datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
unified-vlm-steering-emu35
Emu3.5 (BAAI): activation steering sweeps
Steered text and image generations from Emu3.5 (BAAI), one of the unified vision-language models in the unified-vlm-steering project. Steering adds alpha * v_hat (the per-layer unit difference-of-means vector) to the residual stream at every layer of a layer config.
34B dense autoregressive model, 64 decoder layers (0-indexed). Images are 32x32 IBQ tokens (512 px), generated on BAAI's patched vLLM engine with request-id-keyed CFG. The… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/unified-vlm-steering-emu35.unified-vlm-steering-uniar
UniAR (ShareLab-SII/UniAR-RL): activation steering sweeps
Steered text and image generations from UniAR (ShareLab-SII/UniAR-RL), one of the unified vision-language models in the unified-vlm-steering project. Steering adds alpha * v_hat (the per-layer unit difference-of-means vector) to the residual stream at every layer of a layer config.
Qwen3-VL backbone, 36 decoder layers (0-indexed). Images are BSQ tokens rendered by an SD3 decoder (16 decoding steps, 544 px).… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/unified-vlm-steering-uniar.unified-vlm-steering-liquid
Liquid (FoundationVision Liquid_V1_7B): activation steering sweeps
Steered text and image generations from Liquid (FoundationVision Liquid_V1_7B), one of the unified vision-language models in the unified-vlm-steering project. Steering adds alpha * v_hat (the per-layer unit difference-of-means vector) to the residual stream at every layer of a layer config.
Gemma-7B backbone, 28 decoder layers (0-indexed). Images are VQGAN codes (512 px), CFG 7.0, top-k 4096, top-p 0.96… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/unified-vlm-steering-liquid.uniar-steering-eval
UniAR Steering Eval — text quadrants (samples only)
Activation-steering text generations from UniAR (Qwen3-VL backbone, BSQ visual tokens, SD3 decoder).
Raw generated samples only — the LLM-judge scores have been removed.
Quadrants (2, text output)
A steering direction is extracted from minimal pairs in one modality, then injected during pure text generation.
sub
vector from
steers
output
txt2txt
text pairs
whole user message + generation
text
img2txt… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/uniar-steering-eval.unified-vlm-steering-minimal-pairs
Unified VLM Steering: Minimal Pairs
Minimal pairs used to extract steering vectors (difference of means between the two poles) for 7 concepts in the
unified-vlm-steering project: 100 text pairs and 100 image pairs per concept.
Layout
txt/<concept>/pairs.json 100 text pairs: concept, pos_label, neg_label, template, n_pairs,
pairs [{subject, pos, neg}], and the pos / neg sentence lists
img/<concept>/<000-099>/
baseline.png… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/unified-vlm-steering-minimal-pairs.unified-vlm-steering-eval
Unified VLM steering eval
Activation steering of unified vision-language models: steered text and image generations, steering vectors and
judge scores. One folder per model; prompts/ is shared. Steering is h <- h + alpha * v_hat everywhere.
model
run
text rows
image rows
concepts with images
published
uniar/
av_v2
21,560
21,560
age, chaos, cleanness, emotion, near_far, size, spatial_lr
2026-09-11
Layout per model: manifest.json (exact config)… See the full description on the dataset page: https://huggingface.co/datasets/saintsauce/unified-vlm-steering-eval.eval_steering_ours_low_4_same_noiseThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "koch_follower",
"total_episodes": 20,
"total_frames": 4259,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:20"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/ethanCSL/eval_steering_ours_low_4_same_noise.sdxl-activation-steering
SDXL Image Activation Steering: Continuous Concept Trajectory Control
This repository demonstrates Representation Engineering and Activation Steering on Diffusion Models (SDXL Turbo) using PyTorch and Hugging Face diffusers on an NVIDIA H100 GPU.
⚡ How It Works
Instead of retraining a LoRA or using binary negative prompt weights, we extract continuous concept steering vectors:
vstyle=1N∑i=1N(ecyberpunk_neon(i)−egolden_hour(i))\mathbf{v}_{\text{style}} =… See the full description on the dataset page: https://huggingface.co/datasets/mayank-dubey-ai/sdxl-activation-steering.F1-steering-angle-datasetsteering_data_two_tasks_fixedThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "droid",
"total_episodes": 30,
"total_frames": 3229,
"total_tasks": 2,
"total_videos": 0,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 10,
"splits": {
"train": "0:30"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": null,
"features": {… See the full description on the dataset page: https://huggingface.co/datasets/shubhamg20/steering_data_two_tasks_fixed.boltzmann-attention-steering-artifactssteering_data_two_tasksThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "droid",
"total_episodes": 62,
"total_frames": 7042,
"total_tasks": 2,
"total_videos": 0,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 10,
"splits": {
"train": "0:62"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": null,
"features": {… See the full description on the dataset page: https://huggingface.co/datasets/shubhamg20/steering_data_two_tasks.thinking-steering-visualizationsf1-steering-angleCheck the app!
https://f1-steering-angle-model.streamlit.app/
steering_data_three_tasksThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "droid",
"total_episodes": 180,
"total_frames": 19500,
"total_tasks": 3,
"total_videos": 0,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 10,
"splits": {
"train": "0:180"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": null,
"features": {… See the full description on the dataset page: https://huggingface.co/datasets/shubhamg20/steering_data_three_tasks.steering_data_two_tasks_2This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v2.1",
"robot_type": "droid",
"total_episodes": 60,
"total_frames": 6456,
"total_tasks": 2,
"total_videos": 0,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 10,
"splits": {
"train": "0:60"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": null,
"features": {… See the full description on the dataset page: https://huggingface.co/datasets/shubhamg20/steering_data_two_tasks_2.F1-steering-angle-datasetmultiple-steering-visualization