datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
libero_90_lerobot_heatmapGoalxMIL-HeatmapsHeatmap data for the multiple instance learning models presented in:
Jamshidi Idaji et al. "Beyond attention heatmaps: How to get better explanations for multiple instance learning models in histopathology". Medical Image Analysis (2026).
Link: https://www.sciencedirect.com/science/article/pii/S1361841526002173
Code: https://github.com/bifold-pathomics/xMIL
@article{
jamshidi26beyond,
title = {Beyond attention heatmaps: How to get better explanations for multiple instance learning models… See the full description on the dataset page: https://huggingface.co/datasets/bifold-pathomics/xMIL-Heatmaps.fold_towel_20250919_subsampled_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 50,
"total_frames": 23011,
"total_tasks": 1,
"total_videos": 200,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 15,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/fold_towel_20250919_subsampled_heatmapGoal.libero_lerobot_object9_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 450,
"total_frames": 67539,
"total_tasks": 9,
"total_videos": 1800,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:450"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/libero_lerobot_object9_heatmapGoal.mug_on_platform_20250910_human_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 50,
"total_frames": 19564,
"total_tasks": 1,
"total_videos": 150,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 15,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/mug_on_platform_20250910_human_heatmapGoal.libero_lerobot_singleTask_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 50,
"total_frames": 7808,
"total_tasks": 1,
"total_videos": 200,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/libero_lerobot_singleTask_heatmapGoal.fold_bottoms_20250919_human_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 50,
"total_frames": 22954,
"total_tasks": 1,
"total_videos": 150,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 15,
"splits": {
"train": "0:50"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/fold_bottoms_20250919_human_heatmapGoal.libero_lerobot_object10_heatmapGoalThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": null,
"total_episodes": 500,
"total_frames": 74507,
"total_tasks": 10,
"total_videos": 2000,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:500"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/sriramsk/libero_lerobot_object10_heatmapGoal.lego_stack_4x4_regular_plus_correction_frontdot_backwrist_heatmap_history_dynamic_lerobot_v3This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "ur5_wsg50_lego_stack",
"total_episodes": 202,
"total_frames": 80912,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 20,
"splits": {
"train": "0:202"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet"… See the full description on the dataset page: https://huggingface.co/datasets/ajaysri/lego_stack_4x4_regular_plus_correction_frontdot_backwrist_heatmap_history_dynamic_lerobot_v3.tribe-replay-heatmaps
TRIBE Replay Heatmaps
Video-ID manifest and per-video results for the paper A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps.
Paper: https://arxiv.org/abs/2607.01400
Code: https://github.com/mercurialsolo/tribe-replay-heatmaps
Summary
We run TRIBE, the winning model of the Algonauts 2025 brain-encoding challenge combining Llama-3.2, V-JEPA2 and Wav2Vec-BERT, on 48 YouTube videos. We reduce its predicted cortical response to… See the full description on the dataset page: https://huggingface.co/datasets/mercurialsolo/tribe-replay-heatmaps.Grad-CAM_Heatmap_Study