tasks.