Flownomaly recovers normal features for few-shot anomaly detection
In the 1-shot setting, image-level AUROC reached 97.8% on MVTec-AD and 95.3% on VisA.
5 stories, newest first · one card per story
In the 1-shot setting, image-level AUROC reached 97.8% on MVTec-AD and 95.3% on VisA.
Approximate Pareto Optimality learns shared aligner initializations for few-shot LLM personalization from 20 examples.
ENCORE turns a few robot demonstrations into frozen manipulation policies without leaking the success signal.
APPL uses each skill policy's structural prior so robots compose skills and generalize from few demonstrations.
ToneCL reaches 91.6% few-shot Mandarin tone accuracy using contrastive pretraining on unlabeled speech.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views