datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
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.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.UniAR_assetsUniAR-Bench
📂 UniAR-Bench: Benchmarking Evidence-Grounded Anomaly Reasoning Across Modalities in MLLMs
UniAR-Bench is a comprehensive cross-modal anomaly reasoning benchmark with extensive tasks and credible evaluation. Built from publicly available datasets, UniAR-Bench comprises over 40,199 question-answer pairs covering coarse-to-fine reasoning across video, image and text modalities organized into four shared challenges:
Global and Referring Anomaly Discrimination
Fine-Grained Anomaly… See the full description on the dataset page: https://huggingface.co/datasets/jiomimi/UniAR-Bench.UniArch