datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
xMIL-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.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.attention-heatmap-visualizer
Attention Heatmap Visualizer 3.1.0
A Python scripts to generate full attention-head heat-maps for transformer-based Language Models. They show "where the model is looking" or "what tokens/features are most relevant" when processing a specific input element.
By analyzing these heatmaps across all layers and heads you can gain insights into how the model processes information, identifies relationships between tokens, and prioritizes specific parts of the input during inference.… See the full description on the dataset page: https://huggingface.co/datasets/ronniross/attention-heatmap-visualizer.Thermal-Heatmap-Source-Localization
ThermBench 🔥 — Thermal Heatmap Source Localization Benchmark
📝 Summary
ThermBench is a physics-inspired synthetic dataset designed to evaluate algorithms that infer hidden thermal sources from an observed heat diffusion map.
Each data sample contains:
an observed heatmap (matrix of values),
and the ground-truth sources: (row, col, intensity).
Diffusion follows inverse Manhattan distance:
[
H(i,j) ;=; \sum_{s=1}^{K} \frac{I_s}{d(i,j,s)+1}
]
where (d) is the Manhattan… See the full description on the dataset page: https://huggingface.co/datasets/ZoneTwelve/Thermal-Heatmap-Source-Localization.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.target-heatmap-datasettribe-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.eggs-heatmaphidden-state-heatmap-visualizer
hidden-state-heatmap-visualizer
A set of scripts to visualize neuron activations, the evolution of hidden states, neural pathways, and semantic clustering (token similarity) in language models.
Ronni Ross2026
fnbm-current-sweep-chart-z2-recovery-heatmap
fnbm-current-sweep-chart-z2-recovery-heatmap
20260713 second-order sweep visualization: z2-recovery-heatmap.
Dataset Info
Rows: 1
Columns: 1
Columns
Column
Type
Description
plotly_json
Value('string')
No description provided
Generation Parameters
{
"script_name": "build_20260713_charts.py",
"model": "fnbm_20260707",
"description": "20260713 second-order sweep visualization: z2-recovery-heatmap."… See the full description on the dataset page: https://huggingface.co/datasets/arushram/fnbm-current-sweep-chart-z2-recovery-heatmap.malvec-heatmapGrad-CAM_Heatmap_Study