Tag: adversarial machine learning
Browse our exclusive articles!
TinySSL: Self-Supervised Learning for Sub-MB MCU Models
Discover TinySSL, a novel self-supervised learning method boosting performance of sub-megabyte microcontroller models with efficient distillation.
DOSER: Diffusion-Based OOD Detection in Offline RL
Discover DOSER, a diffusion-based method for accurate out-of-distribution detection and selective regularization in offline reinforcement learning.
Weakly Supervised Concept Learning for Object Reasoning
Discover a novel weakly supervised method enhancing object-centric visual reasoning with minimal labeled data and strong domain generalization.
Robust OOD Detection with Synergistic Score Smoothing
Discover ROSS, a robust out-of-distribution detection framework using median smoothing to enhance accuracy and defend against adversarial attacks.
Entropy Minimization for Test-Time Adaptation in Autoregressive Models
Explore a unified entropy minimization framework enhancing test-time adaptation in autoregressive models, validated on Whisper ASR across 20+ domains.