Get the app
← back to catalog
AUTHOR

uiuc-kang-lab

No models indexed under this account. Publishes 2 alignment datasets (736 downloads) tracked in our /datasets catalog.

Alignment datasets by uiuc-kang-lab

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

2 in /datasets
Dataset
Stage
Downloads
BEAT 0 0
BEAT Training Dataset This dataset accompanies the paper: BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Tri...
misc
584
PersistBD 0 0
PersistBD Dataset This dataset accompanies the paper "Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training" (EMNLP...
misc
152
Dataset
Stage
Downloads
PersistBD 0 0
PersistBD Dataset This dataset accompanies the paper "Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training" (EMNLP...
misc
152
BEAT 0 0
BEAT Training Dataset This dataset accompanies the paper: BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Tri...
misc
584
Dataset
Stage
Downloads
BEAT 0 0
BEAT Training Dataset This dataset accompanies the paper: BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Tri...
misc
584
PersistBD 0 0
PersistBD Dataset This dataset accompanies the paper "Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training" (EMNLP...
misc
152
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration