2 papers
cs.LG2026
Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery
Luoyu Chen, Xiaoyu Ding, Weiqi Wang +4
Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands of carrie…
cs.CV2026
YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
Zhe Li, Xiaoyu Ding, Jiaxin Zheng +1
Neural Architecture Search (NAS) for object detection is severely bottlenecked by high evaluation cost, as fully training each candidate YOLO architecture on COCO demands days of G…